diff --git a/devlog/_plan/260923_grok47_parity/000_plan.md b/devlog/_plan/260923_grok47_parity/000_plan.md new file mode 100644 index 00000000000..36e98e1cdba --- /dev/null +++ b/devlog/_plan/260923_grok47_parity/000_plan.md @@ -0,0 +1,122 @@ +# 260923 grok-4.7 parity — plan + +grok-4.7 shipped on 2026-09-21 and already answers through xAI, Devin, Command Code and Cursor, but OpenCodex has no +registry entry for it: the picker shows it without a context window, reasoning ladder, image input, Fast row or +Responses wire, and cost estimates are unavailable. This unit gives grok-4.7 the same declarations grok-4.6 carries, +using values measured with real grok-4.7 calls (010_probe-evidence.md) and xAI's published model page, and applies +them to the other providers that serve it where their evidence supports each declaration. + +## Loop spec + +- Archetype: satisfy-spec, single work-phase (wp1), one PABCD cycle, one PR to dev. +- Trigger: user request 2026-09-23 "grok-4.7 모델 피커 컨텍스트 fast 와이어를 실제 토큰응답으로 ... grok-4.6과 같이 패치하고 다른 프로바이더들에도 적용하는 pr". +- Goal: grok-4.7 has grok-4.6-equivalent picker/context/effort/image/Fast/wire/price metadata on xAI, plus Devin, + Command Code, Cursor, OpenCode Go and bundled gateway metadata where evidenced. +- Non-goals: changing default or sidecar models (web-search defaults stay grok-4.6); grok-4.7-build-fast; GitHub + Copilot wire pin and OpenCode Go hosted web_search strip for 4.7 (no probe possible, not configured locally); + merge, release, service restart. The user forbade local tests: no bun test, typecheck or build runs locally. +- Verifier: static only locally — `git diff --check`, JSON parse of edited JSON, `rg` roster consistency (every + grok-4.6 xAI-block key has a grok-4.7 sibling), byte-equality of regenerated metadata via the generator script + (codegen, not a test); then exact-head hosted CI on the PR (typecheck + 4 test shards + file-size + layout). +- Stop: PR open, independent review has no unresolved blocker, exact-head CI reported. +- Memory artifact: this unit (000/010), goalplan add-grok-4-7-to-opencodex-with-the-same-first-cl. +- Expected terminal outcomes: DONE (PR open, CI green or failures fixed); BLOCKED if push refused. +- Escalation: a CI failure that needs a local run to diagnose, or a design dispute that requires changing a default. +- HOTL bounds: tools = repo edits, gh, live proxy probes already done; write scope = files listed below; no token or + time budget was set by the user. + +## Architect consultation + +Handle 01a0caad-1195-74b3-8338-e7a354313b5d (Banach, gpt-6-sol). Proposal D1–D8. Dispositions: + +- D1 accept (xAI declarations, grok-4.7 ahead of 4.6 in XAI_MODELS). +- D2 amended in revision 3 (see Audit round 1 synthesis): toggle set unchanged; 4.7 gets the OAuth Responses default + through modelWireDefaults only. +- D3 accept (Devin roster, 500k, measured low..max ladder, default medium). +- D4 accept: add xai/grok-4.7 and xai/grok-4.6 to COMMAND_CODE_IMAGE_MODELS; the 4.6 negative is contradicted by the + same two-path grid probe the header demands. +- D5 amend: OpenCode Go wire/efforts/default ARE mirrored — opencode.ai/docs/go lists "Grok 4.7 grok-4.7 + https://opencode.ai/zen/go/v1/responses @ai-sdk/openai", the same documented evidence the 4.6 pin (#3394) used. + The Go web_search strip and the Copilot Responses pin stay 4.6-only (unprobed; recorded as follow-ups). +- D6 amend: Cursor's live GetUsableModels roster (explorer 01a0caad-9fb2-70a1-9cf5-120ad392775f) lists + grok-4.7-{low,medium,high,xhigh} and the same with -fast, no cursor- prefix, no max. Mirror with no wirePrefix and + keep the prefix condition 4.5/4.6-only. Context: Cursor's API reports no window; 4.6's 500k is likewise the model's + published window, so 4.7 gets 500k from xAI's page and the measured xAI limit. +- D7 accept for xAI prices; OpenRouter's distinct prices arrive through the regenerated bundled metadata rather than + a new overlay (4.6 has no OpenRouter overlay either). Devin-cli gets a derived row only if DEVIN_GROK equals xAI's + list price, labeled derived like the GPT-6 rows. +- D8 accept. + +Reflection: see "Reflection" below. + +## File change map (dependency order) + +1. src/providers/registry/model-seeds.ts — XAI_MODELS: insert "grok-4.7" before "grok-4.6". + COMMAND_CODE_IMAGE_MODELS: add "xai/grok-4.6" and "xai/grok-4.7" with the probe note; drop xai/grok-4.6 from the + verified-negative header list (both mentions). +2. src/providers/registry/entries-core.ts, xai block: modelSupportsServiceTier, modelWireDefaults (oauth, responses + inbound), modelInputModalities, preserveReasoningContentModels, modelReasoningEfforts [low..xhigh], + modelDefaultReasoningEfforts high, modelContextWindows 500_000 — each with a grok-4.7 sibling of 4.6; comments cite + devlog/_plan/260923_grok47_parity/010_probe-evidence.md. Devin block: add "grok-4-7" after "grok-4-6" in models. + OpenCode Go block: modelWireDefaults, modelReasoningEfforts, modelDefaultReasoningEfforts for grok-4.7. +3. src/adapters/devin/live-models.ts — DEVIN_MODEL_CONTEXT_WINDOWS "grok-4-7": 500_000; DEVIN_MODEL_EFFORTS (if it + has per-model entries) "grok-4-7": low..max, default medium if a default map exists. +4. (removed in revision 3 — see Audit round 1 synthesis; xai-responses-opt-in.ts is unchanged) +5. src/usage/expected-prices.ts — xai grok-4.7 base {2,6,0.5,0}, priority 2x rule list gains grok-4.7, >=200k + UNIFORM_DOUBLE row with confirmedPriorityRelation lower-bound; devin-cli grok-4-7 conditional (D7). +6. src/adapters/cursor/{catalog.ts,effort-map.ts,discovery.ts} — "grok-4.7" capability (displayName "Cursor Grok + 4.7", CONTEXT_500K, no wirePrefix, regular+fast low..xhigh), tiers for "grok-4.7" and "grok-4.7-fast", heuristic + window 500_000 for grok-4.7 ids. Verify the Fast path emits flattened grok-4.7--fast (accepted live) and + not the bare grok-4.7-fast (not_found live). +7. scripts/model-metadata.source.json + src/generated/model-metadata.ts — add grok-4.7 rows beside each existing + grok-4.6 row for providers whose current models.dev entry lists 4.7 (xai, opencode-go, opencode, openrouter, kilo, + vercel, zenmux if present), copying that provider's live models.dev record; regenerate with + scripts/generate-model-metadata.ts. +8. Tests (hosted CI runs them): tests/providers/provider-registry-parity.test.ts:1259 default-effort map; + tests/service/service-tier-capability.test.ts:125; tests/usage/usage-cost.test.ts:939; an xAI + wire-default case for 4.7 (OAuth Responses inbound resolves openai-responses; explicit modelAdapters Chat wins); command-code vision assertion + (tests/providers/command-code-provider.test.ts:219 flips 4.6 to image-capable); cursor effort/Fast wire-id cases for + 4.7; opencode-go Responses wire case for 4.7. codex-catalog.test.ts is at its cap: no edits there. +9. Docs: docs-site guides/codex-app-models.md model table (+ locales), reference/configuration/providers.md xAI Responses + default note if it lists models (the opt-in toggle list stays 4.5/4.6); structure/providers/xai-grok.md Fast set, structure/transports/responses.md:418, + structure/providers/cursor.md grok row. + +## Acceptance + +- A1 every xai-block map that names grok-4.6 also names grok-4.7 with the measured value (rg check). +- A2 Cursor 4.7 wire ids equal the live roster: regular grok-4.7-, Fast grok-4.7--fast, no cursor- prefix. +- A3 (removed in revision 3): toggle set unchanged; xai-transport and management toggle tests stay as they are. +- A4 generated metadata byte-matches the generator output (codegen run + model-metadata-sync test in CI). +- A5 hosted CI green at the PR head, or failures diagnosed and fixed. + + +## Reflection + +Architect 01a0caad-1195-74b3-8338-e7a354313b5d on revision 1: MISALIGNED (narrow), D1–D8 all mapped. Gaps and +dispositions: + +- OpenRouter >=200k band rule: rebutted. `src/usage/expected-prices.ts` carries no OpenRouter context tier for any + model, including grok-4.6 whose OpenRouter entry publishes the same kind of override band. Adding one only for 4.7 + would create a new, inconsistent pattern; it belongs in a separate change that covers OpenRouter tiers as a whole. + Recorded as a follow-up. +- Broken evidence pointer (010 -> 010_plan.md): fixed to 000_plan.md, and the Cursor Fast success / bare-id + rejection recorded in 010_probe-evidence.md. +- Missing Reflection section: this section (revision 2). + + +## Audit round 1 synthesis (revision 3) + +Reviewer 01a0cab4-38a2-7ec0-8de2-02c1982a4345: FAIL, 2 High, both caused by D2 (4.7 joining the Responses toggle). + +Root cause: `XAI_RESPONSES_OPT_IN_MODELS` is the scope of a legacy compatibility switch (dashboard copy +"Grok 4.5 and 4.6", management write path provider-routes.ts:449, v1 migration). grok-4.6's actual Responses +default comes from `modelWireDefaults` (entries-core.ts:264), and that is the declaration parity requires. + +D2 amended (before -> after): before, 4.7 joins the toggle set and the migration gets a separate legacy list; after, +the toggle set, its migration, the GUI copy and the management tests stay unchanged, and 4.7 receives the same OAuth +Responses default through `modelWireDefaults` only. A user who wants 4.7 on Chat sets +`modelAdapters["grok-4.7"]="openai-chat"`, which always wins (the same escape hatch the Go/Copilot pins document). +Consequences: blocker 1 (xai-transport.test.ts:85, management-provider-validation.test.ts:4102/4123) and blocker 2 +(gui/src/i18n copy, ProviderAuthPanel mixed state) no longer arise; plan step 4 is removed, and so is acceptance A3. +Non-blocking note folded: DEVIN_STATIC_MODELS (src/adapters/devin/live-models.ts:18) gains "grok-4-7". +The proposed "grok-4-6" fallback entry was removed because its Devin-specific ladder was not measured. diff --git a/devlog/_plan/260923_grok47_parity/010_probe-evidence.md b/devlog/_plan/260923_grok47_parity/010_probe-evidence.md new file mode 100644 index 00000000000..86340dad256 --- /dev/null +++ b/devlog/_plan/260923_grok47_parity/010_probe-evidence.md @@ -0,0 +1,51 @@ +# Live probe evidence — grok-4.7 (2026-09-23 KST) + +Mechanics: POST /v1/responses on the running proxy (127.0.0.1:10100, ocx 2.62.0), then `ocx logs --json` for the +matching attempt (adapter, credentialSource, reasoningWireField/Value, tierOutcome, usage). xAI traffic used the Grok +OAuth lane (credentialSource "grok-oauth"); no API key was involved. The Responses-wire and `--fast` rows used a +temporary `providers.xai.modelAdapters["grok-4.7"]="openai-responses"` plus +`modelSupportsServiceTier["grok-4.7"]=true` override, applied through the attested provider reload +(`notifyRunningProxy("xai")`, the path `ocx login` uses) and removed the same way afterwards; the restored maps were +compared against a pre-probe backup. Scratch scripts lived in the gitignored `.tmp/`. + +## xAI grok-4.7 (Grok OAuth) + +| Probe | Chat wire (provider default) | Responses wire (temporary override) | +|---|---|---| +| effort low / medium / high / xhigh | 200, sent as `reasoning_effort` | 200 on all four | +| effort max | 400 `Invalid reasoning effort.` | 400 `Invalid reasoning effort.` | +| effort none | 200, but 640 reasoning tokens: the proxy omits the field and the model still reasons | not probed | +| image, user message (3x3 random color grid, 180x180 PNG) | 9/9 | — | +| image, tool result (same grid inside function_call_output) | 9/9 | — | +| caller `service_tier: "priority"` | 200, wire service-tier priority, response tier priority | 200, applied/confirmed, response tier priority | +| `xai/grok-4.7--fast` | — | 200, fastOutcome applied, confirmation confirmed, response tier priority | +| 530,000-word prompt | 400 `context_length_exceeded`: "531243 tokens > 500000 tokens" | — | + +Upstream model name on the Responses wire is `grok-4.7-build` (grok-4.6 reports `grok-4.6-build` the same way). + +Billing parity: the Responses `cost_in_usd_ticks` fits these per-token rates exactly across every probe, for both models: +default input 6800, cached input 1700, output 20400 ticks; priority input 40000, cached 10000, output 120000 ticks. +grok-4.6 probed in the same window produced identical rates (e.g. 83 uncached + 128 cached input, 58 output = +1,965,200 ticks). The OAuth subscription is not per-token billed, so these ticks are recorded as parity evidence only; +the key-auth prices below come from xAI's published page. + +Published (docs.x.ai/developers/models/grok-4.7, read 2026-09-23): 500,000 context; reasoning effort +low/medium/high (default)/xhigh, reasoning cannot be disabled; text+image input; $2.00 input, $0.50 cached, +$6.00 output per 1M; prompts over 200k tokens $4.00 / $1.00 / $12.00; Responses and Chat Completions. +models.dev `xai/grok-4.7`: output limit 500,000 (same as grok-4.6), released 2026-09-21. + +## Other providers + +| Provider | Evidence | Result | +|---|---|---| +| devin (`grok-4-7`) | live probe 200 at low and xhigh; tool-result grid 9/9; proxy /v1/models from Devin's live catalog: context 500000, input text+image, efforts low/medium/high/xhigh/max, default medium | exposes | +| command-code (`xai/grok-4.7`) | live probe 200; grid 9/9 on user-message and tool-result paths; COMMAND_CODE_TEXT_ONLY_MODELS is empty and the logs show no vision-sidecar request, so the route read the image natively | exposes, native image | +| cursor (`grok-4.7`) | live probe 200 through the cursor adapter; live GetUsableModels lists grok-4.7-{low,medium,high,xhigh} and the same ids with -fast (no cursor- prefix, no max); probes: grok-4.7-low and grok-4.7-xhigh-fast accepted, bare grok-4.7-fast rejected not_found (see 000_plan.md D6) | exposes | +| opencode-go / opencode-zen | public `/zen/go/v1/models` and `/zen/v1/models` list `grok-4.7` | listed (not configured locally, not probed) | +| openrouter | public API `x-ai/grok-4.7`: 500000 ctx, max completion 450000, $1.6/$4.8/$0.4, >=200k $3.2/$9.6/$0.8, text+image+file | listed (not probed) | +| github-copilot | models.dev `grok-4.7`: ctx 500000, input 372000, output 128000 | listed (not configured locally) | +| kilo, vercel | models.dev lists kilo `x-ai/grok-4.7` and vercel `spacexai/grok-4.7` | listed | + +Command Code `xai/grok-4.6` is included in `COMMAND_CODE_IMAGE_MODELS`: it read the grids 9/9 +(user message) and 8/9 (tool result) without a vision sidecar. The registry accepts native image +input; 8/9 remains the measured limitation on the tool-result path. diff --git a/docs-site/src/content/docs/fr/guides/codex-app-models.md b/docs-site/src/content/docs/fr/guides/codex-app-models.md index 28fa0ee8a39..0e69068a714 100644 --- a/docs-site/src/content/docs/fr/guides/codex-app-models.md +++ b/docs-site/src/content/docs/fr/guides/codex-app-models.md @@ -143,8 +143,8 @@ approximation fondée sur un ancien modèle d'entrée. | Connexion Codex (ligne Daybreak transférée explicitement) | `openai/gpt-daybreak-blue-latest` uniquement lorsque l'entrée `customModels` exacte est configurée sur le fournisseur canonique `openai`. Elle conserve l'identifiant Daybreak transmis et utilise l'instantané de capacités Sol épinglé (contexte de 372 000 jetons ; compactage automatique à 334 800 jetons). | | OpenAI (clé API) | Exactement dix lignes avec espace de noms : `gpt-5.5`, `gpt-5.6`, Sol/Terra/Luna, les trois identifiants virtuels `*-pro` et les deux alias Daybreak (contexte de 1 050 000 jetons ; entrée maximale de 922 000 jetons pour les dix) | | OpenRouter | `openrouter/openai/gpt-5.6-sol`, `openrouter/openai/gpt-5.6-terra`, `openrouter/openai/gpt-5.6-luna` (1 050 000) | -| Cursor | Le repli statique comprend `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` et `cursor/gpt-5.6-luna` (1 000 000), ainsi que des lignes ordinaires/rapides pour Grok 4.5 et 4.6 (500 000) ; 4.6 ajoute `xhigh`, et la découverte dynamique propre au compte détermine quelles lignes restent visibles. | -| xAI | La découverte dynamique fait autorité. Le catalogue de secours comprend `xai/grok-4.6` et utilise `xai/grok-4.5` par défaut ; les deux ont une fenêtre de 500 000 jetons. Grok 4.6 propose `low` / `medium` / `high` / `xhigh` (valeur amont par défaut : `high`), tandis que Grok 4.5 s'arrête à `high`. | +| Cursor | Le repli statique comprend `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` et `cursor/gpt-5.6-luna` (1 000 000), ainsi que des lignes ordinaires/rapides pour Grok 4.5, 4.6 et 4.7 (500 000) ; 4.6 et 4.7 ajoutent `xhigh`, et la découverte dynamique propre au compte détermine quelles lignes restent visibles. | +| xAI | La découverte dynamique fait autorité. Le catalogue de secours comprend `xai/grok-4.6` et `xai/grok-4.7` et utilise `xai/grok-4.5` par défaut ; les trois ont une fenêtre de 500 000 jetons. Grok 4.6 et 4.7 proposent `low` / `medium` / `high` / `xhigh` (valeur amont par défaut : `high`), tandis que Grok 4.5 s’arrête à `high`. | Les entrées GPT-5.6 épinglées préservent exactement l'échelle amont. Sol et Terra proposent les niveaux de `low` à `ultra` ; Luna s'arrête à `max`. Sol utilise `low` par défaut, contre `medium` pour Terra et Luna. diff --git a/docs-site/src/content/docs/fr/guides/providers.md b/docs-site/src/content/docs/fr/guides/providers.md index 7e9115e0033..da65598a8cf 100644 --- a/docs-site/src/content/docs/fr/guides/providers.md +++ b/docs-site/src/content/docs/fr/guides/providers.md @@ -622,12 +622,13 @@ Cursor est géré séparément comme adaptateur expérimental. `adapter: "cursor le sélecteur **Ajouter un fournisseur** du tableau de bord comme entrée expérimentale de la configuration locale, avec les métadonnées du catalogue statique de repli de Cursor. Lorsqu'un jeton d'accès Cursor est configuré, opencodex utilise le transport HTTP/2 direct de Cursor. Sa liste de repli intégrée comprend `gpt-5.6-sol` / -`terra` / `luna` (contexte de 1M), les variantes ordinaires et Fast de Grok 4.5 et 4.6 (500K), ainsi que -`kimi-k3` (262K) ; la découverte en direct détermine celles qui restent visibles pour le compte. Grok 4.6 expose -`low` / `medium` / `high` / `xhigh` sous les deux formes, tandis que 4.5 s'arrête à `high`. Les requêtes Fast -envoient le modèle Grok de base correspondant avec des paramètres `effort` et `fast=true` `requested_model` -distincts ; les identifiants aplatis `cursor-grok-{version}-{effort}-fast` servent uniquement à la découverte et -à la sélection. Cursor ne fournit Kimi K3 qu'avec des identifiants de protocole suffixés par l'effort ; +`terra` / `luna` (contexte de 1M), les variantes ordinaires et Fast de Grok 4.5, 4.6 et 4.7 (500K), ainsi que +`kimi-k3` (262K) ; la découverte en direct détermine celles qui restent visibles pour le compte. Grok 4.6 et 4.7 exposent +`low` / `medium` / `high` / `xhigh` sous les deux formes, tandis que 4.5 s'arrête à `high`. Pour Grok 4.5 et 4.6, +les requêtes Fast envoient le modèle de base avec des paramètres `effort` et `fast=true` distincts dans +`requested_model` ; leurs identifiants aplatis `cursor-grok-{version}-{effort}-fast` servent uniquement à la découverte +et à la sélection. Grok 4.7 figure sans préfixe `cursor-` et envoie directement `grok-4.7-{effort}-fast`. +Cursor ne fournit Kimi K3 qu'avec des identifiants de protocole suffixés par l'effort ; `cursor/kimi-k3` expose donc une échelle `low` / `high` / `max` avec `max` par défaut, conformément à la valeur par défaut documentée de l'API du modèle. L'exécution native read/write/delete/ls/grep/shell/fetch pilotée par le serveur Cursor est désactivée par défaut, car elle contourne le parcours d'approbation et le bac à sable de diff --git a/docs-site/src/content/docs/fr/reference/configuration/providers.md b/docs-site/src/content/docs/fr/reference/configuration/providers.md index c4fd2dc57de..00de2eea8b2 100644 --- a/docs-site/src/content/docs/fr/reference/configuration/providers.md +++ b/docs-site/src/content/docs/fr/reference/configuration/providers.md @@ -119,7 +119,7 @@ sauvegarde dont le contenu diffère, puis réécrit en identifiants sans préfix | `modelSupportsReasoningSummaries?` | `Record` | Définissez un modèle sur `false` pour arrêter la publicité des résumés et supprimer les champs de livraison du résumé. | | `modelReasoningSummaryDelivery?` | `Record` | Énumération de livraison des réponses par modèle ; réécrit un champ de livraison existant. | | `modelAdapters?` | `Record` | Remplacement du protocole `openai-chat` ou `openai-responses` par modèle pour les passerelles multiprotocoles. Les entrées explicites priment sur les valeurs par défaut du registre. Le préréglage OpenCode Go sélectionne Responses pour `gpt-5.6-luna` tout en laissant les modèles apparentés sur leurs protocoles documentés ; DeepSeek peut sélectionner Responses natif pour `deepseek-v4-flash` ; GitHub Copilot déclare des valeurs par défaut limitées à Responses pour ces modèles (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`), car ces modèles rejettent `/chat/completions` pour le trafic des agents. Les modèles sans valeur intégrée par défaut, comme `gpt-5.4-nano`, peuvent être activés ici. Les services en amont à protocole unique et le transfert canonique ChatGPT rejettent ces remplacements. | -| Activation Responses xAI (tableau de bord) | interrupteur | Pour `xai` uniquement, définit ou efface atomiquement les entrées `modelAdapters` de `grok-4.5` et `grok-4.6`. Une seule entrée apparaît comme un état mixte jusqu’à la prochaine écriture. Les autres remplacements et le comportement des tiers restent inchangés. | +| Activation Responses xAI (tableau de bord) | interrupteur | Pour `xai` uniquement, définit ou efface atomiquement les entrées `modelAdapters` de `grok-4.5` et `grok-4.6`. Une seule entrée apparaît comme un état mixte jusqu’à la prochaine écriture. Les autres remplacements et le comportement des tiers restent inchangés. Grok 4.7 utilise Responses par défaut sur OAuth via le registre et peut passer à Chat avec une entrée explicite `modelAdapters["grok-4.7"] = "openai-chat"`. | | `xaiResponsesXSearch?` | `boolean` | Désactivé par défaut. Sur une destination xAI Responses, ajoute la déclaration `x_search` hébergée par le fournisseur uniquement lorsqu’un outil `web_search` actif subsiste après la normalisation finale de la requête. Les déclarations existantes ne sont pas dupliquées, les sélecteurs `tool_choice`/`allowed_tools` de l’appelant ne sont jamais élargis, et cette option est distincte des options `search.xSearch` du service auxiliaire de recherche web. | | `modelPreferHostedTools?` | `Record` | Activation explicite par modèle exact pour les passerelles Responses hors transfert qui réservent un espace de noms aux outils hébergés. Seul `["image_generation"]` est actuellement accepté ; le modèle correspondant doit utiliser le protocole `openai-responses` et prendre en charge cet outil hébergé. Le proxy supprime les déclarations clientes `image_gen` en conflit et réécrit leurs sélecteurs afin de préserver le choix d'outil de l'appelant. Pour les modèles virtuels `-pro` de l'API OpenAI, l'identifiant public sélectionné est comparé en premier et l'identifiant résolu du modèle de base sur le protocole sert de repli. `modelAdapters` résout d'abord l'identifiant public, puis celui de base ; la seconde résolution détermine le protocole final. Les autres modèles conservent le comportement normal des alias. | | `annotateEmptyToolOutputs?` | `boolean` | Remplace un résultat d’outil présent mais vide par un court marqueur avant qu’il n’atteigne le modèle, afin qu’un résultat vide ne soit pas interprété comme manquant. S’applique aux chaînes vides et aux tableaux de parties contenant uniquement du texte ; les parties d’image, de fichier et chiffrées ne sont jamais modifiées. La valeur par défaut issue du registre intégré est `true` pour DeepSeek ; dans les autres cas, elle n’est pas définie. Définissez `false` pour exclure un fournisseur : une valeur `false` explicite est conservée lors des modifications ultérieures qui omettent ce champ. `PATCH /api/providers?name=` accepte `true`, `false` ou `null` pour effacer le remplacement et revenir au comportement par défaut du registre. | @@ -364,6 +364,10 @@ hôte partagé. Laissez l'exécution locale désactivée, sauf si tous les appel acceptez le contournement des autorisations Codex et de la sémantique du bac à sable. ::: +## Grok 4.7 sur xAI + +Grok 4.7 propose le mode Fast sur OAuth, avec `low` / `medium` / `high` / `xhigh` et une fenêtre de 500 000 jetons. Son [tarif xAI](https://docs.x.ai/developers/models/grok-4.7) standard par million de jetons est de 2,00 $ en entrée, 0,50 $ en entrée mise en cache et 6,00 $ en sortie ; à partir de 200 000 jetons de contexte, les tarifs sont de 4,00 $ / 1,00 $ / 12,00 $. + ## Routage des fournisseurs OpenRouter OpenRouter peut servir un modèle au moyen de plusieurs fournisseurs d'inférence. `openRouterRouting` maintient les diff --git a/docs-site/src/content/docs/guides/codex-app-models.md b/docs-site/src/content/docs/guides/codex-app-models.md index 84913591709..2c14db97c6f 100644 --- a/docs-site/src/content/docs/guides/codex-app-models.md +++ b/docs-site/src/content/docs/guides/codex-app-models.md @@ -226,8 +226,8 @@ metadata instead of an older-template approximation. | Codex login (explicit Daybreak forward row) | `openai/gpt-daybreak-blue-latest` only when the exact `customModels` row is configured on the canonical `openai` provider. It keeps the Daybreak wire id and uses the pinned Sol capability snapshot (922,000 context; 829,800 automatic compaction). | | OpenAI (API key) | Exactly ten namespaced rows: `gpt-5.5`, `gpt-5.6`, Sol/Terra/Luna, the three `*-pro` virtual ids, and the two Daybreak aliases (1,050,000 context; 922,000 max input for all ten) | | OpenRouter | `openrouter/openai/gpt-5.6-sol`, `openrouter/openai/gpt-5.6-terra`, `openrouter/openai/gpt-5.6-luna` (922,000) | -| Cursor | Static fallback includes `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra`, and `cursor/gpt-5.6-luna` (1,000,000), plus regular/Fast rows for Grok 4.5 and 4.6 (500,000); 4.6 adds `xhigh`, and live account discovery decides which rows remain visible. | -| xAI | Live discovery is authoritative. The fallback catalog includes `xai/grok-4.6` and defaults to `xai/grok-4.5`; both have 500,000-token windows. Grok 4.6 exposes `low` / `medium` / `high` / `xhigh` (upstream default: `high`), while Grok 4.5 stops at `high`. | +| Cursor | Static fallback includes `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra`, and `cursor/gpt-5.6-luna` (1,000,000), plus regular/Fast rows for Grok 4.5, 4.6, and 4.7 (500,000); 4.6 and 4.7 add `xhigh`, and live account discovery decides which rows remain visible. | +| xAI | Live discovery is authoritative. The fallback catalog includes `xai/grok-4.6` and `xai/grok-4.7` and defaults to `xai/grok-4.5`; all three have 500,000-token windows. Grok 4.6 and 4.7 expose `low` / `medium` / `high` / `xhigh` (upstream default: `high`), while Grok 4.5 stops at `high`. | The pinned GPT-5.6 entries preserve the exact upstream ladder. Sol and Terra expose `low` through `ultra`; Luna stops at `max`. Sol defaults to `low`, while Terra and Luna default to `medium`. diff --git a/docs-site/src/content/docs/guides/providers.md b/docs-site/src/content/docs/guides/providers.md index e8cba6c928d..749ab98affb 100644 --- a/docs-site/src/content/docs/guides/providers.md +++ b/docs-site/src/content/docs/guides/providers.md @@ -1026,11 +1026,13 @@ fallback model catalog metadata. When a Cursor access token is configured, openc live HTTP/2 transport. Set `upstreamHttpVersion: "http1.1"` when a proxy requires Cursor's HTTP/1.1 compatibility path; the setting covers both inference and live model discovery and is exposed at **Providers → Cursor → Settings → Cursor transport**. Its bundled fallback seed includes `gpt-5.6-sol` / `terra` / `luna` (1M context), -regular/Fast rows for Grok 4.5 and 4.6 (500K), and `kimi-k3` (262K); live discovery decides which -remain visible for the account. Grok 4.6 exposes `low` / `medium` / `high` / `xhigh` in both forms, -while 4.5 stops at `high`. Fast requests send the matching base Grok model with separate `effort` -and `fast=true` `requested_model` parameters; flattened `cursor-grok-{version}-{effort}-fast` ids -are discovery and picker identities only. Cursor serves Kimi K3 only as effort-suffixed wire ids, so +regular/Fast rows for Grok 4.5, 4.6, and 4.7 (500K), and `kimi-k3` (262K); live discovery decides which +remain visible for the account. Grok 4.6 and 4.7 expose `low` / `medium` / `high` / `xhigh` in both forms, +while 4.5 stops at `high`. Grok 4.5 and 4.6 Fast requests send the matching base model with separate +`effort` and `fast=true` `requested_model` parameters; their flattened +`cursor-grok-{version}-{effort}-fast` ids are discovery and picker identities only. Grok 4.7 is listed +without the `cursor-` prefix and sends `grok-4.7-{effort}-fast` directly. Cursor serves Kimi K3 only as +effort-suffixed wire ids, so `cursor/kimi-k3` exposes a `low` / `high` / `max` ladder and defaults to `max`, matching the model's documented API default. Cursor server-driven native read/write/delete/ls/grep/shell/fetch execution is disabled by default because it bypasses Codex's approval and sandbox path; set diff --git a/docs-site/src/content/docs/ja/guides/codex-app-models.md b/docs-site/src/content/docs/ja/guides/codex-app-models.md index fa3bc09fcb6..63d62a27364 100644 --- a/docs-site/src/content/docs/ja/guides/codex-app-models.md +++ b/docs-site/src/content/docs/ja/guides/codex-app-models.md @@ -56,8 +56,8 @@ visibility = "list" | Codex ログイン (account-qualified 行が有効で、有効な selector あり) | 有効な selector とサポート対象 native model の各組み合わせに `/` 行を表示します。各行は対応付けられたアカウントだけを使用し、bare native 行はピッカーで非表示になります。Native metadata と context window は保持されます。 | | OpenAI (API キー) |正確に 8 つの名前空間行: `gpt-5.5`、`gpt-5.6`、Sol/Terra/Luna、および 3 つの `*-pro` 仮想 ID (コンテキスト 922,000、8 つすべての最大入力 922,000) | |オープンルーター | `openrouter/openai/gpt-5.6-sol`、`openrouter/openai/gpt-5.6-terra`、`openrouter/openai/gpt-5.6-luna` (922,000) | -| Cursor | 静的フォールバックには `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna` (1,000,000) と、Grok 4.5 / 4.6 の通常・Fast 行 (500,000) が含まれます。4.6 は `xhigh` も公開し、ライブアカウントの検出によって表示される行が決まります。 | -|かおるライブディスカバリーには信頼性があります。フォールバック カタログのデフォルトは、500,000 トークン ウィンドウと `low` / `medium` / `high` 推論制御を備えた `xai/grok-4.5` です。 | +| Cursor | 静的フォールバックには `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna` (1,000,000) と、Grok 4.5 / 4.6 / 4.7 の通常・Fast 行 (500,000) が含まれます。4.6 と 4.7 は `xhigh` も公開し、ライブアカウントの検出によって表示される行が決まります。 | +| xAI | xAI のライブ検出が優先されます。フォールバックには `xai/grok-4.6` と `xai/grok-4.7` が含まれ、デフォルトは `xai/grok-4.5` です。3 モデルともコンテキストは 500,000 トークンです。Grok 4.6 と 4.7 は `low` / `medium` / `high` / `xhigh`（上流のデフォルトは `high`）を提供し、Grok 4.5 は `high` までです。 | 固定された GPT-5.6 エントリは、正確な上流ラダーを保存します。 Sol と Terra は `low` から `ultra` を公開します。ルナは`max`で止まります。 Sol のデフォルトは `low`、Terra と Luna のデフォルトは `medium` です。 `ultra` は、最大限の推論とプロアクティブな委任を目的としたクライアント向けの選択肢であり、`max` としてバックエンドに到達します。ピッカーのエントリは、カタログの準備ができていることを意味するだけです。接続されたアカウントまたは API キーには、そのモデルを使用する資格がまだある必要があります。 diff --git a/docs-site/src/content/docs/ja/guides/providers.md b/docs-site/src/content/docs/ja/guides/providers.md index adad28ad00c..9b4fbc5378d 100644 --- a/docs-site/src/content/docs/ja/guides/providers.md +++ b/docs-site/src/content/docs/ja/guides/providers.md @@ -443,11 +443,13 @@ Cursor は別の実験的アダプターとして追跡します。`adapter: "cu Provider ピッカーに実験的 local config 項目として表示され、Cursor の静的フォールバックモデルカタログ メタデータを保存します。Cursor アクセストークンを設定すると opencodex は Cursor ライブ HTTP/2 トランスポートを 使います。バンドル済みフォールバックリストには 1M コンテキストの `gpt-5.6-sol` / `terra` / `luna`、500K コンテキストの -Grok 4.5 / 4.6 の通常・Fast 行、262K コンテキストの `kimi-k3` が含まれ、ライブ探索結果に基づき現在の -アカウントに表示するモデルを決定します。Grok 4.6 は両形式で `low` / `medium` / `high` / `xhigh` を公開し、 -4.5 は `high` までです。Fast リクエストは対応する Grok ベースモデルを、独立した `effort` と `fast=true` の -`requested_model` パラメータとともに送信します。平坦化された `cursor-grok-{version}-{effort}-fast` id は -探索と picker の識別子としてのみ使われます。Cursor は Kimi K3 を effort サフィックス付きの wire id +Grok 4.5 / 4.6 / 4.7 の通常・Fast 行、262K コンテキストの `kimi-k3` が含まれ、ライブ探索結果に基づき現在の +アカウントに表示するモデルを決定します。Grok 4.6 と 4.7 は両形式で `low` / `medium` / `high` / `xhigh` を公開し、 +4.5 は `high` までです。Grok 4.5 と 4.6 の Fast リクエストは、対応するベースモデルを独立した `effort` と +`fast=true` の `requested_model` パラメータとともに送信します。これらの平坦化された +`cursor-grok-{version}-{effort}-fast` id は探索と picker の識別子としてのみ使われます。Grok 4.7 は +`cursor-` プレフィックスなしで一覧に表示され、`grok-4.7-{effort}-fast` を直接送信します。 +Cursor は Kimi K3 を effort サフィックス付きの wire id としてのみ提供するため、`cursor/kimi-k3` は `low` / `high` / `max` のラダーを公開し、既定値はモデル ドキュメントの API 既定値と同じ `max` です。Cursor サーバーが直接送るネイティブ read/write/delete/ls/grep/shell/fetch 実行は Codex 承認とサンドボックス経路をバイパスするためデフォルトで無効です。信頼できるローカル実験でのみ diff --git a/docs-site/src/content/docs/ja/reference/configuration/providers.md b/docs-site/src/content/docs/ja/reference/configuration/providers.md index 7dacef8a955..6cb95631836 100644 --- a/docs-site/src/content/docs/ja/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ja/reference/configuration/providers.md @@ -112,7 +112,7 @@ account を削除しても mapping は保持され、同じ id を再追加す | `modelSupportsReasoningSummaries?` | `Record` |モデルを `false` に設定して、概要の広告を停止し、概要配信フィールドを削除します。 | | `modelReasoningSummaryDelivery?` | `Record` |モデルごとの応答配信列挙型。既存の配信フィールドを書き換えます。 | | `modelAdapters?` | `Record` | 混合配線ゲートウェイのモデルごとの `openai-chat` または `openai-responses` 配線オーバーライド。明示的なエントリはレジストリのデフォルトを破ります。DeepSeek のプリセットは `deepseek-v4-flash` のネイティブ Responses を選択でき、GitHub Copilot は モデル (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`) を Responses 専用デフォルトとして宣言します。これらのモデルはエージェント トラフィックで `/chat/completions` を拒否するためです。`gpt-5.4-nano` のようなビルトイン デフォルトのないモデルはここでオプトインできます。単線アップストリーム ピンと正規の ChatGPT 転送はオーバーライドを拒否します。 | -| xAI Responses オプトイン（ダッシュボード） | スイッチ | `xai` のみで、`grok-4.5` と `grok-4.6` の `modelAdapters` エントリを原子的に設定または削除します。片方だけの場合は、次のスイッチ操作で両方が正規化されるまで混合状態を表示します。他のオーバーライドと tier 動作は変わりません。 | +| xAI Responses オプトイン（ダッシュボード） | スイッチ | `xai` のみで、`grok-4.5` と `grok-4.6` の `modelAdapters` エントリを原子的に設定または削除します。片方だけの場合は、次のスイッチ操作で両方が正規化されるまで混合状態を表示します。他のオーバーライドと tier 動作は変わりません。 Grok 4.7 は OAuth でレジストリの既定値により Responses を使用し、明示的な `modelAdapters["grok-4.7"] = "openai-chat"` で Chat に切り替えられます。 | | `xaiResponsesXSearch?` | `boolean` | デフォルトでは無効です。xAI Responses の宛先では、最終的なリクエスト正規化後もライブの `web_search` ツールが残っている場合にのみ、プロバイダーがホストする `x_search` 宣言を追加します。既存の宣言は重複させず、呼び出し元の `tool_choice` / `allowed_tools` セレクターの範囲を拡張することもありません。また、これは `search.xSearch` オプションを持つウェブ検索サイドカーとは別です。 | | `modelPreferHostedTools?` | `Record` | hosted tool namespace を予約する非 forward Responses gateway 向けの完全一致モデル opt-in。現在は `["image_generation"]` のみを受け付けます。一致したモデルは `openai-responses` wire を使い、その hosted tool をサポートする必要があります。競合するクライアント `image_gen` 宣言を除去し、呼び出し元の tool choice を維持するため selector も書き換えます。OpenAI API の仮想 `-pro` モデルでは、まず選択した公開 ID に一致させ、解決後のベース wire-model ID をフォールバックとして使用します。`modelAdapters` は公開 ID、次にベース ID の順に解決し、後者の結果が最終 wire を決めます。未設定のモデルは通常の alias 動作を維持します。 | | `annotateEmptyToolOutputs?` | `boolean` | 存在するものの空であるツール結果を、モデルに届く前に短いマーカーへ置き換え、空白の結果が欠落した結果として解釈されないようにします。空文字列とテキストのみのパーツ配列に適用されます。画像、ファイル、暗号化されたパーツには一切手を加えません。組み込みレジストリでは `DeepSeek` のデフォルトが `true` で、それ以外は未設定です。プロバイダーを対象外にするには `false` を設定します。明示的な `false` は、後続の編集でこのフィールドが省略されても保持されます。`PATCH /api/providers?name=` は `true`、`false`、またはオーバーライドを消去してレジストリのデフォルト動作へ戻すための `null` を受け付けます。 | @@ -307,6 +307,10 @@ Anthropic アカウント ポリシーのリスクを理解していない限り デフォルトのループバック バインドでは、マルチユーザー ホスト上の他のユーザーを含む、認証なしのローカル プロセスを許可します。すべてのデータプレーン呼び出し元が信頼されており、Codex 承認とサンドボックス セマンティクスのバイパスを意図的に受け入れる場合を除き、ローカル exec はオフのままにしておきます。 ::: +## xAI の Grok 4.7 + +Grok 4.7 は OAuth で Fast を利用でき、`low` / `medium` / `high` / `xhigh` と 500,000 トークンのコンテキストを提供します。[xAI の標準料金](https://docs.x.ai/developers/models/grok-4.7)は 100 万トークンあたり入力 2.00 ドル、キャッシュ入力 0.50 ドル、出力 6.00 ドルです。コンテキストが 200,000 トークン以上の場合は 4.00 / 1.00 / 12.00 ドルになります。 + ## OpenRouter プロバイダーのルーティング OpenRouter は、複数の推論プロバイダーを通じて 1 つのモデルを提供できます。 `openRouterRouting` は優先プロバイダーでリクエストを保持します。 `modelOpenRouterRouting` は、正確なモデル ID に置き換えられます。キャッシュのサポート、保持、ヒット率、価格は推論プロバイダーによって異なるため、これはプロンプト キャッシュ アフィニティに役立ちます。 diff --git a/docs-site/src/content/docs/ko/guides/codex-app-models.md b/docs-site/src/content/docs/ko/guides/codex-app-models.md index 0a40e9eacfd..37781c6442d 100644 --- a/docs-site/src/content/docs/ko/guides/codex-app-models.md +++ b/docs-site/src/content/docs/ko/guides/codex-app-models.md @@ -109,8 +109,8 @@ GPT-5.6에만 사용합니다. 오래된 템플릿으로 근사하지 않고 모 | Codex 로그인(명시적 Daybreak forward 행) | canonical `openai` provider에 정확한 `customModels` 항목이 있을 때만 `openai/gpt-daybreak-blue-latest`를 표시합니다. Daybreak wire id를 유지하고 고정된 Sol capability snapshot(컨텍스트 922,000; 자동 압축점 922,000)을 사용합니다. | | OpenAI(API key) | 정확히 열 개의 네임스페이스 행: `gpt-5.5`, `gpt-5.6`, Sol/Terra/Luna, 세 개의 `*-pro` 가상 id, 두 Daybreak 별칭 (모두 컨텍스트 922,000; 최대 입력 922,000) | | OpenRouter | `openrouter/openai/gpt-5.6-sol`, `openrouter/openai/gpt-5.6-terra`, `openrouter/openai/gpt-5.6-luna` (922,000) | -| Cursor | 정적 폴백에는 `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra`, `cursor/gpt-5.6-luna` (1,000,000)와 Grok 4.5/4.6의 일반·Fast 항목(500,000)이 들어갑니다. 4.6은 `xhigh`도 노출하며, 실시간 계정 탐색이 어떤 항목을 계속 보일지 정합니다. | -| xAI | 실시간 탐색이 기준입니다. 폴백 카탈로그에는 `xai/grok-4.6`이 포함되며 기본값은 `xai/grok-4.5`입니다. 두 모델 모두 컨텍스트 창은 500,000입니다. Grok 4.6은 `low` / `medium` / `high` / `xhigh`(업스트림 기본값: `high`)를 제공하고, Grok 4.5는 `high`까지만 제공합니다. | +| Cursor | 정적 폴백에는 `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra`, `cursor/gpt-5.6-luna` (1,000,000)와 Grok 4.5/4.6/4.7의 일반·Fast 항목(500,000)이 들어갑니다. 4.6과 4.7은 `xhigh`도 노출하며, 실시간 계정 탐색이 어떤 항목을 계속 보일지 정합니다. | +| xAI | 실시간 탐색이 기준입니다. 폴백 카탈로그에는 `xai/grok-4.6`과 `xai/grok-4.7`이 포함되며 기본값은 `xai/grok-4.5`입니다. 세 모델 모두 컨텍스트 창은 500,000입니다. Grok 4.6과 4.7은 `low` / `medium` / `high` / `xhigh`(업스트림 기본값: `high`)를 제공하고, Grok 4.5는 `high`까지만 제공합니다. | 고정된 GPT-5.6 항목은 업스트림 ladder를 그대로 보존합니다. Sol과 Terra는 `low`부터 `ultra`까지 노출하고, Luna는 `max`에서 멈춥니다. Sol의 기본값은 `low`이고, Terra와 Luna의 기본값은 `medium`입니다. 명시적 diff --git a/docs-site/src/content/docs/ko/guides/providers.md b/docs-site/src/content/docs/ko/guides/providers.md index 0eea4be4b70..d691dcf6fc0 100644 --- a/docs-site/src/content/docs/ko/guides/providers.md +++ b/docs-site/src/content/docs/ko/guides/providers.md @@ -439,11 +439,13 @@ Cursor는 별도의 실험적 어댑터로 추적합니다. `adapter: "cursor"` Provider picker에 실험적 local config 항목으로 표시되며, Cursor의 static fallback model catalog metadata를 저장합니다. Cursor access token이 설정되면 opencodex는 Cursor live HTTP/2 transport를 사용합니다. 번들 폴백 목록에는 1M 컨텍스트의 `gpt-5.6-sol` / `terra` / `luna`, 500K 컨텍스트의 -Grok 4.5/4.6의 일반·Fast 항목, 262K 컨텍스트의 `kimi-k3`가 들어 있으며, 실시간 탐색 결과에 따라 -현재 계정에 표시할 모델을 결정합니다. Grok 4.6은 두 형식 모두 `low` / `medium` / `high` / `xhigh`를 -노출하고 4.5는 `high`까지만 노출합니다. Fast 요청은 일치하는 Grok 기본 모델과 별도의 `effort`, -`fast=true` `requested_model` 파라미터를 전송합니다. 평탄화된 `cursor-grok-{version}-{effort}-fast` id는 -탐색 및 picker 식별자로만 사용됩니다. Cursor는 Kimi K3를 effort 접미사가 붙은 wire id로만 +Grok 4.5/4.6/4.7의 일반·Fast 항목, 262K 컨텍스트의 `kimi-k3`가 들어 있으며, 실시간 탐색 결과에 따라 +현재 계정에 표시할 모델을 결정합니다. Grok 4.6과 4.7은 두 형식 모두 `low` / `medium` / `high` / `xhigh`를 +노출하고 4.5는 `high`까지만 노출합니다. Grok 4.5와 4.6의 Fast 요청은 해당 기본 모델과 별도의 +`effort`, `fast=true` `requested_model` 파라미터를 전송합니다. 이 두 버전의 평탄화된 +`cursor-grok-{version}-{effort}-fast` id는 탐색 및 picker 식별자로만 사용됩니다. Grok 4.7은 +`cursor-` 접두사 없이 목록에 표시되며 `grok-4.7-{effort}-fast`를 직접 전송합니다. Cursor는 Kimi K3를 +effort 접미사가 붙은 wire id로만 제공하므로 `cursor/kimi-k3`는 `low` / `high` / `max` 래더를 노출하고 기본값은 모델 문서의 API 기본값과 같은 `max`입니다. Cursor 서버가 직접 보내는 native read/write/delete/ls/grep/shell/fetch 실행은 Codex 승인 및 sandbox 경로를 우회하므로 기본적으로 비활성화되어 있습니다. 신뢰한 로컬 실험에서만 diff --git a/docs-site/src/content/docs/ko/reference/configuration/providers.md b/docs-site/src/content/docs/ko/reference/configuration/providers.md index fdbf9c697a8..e4daebc30dc 100644 --- a/docs-site/src/content/docs/ko/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ko/reference/configuration/providers.md @@ -112,7 +112,7 @@ managed map을 활성화하면 privacy-safe selector를 만들고, 이후 계정 | `modelSupportsReasoningSummaries?` | `Record` | 모델을 `false`로 두면 summary 광고를 멈추고 summary 전달 필드를 제거합니다. | | `modelReasoningSummaryDelivery?` | `Record` | 모델별 Responses 전달 enum입니다. 기존 delivery 필드를 다시 씁니다. | | `modelAdapters?` | `Record` | 혼합 와이어 게이트웨이를 위한 모델별 `openai-chat` 또는 `openai-responses` 와이어 재정의입니다. 명시적 항목이 레지스트리 기본값보다 우선합니다. DeepSeek 프리셋은 `deepseek-v4-flash`에 네이티브 Responses를 선택할 수 있고, GitHub Copilot은 모델(`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`)을 Responses 전용 기본값으로 선언합니다. 이 모델들은 에이전트 트래픽에서 `/chat/completions`를 거부하기 때문입니다. `gpt-5.4-nano`처럼 기본값이 없는 모델은 여기서 직접 옵트인할 수 있습니다. 단일 와이어 상위 항목과 정식 ChatGPT forward는 재정의를 거부합니다. | -| xAI Responses 옵트인(대시보드) | 스위치 | `xai`에서만 `grok-4.5`와 `grok-4.6`의 `modelAdapters` 항목을 원자적으로 설정하거나 지웁니다. 한 항목만 있으면 다음 스위치 쓰기가 둘을 정규화할 때까지 혼합 상태로 표시됩니다. 다른 재정의와 티어 동작은 바뀌지 않습니다. | +| xAI Responses 옵트인(대시보드) | 스위치 | `xai`에서만 `grok-4.5`와 `grok-4.6`의 `modelAdapters` 항목을 원자적으로 설정하거나 지웁니다. 한 항목만 있으면 다음 스위치 쓰기가 둘을 정규화할 때까지 혼합 상태로 표시됩니다. 다른 재정의와 티어 동작은 바뀌지 않습니다. Grok 4.7은 OAuth에서 레지스트리 와이어 기본값으로 Responses를 사용하며, 명시적 `modelAdapters["grok-4.7"] = "openai-chat"` 항목으로 Chat으로 전환할 수 있습니다. | | `xaiResponsesXSearch?` | `boolean` | 기본적으로 비활성화됩니다. xAI Responses 대상에서는 최종 요청 정규화 후에도 실제 `web_search` 도구가 남아 있을 때만 공급자가 호스팅하는 `x_search` 선언을 추가합니다. 기존 선언은 중복하지 않고, 호출자의 `tool_choice`/`allowed_tools` 선택기 범위를 확장하지 않으며, 웹 검색 사이드카의 `search.xSearch` 옵션과는 별개입니다. | | `modelPreferHostedTools?` | `Record` | hosted tool namespace를 예약하는 non-forward Responses gateway용 정확한 모델 ID opt-in입니다. 현재 `["image_generation"]`만 허용하며, 일치하는 모델은 `openai-responses` wire를 사용하고 해당 hosted tool을 지원해야 합니다. 충돌하는 클라이언트 `image_gen` 선언을 제거하고 호출자의 tool choice를 유지하도록 selector도 다시 씁니다. OpenAI API 가상 `-pro` 모델은 선택한 공개 ID를 먼저 일치시키고, 해석된 기본 wire-model ID를 대체값으로 사용합니다. `modelAdapters`는 공개 ID를 먼저, 그 다음 기본 ID를 해석하며, 두 번째 결과가 최종 wire를 결정합니다. 설정하지 않은 모델은 일반 alias 동작을 유지합니다. | | `annotateEmptyToolOutputs?` | `boolean` | 존재하지만 비어 있는 도구 결과가 모델에 도달하기 전에 짧은 표시로 바꿔, 빈 결과를 누락된 결과로 해석하지 않도록 합니다. 빈 문자열과 텍스트 전용 파트 배열에 적용되며, 이미지·파일·암호화된 파트는 절대 변경하지 않습니다. 기본 제공 레지스트리에 따라 DeepSeek의 기본값은 `true`이며, 그 외에는 설정되지 않습니다. 공급자를 이 동작에서 제외하려면 `false`로 설정합니다. 명시적인 `false`는 이후 해당 필드를 생략한 편집에서도 유지됩니다. `PATCH /api/providers?name=`는 `true`, `false`, 또는 `null`을 받아 재정의를 지우고 레지스트리 기본 동작으로 되돌릴 수 있습니다. | @@ -306,6 +306,10 @@ Cursor 서버 주도 로컬 도구는 기본값으로 비활성화됩니다. Cod 기본 loopback 바인드는 다른 사용자를 포함한 인증되지 않은 로컬 프로세스라면 무엇이든 허용합니다. 데이터 평면 호출자가 모두 신뢰된 경우가 아니고, Codex 승인과 샌드박스 의미를 의도적으로 우회할 생각이 아니라면 로컬 실행은 꺼 두십시오. ::: +## xAI Grok 4.7 + +Grok 4.7은 OAuth에서 Fast를 지원하며, `low` / `medium` / `high` / `xhigh`와 500,000토큰 컨텍스트 창을 제공합니다. [xAI 표준 요금](https://docs.x.ai/developers/models/grok-4.7)은 100만 토큰당 입력 $2.00, 캐시 입력 $0.50, 출력 $6.00이며, 컨텍스트가 200,000토큰 이상이면 각각 $4.00 / $1.00 / $12.00입니다. + ## OpenRouter 공급자 라우팅 OpenRouter는 하나의 모델을 여러 추론 공급자로 제공할 수 있습니다. `openRouterRouting`은 요청을 선호하는 공급자에 유지하고, `modelOpenRouterRouting`은 정확한 모델 id에 대해 이를 대체합니다. 캐시 지원, 유지 시간, 히트율, 가격이 추론 공급자마다 다르기 때문에 프롬프트 캐시 결속에 유용합니다. diff --git a/docs-site/src/content/docs/reference/configuration/providers.md b/docs-site/src/content/docs/reference/configuration/providers.md index 684ad40a6e8..62260e0f709 100644 --- a/docs-site/src/content/docs/reference/configuration/providers.md +++ b/docs-site/src/content/docs/reference/configuration/providers.md @@ -210,7 +210,7 @@ Providers can expose a built-in shorthand, such as `agy` for `google-antigravity | `modelSupportsReasoningSummaries?` | `Record` | Set a model to `false` to stop advertising summaries and strip summary-delivery fields. | | `modelReasoningSummaryDelivery?` | `Record` | Per-model Responses delivery enum; rewrites an existing delivery field. | | `modelAdapters?` | `Record` | Per-model `openai-chat` or `openai-responses` wire override for mixed-wire gateways. Explicit entries beat registry defaults. The OpenCode Go preset selects Responses for `gpt-5.6-luna` while leaving sibling models on their documented wires; DeepSeek can select native Responses for `deepseek-v4-flash`; Alibaba Token Plan (Beijing) serves `qwen3.8-flash`, `qwen3.7-plus`, and `glm-5.3` over its native Responses API on the same base, verified end to end on that gateway, so they can be opted in here while the wire default stays Chat; and GitHub Copilot declares Responses-only defaults for the following models (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`) because those models reject `/chat/completions` for agent traffic. Models without a built-in default (for example `gpt-5.4-nano`) can be opted in here. Single-wire upstream pins and canonical ChatGPT forward reject overrides. | -| xAI Chat Completions (dashboard / CLI) | switch | Grok 4.5/4.6 OAuth Responses requests default to Responses. Existing Chat overrides are migrated once on upgrade; later Chat choices are preserved. Turn on to select Chat for both models, off to select Responses. CLI: `ocx provider edit xai --xai-chat on` or `--xai-chat off` (running proxy required). Mixed means only one model currently uses Chat. Other overrides and tier policy stay unchanged. API-key and translated Chat/Anthropic defaults are unchanged. | +| xAI Chat Completions (dashboard / CLI) | switch | Grok 4.5/4.6 OAuth Responses requests default to Responses. Existing Chat overrides are migrated once on upgrade; later Chat choices are preserved. Turn on to select Chat for both models, off to select Responses. CLI: `ocx provider edit xai --xai-chat on` or `--xai-chat off` (running proxy required). Mixed means only one model currently uses Chat. Other overrides and tier policy stay unchanged. API-key and translated Chat/Anthropic defaults are unchanged. Grok 4.7 defaults to Responses on OAuth through its registry wire default and can use Chat through an explicit `modelAdapters["grok-4.7"] = "openai-chat"` override. | | `xaiResponsesXSearch?` | `boolean` | Disabled by default. On an xAI Responses destination, append the provider-hosted `x_search` declaration only when a live `web_search` tool survives final request normalization. Existing declarations are not duplicated, caller `tool_choice`/`allowed_tools` selectors are never widened, and this is separate from the web-search sidecar's `search.xSearch` options. | | `modelPreferHostedTools?` | `Record` | Exact-model opt-in for non-forward Responses gateways that reserve a hosted-tool namespace. Currently accepts only `["image_generation"]`; a matching model must use the `openai-responses` wire and support that hosted tool. It removes colliding client `image_gen` declarations and rewrites their selectors to preserve caller tool choice. For OpenAI API virtual `-pro` models, the selected public ID is matched first and the resolved base wire-model ID is a fallback. `modelAdapters` resolves the public ID first, then the base ID; the second resolution determines the final wire. Other models retain normal alias behavior. | | `annotateEmptyToolOutputs?` | `boolean` | Replace a present-but-empty tool result with a short marker before it reaches the model, so a blank result is not read as a missing one. Applies to blank strings and text-only part arrays; image, file, and encrypted parts are never touched. Defaults to `true` for DeepSeek from the built-in registry and is otherwise unset. Set `false` to opt a provider out — an explicit `false` is preserved across later edits that omit the field. `PATCH /api/providers?name=` accepts `true`, `false`, or `null` to clear the override and return to registry-default behavior. | @@ -503,12 +503,13 @@ Explicit capability `false` and Responses caller-tier forwarding retain their ex ### Cursor Fast (`cursor-variant`) Cursor has no `service_tier` field. Its fast product is a different **model variant** — -`claude-opus-5-thinking-high-fast`, or a `{id:"fast",value:"true"}` request parameter for -Grok — so the Cursor entry declares `fastWire.kind: "cursor-variant"` and the request -builder resolves the variant instead of setting a request field. +`claude-opus-5-thinking-high-fast`, a `{id:"fast",value:"true"}` request parameter for +Grok 4.5/4.6, or a flattened `grok-4.7-{effort}-fast` wire id for Grok 4.7 — so the Cursor +entry declares `fastWire.kind: "cursor-variant"` and the request builder resolves the variant +instead of setting a request field. Only the bases that actually declare a fast variant advertise Fast: `claude-opus-4-7`, -`claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `grok-4.5`, `grok-4.6`. Every other Cursor row publishes +`claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `grok-4.5`, `grok-4.6`, `grok-4.7`. Every other Cursor row publishes `supportsServiceTier: false`, so Codex shows no toggle rather than a dead one. A base whose umbrella row routes thinking upgrades to its **thinking-fast** variant, not to @@ -537,7 +538,7 @@ API-key mode targets `https://api.x.ai/v1`; routes resolved to `openai-chat` sen select the `openai-responses` transport instead. `ocx login xai` instead stores OAuth credentials for the Grok subscription gateway (`https://cli-chat-proxy.grok.com/v1`; these credentials refresh automatically), where Fast -is classified per model (live-probed 2026-09-13): grok-4.6, grok-4.5, grok-4.3, grok-4.20-0309-reasoning, +is classified per model (live-probed 2026-09-13 and 2026-09-23): grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-4.20-0309-reasoning, grok-4.20-0309-non-reasoning, grok-build-0.1, and grok-composer-2.5-fast accept `service_tier: "priority"` over Grok OAuth and echo it, so those rows advertise Fast, accept `--fast` selectors, and forward a caller-sent tier on either wire. grok-4.20-multi-agent-0309 @@ -550,7 +551,7 @@ reasoning tokens; cache discounts are applied before the multiplier. Cost estima only when xAI's response confirms `service_tier: "priority"`. A missing or unparsed response tier is not confirmation, and an echoed `default` is a downgrade; all three stay at the standard price. -For `grok-4.6`, the standard rate per 1M tokens is $2.00 input, $0.50 cached input, and $6.00 +For `grok-4.6` and `grok-4.7`, the standard rate per 1M tokens is $2.00 input, $0.50 cached input, and $6.00 output. A prompt of at least 200,000 tokens reprices the whole request at $4.00 / $1.00 / $12.00. xAI has not published how that long-context band combines with Priority Processing. When a long-context response confirms `priority`, the dashboard therefore shows the published long-context diff --git a/docs-site/src/content/docs/ru/guides/codex-app-models.md b/docs-site/src/content/docs/ru/guides/codex-app-models.md index 3445dc08c09..366b3b44046 100644 --- a/docs-site/src/content/docs/ru/guides/codex-app-models.md +++ b/docs-site/src/content/docs/ru/guides/codex-app-models.md @@ -88,8 +88,8 @@ per-model identity и метаданные вместо приближения | Вход Codex (строки с указанием аккаунта включены и есть подходящие селекторы) | По одной строке `/` для каждой пары подходящего селектора и поддерживаемой нативной модели; каждая строка использует только сопоставленный аккаунт, а bare native-строки скрыты из picker'а. Нативные метаданные и окна контекста сохраняются. | | OpenAI (API key) | Ровно восемь namespaced-строк: `gpt-5.5`, `gpt-5.6`, Sol/Terra/Luna и три виртуальных id `*-pro` (контекст 922,000; максимум входа 922,000 у всех восьми) | | OpenRouter | `openrouter/openai/gpt-5.6-sol`, `openrouter/openai/gpt-5.6-terra`, `openrouter/openai/gpt-5.6-luna` (922,000) | -| Cursor | Статический fallback включает `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` и `cursor/gpt-5.6-luna` (1,000,000), а также обычные/Fast-строки Grok 4.5 и 4.6 (500,000). Для 4.6 доступен ещё `xhigh`; какие строки останутся видимыми, решает live-discovery аккаунта. | -| xAI | Live-discovery авторитетно. Fallback-каталог включает `xai/grok-4.6`, а моделью по умолчанию остаётся `xai/grok-4.5`; у обеих окно 500,000 токенов. Grok 4.6 поддерживает `low` / `medium` / `high` / `xhigh` (upstream-default: `high`), а Grok 4.5 — только до `high`. | +| Cursor | Статический fallback включает `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` и `cursor/gpt-5.6-luna` (1,000,000), а также обычные/Fast-строки Grok 4.5, 4.6 и 4.7 (500,000). Для 4.6 и 4.7 доступен ещё `xhigh`; какие строки останутся видимыми, решает live-discovery аккаунта. | +| xAI | Live-discovery имеет приоритет. Fallback-каталог включает `xai/grok-4.6` и `xai/grok-4.7`, а моделью по умолчанию остаётся `xai/grok-4.5`; у всех трёх окно 500,000 токенов. Grok 4.6 и 4.7 поддерживают `low` / `medium` / `high` / `xhigh` (upstream-default: `high`), а Grok 4.5 — только до `high`. | Закреплённые записи GPT-5.6 сохраняют точную upstream-лестницу. Sol и Terra дают диапазон от `low` до `ultra`; у Luna верхняя ступень — `max`. По умолчанию у Sol стоит `low`, а у Terra и diff --git a/docs-site/src/content/docs/ru/guides/providers.md b/docs-site/src/content/docs/ru/guides/providers.md index 53e86522e2b..3bf632cb11e 100644 --- a/docs-site/src/content/docs/ru/guides/providers.md +++ b/docs-site/src/content/docs/ru/guides/providers.md @@ -487,12 +487,13 @@ Cursor отслеживается отдельно как эксперимент `ocx init` и в селекторе Add Provider дашборда как экспериментальная запись локальной конфигурации с метаданными статического резервного каталога моделей Cursor. Когда настроен токен доступа Cursor, opencodex использует живой транспорт HTTP/2 Cursor. Его встроенный резервный список включает -`gpt-5.6-sol` / `terra` / `luna` (контекст 1M), обычные/Fast-строки Grok 4.5 и 4.6 (500K) и +`gpt-5.6-sol` / `terra` / `luna` (контекст 1M), обычные/Fast-строки Grok 4.5, 4.6 и 4.7 (500K) и `kimi-k3` (262K); живое обнаружение решает, какие из них останутся видимыми для аккаунта. Для -Grok 4.6 в обеих формах доступны `low` / `medium` / `high` / `xhigh`, а для 4.5 — только до `high`. -Fast-запросы передают соответствующую базовую модель Grok с отдельными параметрами `effort` и -`fast=true` в `requested_model`; плоские id `cursor-grok-{version}-{effort}-fast` служат только -идентификаторами discovery и picker. Cursor отдаёт +Grok 4.6 и 4.7 в обеих формах доступны `low` / `medium` / `high` / `xhigh`, а для 4.5 — только до `high`. +Для Grok 4.5 и 4.6 Fast-запросы передают соответствующую базовую модель с отдельными параметрами +`effort` и `fast=true` в `requested_model`; их плоские id `cursor-grok-{version}-{effort}-fast` служат +только идентификаторами discovery и picker. Grok 4.7 отображается без префикса `cursor-` и напрямую +передаёт `grok-4.7-{effort}-fast`. Cursor отдаёт Kimi K3 только через wire id с суффиксом усилия, поэтому `cursor/kimi-k3` предоставляет лестницу `low` / `high` / `max` и по умолчанию использует `max` — как и задокументированное значение по умолчанию в API модели. Управляемое сервером Cursor diff --git a/docs-site/src/content/docs/ru/reference/configuration/providers.md b/docs-site/src/content/docs/ru/reference/configuration/providers.md index 35de1cf8541..84ca71c5b0b 100644 --- a/docs-site/src/content/docs/ru/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ru/reference/configuration/providers.md @@ -125,7 +125,7 @@ cross-route credential fallback не существует. Строки API GPT- | `modelSupportsReasoningSummaries?` | `Record` | Установите `false` для модели, чтобы перестать рекламировать summary и вырезать поля доставки summary. | | `modelReasoningSummaryDelivery?` | `Record` | Responses delivery enum по моделям; переписывает уже существующее поле delivery. | | `modelAdapters?` | `Record` | Wire-override по модели для `openai-chat` или `openai-responses` в gateway с несколькими wire-форматами. Явные записи имеют приоритет над default'ами registry; preset DeepSeek может выбирать native Responses для `deepseek-v4-flash`, а GitHub Copilot объявляет Responses-only default'ы для моделей (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`), потому что эти модели отклоняют `/chat/completions` для агентного трафика. Модели без встроенного default'а (например, `gpt-5.4-nano`) можно включить здесь. Single-wire upstream pin'ы и canonical ChatGPT forward override не принимают. | -| Opt-in xAI Responses (панель) | переключатель | Только для `xai`: атомарно задаёт или удаляет записи `modelAdapters` для `grok-4.5` и `grok-4.6`. Одна запись отображается как смешанное состояние до следующего переключения. Остальные override и поведение tier не меняются. | +| Opt-in xAI Responses (панель) | переключатель | Только для `xai`: атомарно задаёт или удаляет записи `modelAdapters` для `grok-4.5` и `grok-4.6`. Одна запись отображается как смешанное состояние до следующего переключения. Остальные override и поведение tier не меняются. Grok 4.7 по умолчанию использует Responses на OAuth через настройку реестра и может перейти на Chat через явную запись `modelAdapters["grok-4.7"] = "openai-chat"`. | | `xaiResponsesXSearch?` | `boolean` | По умолчанию отключено. Для назначения xAI Responses декларация `x_search`, размещённая у провайдера, добавляется только тогда, когда действующий инструмент `web_search` сохраняется после окончательной нормализации запроса. Существующие декларации не дублируются, селекторы вызывающей стороны `tool_choice`/`allowed_tools` никогда не расширяются, и эта настройка не связана с параметрами `search.xSearch` сайдкара веб-поиска. | | `modelPreferHostedTools?` | `Record` | Opt-in для точного model ID в non-forward Responses gateway, который резервирует namespace hosted tool. Сейчас допускается только `["image_generation"]`; совпавшая модель должна использовать wire `openai-responses` и поддерживать этот hosted tool. Прокси удаляет конфликтующие клиентские объявления `image_gen` и переписывает их selectors, сохраняя caller tool choice. Для виртуальных моделей OpenAI API `-pro` сначала сопоставляется выбранный публичный ID, а затем в качестве fallback используется ID базовой wire-модели. `modelAdapters` сначала разрешается по публичному ID, затем по базовому ID; второй результат определяет итоговый wire. Остальные модели сохраняют обычное alias-поведение. | | `annotateEmptyToolOutputs?` | `boolean` | Заменяет присутствующий, но пустой результат вызова инструмента короткой меткой до его передачи модели, чтобы пустой результат не воспринимался как отсутствующий. Применяется к пустым строкам и массивам частей, содержащим только текст; части с изображениями, файлами и зашифрованными данными никогда не изменяются. Во встроенном реестре по умолчанию имеет значение `true` для DeepSeek, а для остальных провайдеров не задано. Укажите `false`, чтобы отключить эту возможность для провайдера: явное значение `false` сохраняется при последующих изменениях без этого поля. `PATCH /api/providers?name=` принимает `true`, `false` или `null`, чтобы удалить переопределение и вернуться к поведению по умолчанию из реестра. | @@ -374,6 +374,10 @@ Bind по умолчанию на loopback допускает любой лок semantics Codex. ::: +## Grok 4.7 в xAI + +Grok 4.7 поддерживает Fast через OAuth, уровни `low` / `medium` / `high` / `xhigh` и окно в 500,000 токенов. [Стандартная цена xAI](https://docs.x.ai/developers/models/grok-4.7) за миллион токенов составляет $2.00 за ввод, $0.50 за кэшированный ввод и $6.00 за вывод; при контексте от 200,000 токенов действуют цены $4.00 / $1.00 / $12.00. + ## Маршрутизация провайдера OpenRouter OpenRouter может обслуживать одну и ту же модель через нескольких inference-провайдеров. diff --git a/docs-site/src/content/docs/tr/guides/codex-app-models.md b/docs-site/src/content/docs/tr/guides/codex-app-models.md index 2743b075ed8..36b0230abe6 100644 --- a/docs-site/src/content/docs/tr/guides/codex-app-models.md +++ b/docs-site/src/content/docs/tr/guides/codex-app-models.md @@ -157,8 +157,8 @@ meta verileri sağladığı GPT-5.6 için kullanılır. | Codex girişi (açık Daybreak iletme satırı) | Yalnızca tam `customModels` satırı kurallı `openai` sağlayıcısında yapılandırıldığında `openai/gpt-daybreak-blue-latest`. Daybreak hat kimliğini korur ve sabitlenmiş Sol yetenek anlık görüntüsünü kullanır (922.000 bağlam; 829.800 otomatik sıkıştırma). | | OpenAI (API anahtarı) | Tam olarak on ad alanlı satır: `gpt-5.5`, `gpt-5.6`, Sol/Terra/Luna, üç `*-pro` sanal kimliği ve iki Daybreak takma adı (onunun tümü için 922.000 bağlam; 922.000 maksimum girdi) | | OpenRouter | `openrouter/openai/gpt-5.6-sol`, `openrouter/openai/gpt-5.6-terra`, `openrouter/openai/gpt-5.6-luna` (922.000) | -| Cursor | Statik geri dönüş `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` ve `cursor/gpt-5.6-luna` (1.000.000) artı `cursor/grok-4.5` ve `cursor/grok-4.5-fast` (500.000) içerir; canlı hesap keşfi hangilerinin görünür kalacağına karar verir. | -| xAI | Canlı keşif yetkilidir. Geri dönüş kataloğu `xai/grok-4.6` içerir ve varsayılan olarak `xai/grok-4.5`'tir; her ikisinin de 500.000 tokenlik pencereleri vardır. Grok 4.6, `low` / `medium` / `high` / `xhigh` (yukarı akış varsayılanı: `high`) sunarken, Grok 4.5 `high` ile durur. | +| Cursor | Statik geri dönüş `cursor/gpt-5.6-sol`, `cursor/gpt-5.6-terra` ve `cursor/gpt-5.6-luna` (1.000.000) ile Grok 4.5, 4.6 ve 4.7 için normal/Fast satırları (500.000) içerir; 4.6 ve 4.7 ayrıca `xhigh` sunar. Canlı hesap keşfi hangi satırların görünür kalacağını belirler. | +| xAI | Canlı keşif yetkilidir. Geri dönüş kataloğu `xai/grok-4.6` ve `xai/grok-4.7` içerir; varsayılan model `xai/grok-4.5` olarak kalır. Üçünün de bağlam penceresi 500.000 tokendir. Grok 4.6 ve 4.7 `low` / `medium` / `high` / `xhigh` (yukarı akış varsayılanı: `high`) sunarken, Grok 4.5 `high` ile durur. | Sabitlenmiş GPT-5.6 girdileri tam yukarı akış merdivenini korur. Sol ve Terra `low`'dan `ultra`'ya kadar sunar; Luna `max` ile durur. Sol varsayılan olarak diff --git a/docs-site/src/content/docs/tr/guides/providers.md b/docs-site/src/content/docs/tr/guides/providers.md index c49040b0960..eaa604e4d8e 100644 --- a/docs-site/src/content/docs/tr/guides/providers.md +++ b/docs-site/src/content/docs/tr/guides/providers.md @@ -668,9 +668,14 @@ init`'te ve kontrol paneli Sağlayıcı Ekle seçicisinde Cursor'ın statik geri dönüş model kataloğu meta verileriyle deneysel bir yerel yapılandırma girdisi olarak görünür. Bir Cursor erişim belirteci yapılandırıldığında opencodex Cursor'ın canlı HTTP/2 aktarımını kullanır. Paketlenmiş geri dönüş tohumu -`gpt-5.6-sol` / `terra` / `luna` (1M bağlam), `grok-4.5` / `grok-4.5-fast` +`gpt-5.6-sol` / `terra` / `luna` (1M bağlam), Grok 4.5, 4.6 ve 4.7 için normal/Fast satırları (500K) ve `kimi-k3` (262K) içerir; canlı keşif hesap için hangilerinin görünür -kalacağına karar verir. Cursor, Kimi K3'ü yalnızca çaba sonekli hat kimlikleri +kalacağına karar verir. Grok 4.6 ve 4.7, normal ve Fast biçimlerinde `low` / +`medium` / `high` / `xhigh` sunarken 4.5 `high` ile sınırlıdır. Grok 4.5 ve 4.6'nın Fast istekleri, +eşleşen temel modeli ayrı `effort` ve `fast=true` `requested_model` parametreleriyle gönderir; bunların +düzleştirilmiş `cursor-grok-{version}-{effort}-fast` kimlikleri yalnızca keşif ve model seçimi içindir. +Grok 4.7, `cursor-` öneki olmadan listelenir ve `grok-4.7-{effort}-fast` kimliğini doğrudan gönderir. +Cursor, Kimi K3'ü yalnızca çaba sonekli hat kimlikleri olarak sunar, bu nedenle `cursor/kimi-k3` bir `low` / `high` / `max` merdiveni gösterir ve modelin belgelenmiş API varsayılanıyla eşleşecek şekilde varsayılan olarak `max` olur. Cursor sunucu güdümlü yerel diff --git a/docs-site/src/content/docs/tr/reference/configuration/providers.md b/docs-site/src/content/docs/tr/reference/configuration/providers.md index 1fbe43c91d8..5dedc43c465 100644 --- a/docs-site/src/content/docs/tr/reference/configuration/providers.md +++ b/docs-site/src/content/docs/tr/reference/configuration/providers.md @@ -126,7 +126,7 @@ alanlı seçilmiş kimlikleri yalın kimliklere yeniden yazar. | `modelSupportsReasoningSummaries?` | `Record` | Özetlerin bildirilmesini durdurmak ve özet teslim alanlarını kaldırmak için bir modeli `false` olarak ayarlayın. | | `modelReasoningSummaryDelivery?` | `Record` | Model başına Responses teslim enum'ı; mevcut bir teslim alanını yeniden yazar. | | `modelAdapters?` | `Record` | Karışık hatlı ağ geçitleri için model başına `openai-chat` veya `openai-responses` hat geçersiz kılma. Açık girdiler kayıt defteri varsayılanlarını yener. OpenCode Go önayarı, kardeş modelleri belgelenmiş hatlarında bırakırken `gpt-5.6-luna` için Responses'ı seçer; DeepSeek, `deepseek-v4-flash` için yerel Responses seçebilir; ve GitHub Copilot, modeller (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`) için yalnızca Responses varsayılanlarını bildirir çünkü bu modeller ajan trafiği için `/chat/completions`'ı reddeder. Yerleşik varsayılanı olmayan modeller (örneğin `gpt-5.4-nano`) burada dahil edilebilir. Tek hatlı yukarı akış pinleri ve kurallı ChatGPT iletme geçersiz kılmaları reddeder. | -| xAI Responses katılımı (panel) | anahtar | Yalnızca `xai` için `grok-4.5` ve `grok-4.6` `modelAdapters` girdilerini atomik olarak ayarlar veya temizler. Tek girdi, sonraki anahtar yazımı ikisini eşitleyene kadar karma durum olarak görünür. Diğer geçersiz kılmalar ve katman davranışı değişmez. | +| xAI Responses katılımı (panel) | anahtar | Yalnızca `xai` için `grok-4.5` ve `grok-4.6` `modelAdapters` girdilerini atomik olarak ayarlar veya temizler. Tek girdi, sonraki anahtar yazımı ikisini eşitleyene kadar karma durum olarak görünür. Diğer geçersiz kılmalar ve katman davranışı değişmez. Grok 4.7, OAuth üzerinde kayıt defteri hat varsayılanıyla Responses kullanır ve açık `modelAdapters["grok-4.7"] = "openai-chat"` girdisiyle Chat’e geçirilebilir. | | `xaiResponsesXSearch?` | `boolean` | Varsayılan olarak devre dışıdır. Bir xAI Responses hedefinde, yalnızca canlı bir `web_search` aracı son istek normalleştirmesinden sağ çıktığında sağlayıcı tarafından barındırılan `x_search` bildirimini ekler. Mevcut bildirimler yinelenmez, çağıranın `tool_choice`/`allowed_tools` seçicileri hiçbir zaman genişletilmez ve bu, web araması yardımcı hizmetinin `search.xSearch` seçeneklerinden ayrıdır. | | `modelPreferHostedTools?` | `Record` | Barındırılan bir araç ad alanı ayıran iletme harici Responses ağ geçitleri için tam model dahil etme. Şu anda yalnızca `["image_generation"]` kabul eder; eşleşen bir model `openai-responses` hattını kullanmalı ve bu barındırılan aracı desteklemelidir. Çakışan istemci `image_gen` bildirimlerini kaldırır ve arayan araç seçimini korumak için seçicilerini yeniden yazar. OpenAI API sanal `-pro` modelleri için önce seçilen genel kimlik eşleştirilir ve çözümlenen temel hat model kimliği bir geri dönüştür. `modelAdapters` önce genel kimliği, ardından temel kimliği çözer; ikinci çözümleme son hattı belirler. Diğer modeller normal takma ad davranışını korur. | | `annotateEmptyToolOutputs?` | `boolean` | Mevcut fakat boş bir araç sonucunu modele ulaşmadan önce kısa bir işaretle değiştirir; böylece boş sonuç eksik sonuç olarak yorumlanmaz. Boş dizelere ve yalnızca metin parçalarından oluşan dizilere uygulanır; görsel, dosya ve şifrelenmiş parçalara hiçbir zaman dokunulmaz. Yerleşik kayıt defterindeki DeepSeek için varsayılan değer `true`dur; diğer durumlarda ayarlanmamıştır. Bir sağlayıcıyı kapsam dışında bırakmak için `false` olarak ayarlayın — açık bir `false` değeri, alanı içermeyen sonraki düzenlemelerde korunur. `PATCH /api/providers?name=`, geçersiz kılmayı temizleyip kayıt defteri varsayılanı davranışına dönmek üzere `true`, `false` veya `null` kabul eder. | @@ -405,6 +405,10 @@ ve sanal alan anlambilimini kasıtlı olarak atlamayı kabul etmedikçe yerel yürütmeyi kapalı bırakın. ::: +## xAI Grok 4.7 + +Grok 4.7, OAuth üzerinde Fast ile `low` / `medium` / `high` / `xhigh` düzeylerini ve 500.000 tokenlık bağlam penceresini destekler. [xAI standart fiyatı](https://docs.x.ai/developers/models/grok-4.7) milyon token başına giriş için $2,00, önbellekli giriş için $0,50 ve çıkış için $6,00; 200.000 token ve üzeri bağlamda sırasıyla $4,00 / $1,00 / $12,00’dır. + ## OpenRouter sağlayıcı yönlendirmesi OpenRouter bir modeli birkaç çıkarım sağlayıcısı aracılığıyla sunabilir. diff --git a/docs-site/src/content/docs/zh-cn/guides/codex-app-models.md b/docs-site/src/content/docs/zh-cn/guides/codex-app-models.md index d48a5457dde..5214e768367 100644 --- a/docs-site/src/content/docs/zh-cn/guides/codex-app-models.md +++ b/docs-site/src/content/docs/zh-cn/guides/codex-app-models.md @@ -69,8 +69,8 @@ visibility = "list" | Codex 登录（账户限定的选择器行已启用且存在有效 selector） | 为每个有效 selector 与受支持原生模型的组合显示 `/` 行。每行只使用映射账户，裸原生行会从选择器中隐藏。原生 metadata 与 context window 会保留。 | | OpenAI（API key） | 恰好八个命名空间行：`gpt-5.5`、`gpt-5.6`、Sol/Terra/Luna，以及三个 `*-pro` 虚拟 id（八个条目均为 1,050,000 context / 922,000 max input） | | OpenRouter | `openrouter/openai/gpt-5.6-sol`、`openrouter/openai/gpt-5.6-terra`、`openrouter/openai/gpt-5.6-luna`（922,000） | -| Cursor | 静态回退包含 `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna`（1,000,000），以及 Grok 4.5/4.6 的普通和 Fast 条目（500,000）。4.6 还提供 `xhigh`；实时账户发现会决定最终哪些条目仍然可见。 | -| xAI | 实时发现具有权威性。回退目录包含 `xai/grok-4.6`，默认模型仍为 `xai/grok-4.5`；两者的上下文窗口均为 500,000。Grok 4.6 提供 `low` / `medium` / `high` / `xhigh`（上游默认值为 `high`），Grok 4.5 最高为 `high`。 | +| Cursor | 静态回退包含 `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna`（1,000,000），以及 Grok 4.5/4.6/4.7 的普通和 Fast 条目（500,000）。4.6 和 4.7 还提供 `xhigh`；实时账户发现会决定最终哪些条目仍然可见。 | +| xAI | 实时发现具有权威性。回退目录包含 `xai/grok-4.6` 和 `xai/grok-4.7`，默认模型仍为 `xai/grok-4.5`；三者的上下文窗口均为 500,000。Grok 4.6 和 4.7 提供 `low` / `medium` / `high` / `xhigh`（上游默认值为 `high`），Grok 4.5 最高为 `high`。 | 固定的 GPT-5.6 条目保留了精确的上游阶梯。Sol 和 Terra 暴露从 `low` 到 `ultra` 的档位；Luna 只到 `max`。Sol 默认是 `low`，Terra 和 Luna 默认是 `medium`。`ultra` 是面向客户端的最大 reasoning 加主动委派选项，在后端会以 `max` 传入。选择器里的一个条目只表示目录已经准备好：关联的账户或 API key 仍然必须有权使用该模型。 diff --git a/docs-site/src/content/docs/zh-cn/guides/providers.md b/docs-site/src/content/docs/zh-cn/guides/providers.md index d799f306705..e04834ab544 100644 --- a/docs-site/src/content/docs/zh-cn/guides/providers.md +++ b/docs-site/src/content/docs/zh-cn/guides/providers.md @@ -456,11 +456,12 @@ Cursor 作为单独的实验性 adapter 进行跟踪。`adapter: "cursor"` 会 Cursor access token 后，opencodex 会使用 Cursor live HTTP/2 transport。代理要求 Cursor 的 HTTP/1.1 兼容路径时，可设置 `upstreamHttpVersion: "http1.1"`；该设置同时覆盖推理与实时模型发现， 并可在 **Providers → Cursor → 设置 → Cursor 传输协议** 中选择。内置回退列表包含上下文为 -1M 的 `gpt-5.6-sol` / `terra` / `luna`、上下文为 500K 的 Grok 4.5/4.6 普通与 Fast 条目，以及上下文为 -262K 的 `kimi-k3`；最终显示哪些模型由账号的实时发现结果决定。Grok 4.6 的两种形式均提供 -`low` / `medium` / `high` / `xhigh`，而 4.5 最高为 `high`。Fast 请求会发送对应的 Grok 基础模型， -并通过独立的 `effort` 与 `fast=true` `requested_model` 参数指定模式；扁平化的 -`cursor-grok-{version}-{effort}-fast` id 仅用于发现和 picker 标识。Cursor 只以带 effort 后缀的 wire id +1M 的 `gpt-5.6-sol` / `terra` / `luna`、上下文为 500K 的 Grok 4.5/4.6/4.7 普通与 Fast 条目，以及上下文为 +262K 的 `kimi-k3`；最终显示哪些模型由账号的实时发现结果决定。Grok 4.6 和 4.7 的两种形式均提供 +`low` / `medium` / `high` / `xhigh`，而 4.5 最高为 `high`。Grok 4.5 和 4.6 的 Fast 请求会发送对应的基础模型， +并通过独立的 `effort` 与 `fast=true` `requested_model` 参数指定模式；这两个版本的扁平化 +`cursor-grok-{version}-{effort}-fast` id 仅用于发现和 picker 标识。Grok 4.7 在列表中没有 `cursor-` 前缀， +直接发送 `grok-4.7-{effort}-fast`。Cursor 只以带 effort 后缀的 wire id 提供 Kimi K3，因此 `cursor/kimi-k3` 暴露 `low` / `high` / `max` 阶梯，默认值为 `max`，与该模型 文档中的 API 默认值一致。Cursor 服务器直接发起的 native read/write/delete/ls/grep/shell/fetch 执行默认禁用，因为它会绕过 Codex 的 approval 和 diff --git a/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md b/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md index 85a12fa08ba..ed92907c28e 100644 --- a/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md +++ b/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md @@ -112,7 +112,7 @@ selector，而不是分配一个新名称。 | `modelSupportsReasoningSummaries?` | `Record` | 将某个模型设为 `false`，即可停止暴露摘要并移除摘要交付字段。 | | `modelReasoningSummaryDelivery?` | `Record` | 按模型设置的 Responses 交付枚举；会重写现有的 delivery 字段。 | | `modelAdapters?` | `Record` | 按模型设置的 `openai-chat` 或 `openai-responses` 线协议覆盖项，用于混合线协议网关。显式条目优先于注册表默认值；DeepSeek 预设可以为 `deepseek-v4-flash` 选择原生 Responses，GitHub Copilot 则为 模型（`gpt-5.3-codex`、`gpt-5.4`、`gpt-5.4-mini`、`gpt-5.5`、`gpt-5.6-luna`、`gpt-5.6-sol`、`gpt-5.6-terra`、`gpt-6-astra`, `grok-4.5`, `grok-4.6`, `mai-code-1.1-flash`, `mai-code-1-flash-picker`）声明了 Responses 专用默认值，因为这些模型在代理流量下会拒绝 `/chat/completions`。没有内置默认值的模型（例如 `gpt-5.4-nano`）可以在此手动启用。单一线协议上游固定项和规范 ChatGPT forward 会拒绝覆盖。 | -| xAI Responses 启用项（仪表板） | 开关 | 仅用于 `xai`，以原子方式设置或清除 `grok-4.5` 和 `grok-4.6` 的 `modelAdapters` 条目。若只存在一个条目，则显示混合状态，直到下次开关写入将两者统一。其他覆盖项和层级行为不变。 | +| xAI Responses 启用项（仪表板） | 开关 | 仅用于 `xai`，以原子方式设置或清除 `grok-4.5` 和 `grok-4.6` 的 `modelAdapters` 条目。若只存在一个条目，则显示混合状态，直到下次开关写入将两者统一。其他覆盖项和层级行为不变。 Grok 4.7 在 OAuth 上通过注册表线协议默认使用 Responses，也可通过显式的 `modelAdapters["grok-4.7"] = "openai-chat"` 条目切换到 Chat。 | | `xaiResponsesXSearch?` | `boolean` | 默认禁用。在 xAI Responses 目标上，仅当有效的 `web_search` 工具在最终请求规范化后仍保留时，才附加由提供方托管的 `x_search` 声明。不会重复已有声明，绝不会扩大调用方的 `tool_choice`/`allowed_tools` 选择范围，并且此项独立于网络搜索辅助服务的 `search.xSearch` 选项。 | | `modelPreferHostedTools?` | `Record` | 非 forward Responses gateway 的精确模型 ID opt-in，用于上游预留 hosted tool namespace 的情况。目前只支持 `["image_generation"]`；匹配模型必须使用 `openai-responses` wire 且支持该 hosted 工具。它会移除冲突的客户端 `image_gen` 声明，并改写其 selector 以保持调用方的 tool choice。对于 OpenAI API 的虚拟 `-pro` 模型，先匹配所选公开 ID，未命中时才使用解析出的基础 wire-model ID 作为回退。`modelAdapters` 会先按公开 ID、再按基础 ID 解析；后一次结果决定最终 wire。未配置模型保持普通 alias 行为。 | | `annotateEmptyToolOutputs?` | `boolean` | 在工具结果到达模型之前，将存在但为空的结果替换为简短标记，以免空白结果被误认为缺失结果。适用于空白字符串和仅包含文本的部件数组；图像、文件和加密部件绝不会被修改。内置注册表中 `DeepSeek` 的默认值为 `true`，其他情况下不设置。设为 `false` 可让提供者退出此行为——后续编辑即使省略该字段，也会保留显式的 `false`。`PATCH /api/providers?name=` 接受 `true`、`false` 或 `null`；传入 `null` 可清除覆盖值并恢复注册表默认行为。 | @@ -306,6 +306,10 @@ Cursor 由服务端驱动的本地工具默认是禁用的。Codex 继续使用 默认的 loopback 绑定会让任何本地进程都能在没有认证的情况下接入，包括多用户主机上的其他用户。除非每个数据平面调用方都是受信任的，并且你明确接受绕过 Codex 的审批和沙箱语义，否则请保持本地执行关闭。 ::: +## xAI Grok 4.7 + +Grok 4.7 在 OAuth 上支持 Fast，提供 `low` / `medium` / `high` / `xhigh`，上下文窗口为 500,000。按 [xAI 标准价格](https://docs.x.ai/developers/models/grok-4.7)，每百万 token 的输入、缓存输入和输出费用分别为 $2.00、$0.50 和 $6.00；上下文达到 200,000 token 时分别为 $4.00 / $1.00 / $12.00。 + ## OpenRouter 提供者路由 OpenRouter 可以通过多个推理提供者来提供同一个模型。`openRouterRouting` 会让请求停留在偏好的提供者上；`modelOpenRouterRouting` 则会对精确模型 id 进行替换。对于提示缓存亲和性来说，这很有用，因为不同推理提供者的缓存支持、保留策略、命中率和定价都不同。 diff --git a/docs-site/src/content/docs/zh-tw/guides/codex-app-models.md b/docs-site/src/content/docs/zh-tw/guides/codex-app-models.md index 6c2d7eb9bde..176a68a8bfd 100644 --- a/docs-site/src/content/docs/zh-tw/guides/codex-app-models.md +++ b/docs-site/src/content/docs/zh-tw/guides/codex-app-models.md @@ -90,8 +90,8 @@ GPT-5.6，以便提供每個模型真實的身份和後設資料，而不是套 | Codex 登入（啟用帳號限定列且有合格選擇器） | 每個合格選擇器與受支援的原生模型各有一列 `/`；每列只使用其對應帳號，且裸原生列會從選擇器中隱藏。原生後設資料與 context 視窗保持不變。 | | OpenAI（API key） | 恰好八個帶名稱空間的列：`gpt-5.5`、`gpt-5.6`、Sol/Terra/Luna 與三個 `*-pro` 虛擬 id（全部八個都是 1,050,000 context；922,000 max input） | | OpenRouter | `openrouter/openai/gpt-5.6-sol`、`openrouter/openai/gpt-5.6-terra`、`openrouter/openai/gpt-5.6-luna`（922,000） | -| Cursor | 靜態回退目錄包含 `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna`（1,000,000），以及 Grok 4.5/4.6 的一般與 Fast 項目（500,000）。4.6 還提供 `xhigh`；帳號的即時發現結果決定最終顯示哪些模型。 | -| xAI | 以即時發現結果為準。回退目錄包含 `xai/grok-4.6`，預設模型仍為 `xai/grok-4.5`；兩者的 context window 均為 500,000。Grok 4.6 提供 `low` / `medium` / `high` / `xhigh`（上游預設值為 `high`），Grok 4.5 最高為 `high`。 | +| Cursor | 靜態回退目錄包含 `cursor/gpt-5.6-sol`、`cursor/gpt-5.6-terra`、`cursor/gpt-5.6-luna`（1,000,000），以及 Grok 4.5/4.6/4.7 的一般與 Fast 項目（500,000）。4.6 和 4.7 還提供 `xhigh`；帳號的即時發現結果決定最終顯示哪些模型。 | +| xAI | 以即時發現結果為準。回退目錄包含 `xai/grok-4.6` 與 `xai/grok-4.7`，預設模型仍為 `xai/grok-4.5`；三者的 context window 均為 500,000。Grok 4.6 與 4.7 提供 `low` / `medium` / `high` / `xhigh`（上游預設值為 `high`），Grok 4.5 最高為 `high`。 | 固定的 GPT-5.6 條目會保留精確的上游 reasoning 階梯。Sol 和 Terra 從 `low` 到 `ultra`，Luna 最高到 `max`。Sol 預設使用 `low`，Terra 和 Luna 預設使用 `medium`。`ultra` 是用戶端側的 diff --git a/docs-site/src/content/docs/zh-tw/guides/providers.md b/docs-site/src/content/docs/zh-tw/guides/providers.md index 44263dc002f..569567ab97a 100644 --- a/docs-site/src/content/docs/zh-tw/guides/providers.md +++ b/docs-site/src/content/docs/zh-tw/guides/providers.md @@ -521,10 +521,11 @@ Copilot 的 catalog 混合多種 wire：模型（`gpt-5.3-codex`、`gpt-5.4`、` Cursor 另以實驗性 adapter 追蹤。`adapter: "cursor"` 會在 `ocx init` 與 dashboard Add Provider picker 出現為實驗性 local config，並帶 Cursor static fallback model catalog metadata。設定 Cursor access token 後，opencodex 使用 Cursor 即時 HTTP/2 transport。bundled fallback seed 包含 1M context 的 -`gpt-5.6-sol`／`terra`／`luna`、500K 的 Grok 4.5/4.6 一般與 Fast 項目，以及 262K 的 `kimi-k3`；即時探索 -決定哪些模型對帳號保持可見。Grok 4.6 的兩種形式都提供 `low`／`medium`／`high`／`xhigh`，4.5 則最高到 -`high`。Fast 請求會傳送對應的 Grok 基礎模型，並使用獨立的 `effort` 與 `fast=true` `requested_model` -參數；扁平化的 `cursor-grok-{version}-{effort}-fast` id 僅作為探索與 picker 識別。Cursor 的 Kimi K3 +`gpt-5.6-sol`／`terra`／`luna`、500K 的 Grok 4.5/4.6/4.7 一般與 Fast 項目，以及 262K 的 `kimi-k3`；即時探索 +決定哪些模型對帳號保持可見。Grok 4.6 與 4.7 的兩種形式都提供 `low`／`medium`／`high`／`xhigh`，4.5 則最高到 +`high`。Grok 4.5 與 4.6 的 Fast 請求會傳送對應的基礎模型，並使用獨立的 `effort` 與 `fast=true` +`requested_model` 參數；這兩個版本扁平化的 `cursor-grok-{version}-{effort}-fast` id 僅作為探索與 picker 識別。 +Grok 4.7 在清單中沒有 `cursor-` 前綴，直接傳送 `grok-4.7-{effort}-fast`。Cursor 的 Kimi K3 只以帶 effort suffix 的 wire id 提供，因此 `cursor/kimi-k3` 暴露 `low`／`high`／`max` ladder，預設為 `max`，符合該模型文件化的 API default。 Cursor server-driven native read/write/delete/ls/grep/shell/fetch execution 預設停用，因為它會繞過 Codex diff --git a/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md b/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md index cdbd005d00f..84bfc7f8009 100644 --- a/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md +++ b/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md @@ -88,7 +88,7 @@ ocx models provider openrouter on | `modelSupportsReasoningSummaries?` | `Record` | 將模型設為 `false` 以停止廣告摘要並剝離 summary-delivery 欄位。 | | `modelReasoningSummaryDelivery?` | `Record` | Per-model Responses delivery 列舉；重寫既有的 delivery 欄位。 | | `modelAdapters?` | `Record` | 混合 wire 閘道的 Per-model `openai-chat` 或 `openai-responses` wire 覆寫。明確項目勝過 registry 預設；DeepSeek 的預設可為 `deepseek-v4-flash` 選擇原生 Responses。單一 wire 上游 pin 與規範 ChatGPT forward 拒絕覆寫。 | -| xAI Responses 選用（儀表板） | 開關 | 僅用於 `xai`，以原子方式設定或清除 `grok-4.5` 與 `grok-4.6` 的 `modelAdapters` 項目。若只有一個項目，會顯示混合狀態，直到下次開關寫入統一兩者。其他覆寫與層級行為不變。 | +| xAI Responses 選用（儀表板） | 開關 | 僅用於 `xai`，以原子方式設定或清除 `grok-4.5` 與 `grok-4.6` 的 `modelAdapters` 項目。若只有一個項目，會顯示混合狀態，直到下次開關寫入統一兩者。其他覆寫與層級行為不變。 Grok 4.7 在 OAuth 上透過登錄檔 wire 預設使用 Responses，也可透過明確的 `modelAdapters["grok-4.7"] = "openai-chat"` 項目切換至 Chat。 | | `annotateEmptyToolOutputs?` | `boolean` | 在工具結果送達模型前，將已存在但為空的結果替換成簡短標記，使空白結果不會被解讀為遺漏的結果。適用於空白字串及僅含文字部分的陣列；影像、檔案及加密部分絕不會被更動。DeepSeek 透過內建登錄檔預設為 `true`，其他情況則不設定。設為 `false` 可讓供應商停用此功能；後續編輯即使省略此欄位，也會保留明確設定的 `false`。`PATCH /api/providers?name=` 接受 `true`、`false` 或 `null`；`null` 會清除覆寫並恢復使用登錄檔的預設行為。 | | `xaiResponsesXSearch?` | `boolean` | 預設停用。在 xAI Responses 目的地上，僅當即時 `web_search` 工具通過最終請求正規化後仍保留時，才附加由供應商託管的 `x_search` 宣告。既有宣告不會重複，呼叫端的 `tool_choice`／`allowed_tools` 選擇器絕不會擴大，且此設定與網頁搜尋輔助服務的 `search.xSearch` 選項分開。 | | `reasoningEffortMap?` | `Record` | 供應商範圍的 reasoning 標籤 wire 別名。將標籤對應為 `"__omit__"` 可在上游請求中完全省略推理欄位（例如針對需要省略 `reasoning_effort` 才能觸發深度思考模式的 Ollama 本地模型）。 | @@ -270,6 +270,10 @@ Cursor 伺服器驅動的本機工具預設停用。Codex 繼續使用其自身 預設的回送綁定允許任何本機行程在無認證下存取，包含多使用者主機上的其他使用者。除非每個 data-plane 呼叫者都受信任且你刻意接受繞過 Codex 核可與沙箱語意，否則保持本機執行關閉。 ::: +## xAI Grok 4.7 + +Grok 4.7 在 OAuth 上支援 Fast，提供 `low` / `medium` / `high` / `xhigh`，context window 為 500,000。依 [xAI 標準價格](https://docs.x.ai/developers/models/grok-4.7)，每百萬 token 的輸入、快取輸入及輸出費用分別為 $2.00、$0.50 及 $6.00；context 達 200,000 token 時分別為 $4.00 / $1.00 / $12.00。 + ## OpenRouter 供應商路由 OpenRouter 可透過多個推論供應商提供一個模型。`openRouterRouting` 將請求保持在偏好的供應商上；`modelOpenRouterRouting` 為精確 model id 取代它。這對 prompt-cache 親和性很有用，因為 cache 支援、保留、命中率與定價因推論供應商而異。 diff --git a/scripts/model-metadata.source.json b/scripts/model-metadata.source.json index 4b47f63c92b..fc4c1507b82 100644 --- a/scripts/model-metadata.source.json +++ b/scripts/model-metadata.source.json @@ -23744,6 +23744,31 @@ "maxLevel": "xhigh" } }, + "x-ai/grok-4.7": { + "id": "x-ai/grok-4.7", + "name": "Grok 4.7", + "api": "openai-completions", + "provider": "kilo", + "baseUrl": "https://api.kilo.ai/api/gateway", + "reasoning": true, + "input": [ + "text", + "image" + ], + "cost": { + "input": 1.6, + "output": 4.8, + "cacheRead": 0.4, + "cacheWrite": 0 + }, + "contextWindow": 500000, + "maxTokens": 450000, + "thinking": { + "mode": "effort", + "minLevel": "minimal", + "maxLevel": "xhigh" + } + }, "x-ai/grok-build-0.1": { "id": "x-ai/grok-build-0.1", "name": "Grok Build 0.1", @@ -61046,6 +61071,31 @@ "maxLevel": "xhigh" } }, + "grok-4.7": { + "id": "grok-4.7", + "name": "Grok 4.7", + "api": "openai-responses", + "provider": "opencode-go", + "baseUrl": "https://opencode.ai/zen/go/v1", + "reasoning": true, + "input": [ + "text", + "image" + ], + "cost": { + "input": 2, + "output": 6, + "cacheRead": 0.5, + "cacheWrite": 0 + }, + "contextWindow": 500000, + "maxTokens": 500000, + "thinking": { + "mode": "effort", + "minLevel": "minimal", + "maxLevel": "xhigh" + } + }, "hy3": { "id": "hy3", "name": "Hy3", @@ -71892,6 +71942,31 @@ "maxLevel": "high" } }, + "x-ai/grok-4.7": { + "id": "x-ai/grok-4.7", + "name": "Grok 4.7", + "api": "openai-completions", + "provider": "openrouter", + "baseUrl": "https://openrouter.ai/api/v1", + "reasoning": true, + "input": [ + "text", + "image" + ], + "cost": { + "input": 1.6, + "output": 4.8, + "cacheRead": 0.4, + "cacheWrite": 0 + }, + "contextWindow": 500000, + "maxTokens": 450000, + "thinking": { + "mode": "effort", + "minLevel": "minimal", + "maxLevel": "xhigh" + } + }, "x-ai/grok-build-0.1": { "id": "x-ai/grok-build-0.1", "name": "Grok Build 0.1", @@ -81214,6 +81289,31 @@ "maxLevel": "xhigh" } }, + "spacexai/grok-4.7": { + "id": "spacexai/grok-4.7", + "name": "Grok 4.7", + "api": "anthropic-messages", + "provider": "vercel-ai-gateway", + "baseUrl": "https://ai-gateway.vercel.sh", + "reasoning": true, + "input": [ + "text", + "image" + ], + "cost": { + "input": 1.2, + "output": 3.6, + "cacheRead": 0.3, + "cacheWrite": 0 + }, + "contextWindow": 500000, + "maxTokens": 500000, + "thinking": { + "mode": "budget", + "minLevel": "minimal", + "maxLevel": "high" + } + }, "xai/grok-build-0.1": { "id": "xai/grok-build-0.1", "name": "Grok Build 0.1", @@ -82422,6 +82522,36 @@ "maxLevel": "high" } }, + "grok-4.7": { + "id": "grok-4.7", + "name": "Grok 4.7", + "api": "openai-completions", + "provider": "xai", + "baseUrl": "https://api.x.ai/v1", + "reasoning": true, + "input": [ + "text", + "image" + ], + "cost": { + "input": 2, + "output": 6, + "cacheRead": 0.5, + "cacheWrite": 0 + }, + "contextWindow": 500000, + "maxTokens": 500000, + "compat": { + "supportsImageDetailOriginal": false, + "supportsReasoningSummary": false, + "includeEncryptedReasoning": false + }, + "thinking": { + "mode": "effort", + "minLevel": "minimal", + "maxLevel": "xhigh" + } + }, "grok-beta": { "id": "grok-beta", "name": "Grok Beta", diff --git a/src/adapters/cursor/catalog.ts b/src/adapters/cursor/catalog.ts index e67b9598152..5453d8e223e 100644 --- a/src/adapters/cursor/catalog.ts +++ b/src/adapters/cursor/catalog.ts @@ -265,6 +265,16 @@ export const CURSOR_CAPABILITIES: Record = { fast: { levels: ["low", "medium", "high", "xhigh"] }, }, }, + // Live Cursor ids and xAI's 500k window: devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4.7": { + displayName: "Cursor Grok 4.7", + window: CONTEXT_500K, + defaultVariant: "regular", + variants: { + regular: { levels: ["low", "medium", "high", "xhigh"] }, + fast: { levels: ["low", "medium", "high", "xhigh"] }, + }, + }, "gpt-5.1": { displayName: "GPT-5.1", window: CONTEXT_272K, @@ -756,6 +766,8 @@ export function cursorGrokFastSelection( const kind = fast === true ? upgradeToFast(parsed.baseId, parsed.kind) : parsed.kind; if (!parsed.known || kind !== "fast") return undefined; const capability = CURSOR_CAPABILITIES[parsed.baseId]; + // 4.7 has no cursor- prefix and uses a flattened effort-fast id instead: + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. if (capability?.wirePrefix !== "cursor-") return undefined; const spec = capability.variants.fast; if (!spec) return undefined; diff --git a/src/adapters/cursor/discovery.ts b/src/adapters/cursor/discovery.ts index cca03619bb5..fe8b52e5a49 100644 --- a/src/adapters/cursor/discovery.ts +++ b/src/adapters/cursor/discovery.ts @@ -80,7 +80,7 @@ function inferCursorContextWindowHeuristic(modelId: string): number { if (id.includes("fable")) return CONTEXT_1M; if (id.startsWith("gpt-5.6-")) return CONTEXT_1M; if (id.startsWith("gpt-5") || id === "gpt-5-codex") return CONTEXT_272K; - if (id.startsWith("grok-4.5") || id.startsWith("grok-4.6")) return 500_000; + if (id.startsWith("grok-4.5") || id.startsWith("grok-4.6") || id.startsWith("grok-4.7")) return 500_000; if (id.startsWith("grok-")) return CONTEXT_256K; if (id.includes("claude")) return CONTEXT_200K; return CURSOR_DEFAULT_CONTEXT_WINDOW; diff --git a/src/adapters/cursor/effort-map.ts b/src/adapters/cursor/effort-map.ts index c50a289ca01..fd78b6105a6 100644 --- a/src/adapters/cursor/effort-map.ts +++ b/src/adapters/cursor/effort-map.ts @@ -84,6 +84,10 @@ const CURSOR_MODEL_EFFORT_TIERS: Record = { // Cursor's 260813 lineup exposes Grok 4.6 Extra High in both regular and Fast forms. "grok-4.6": ["low", "medium", "high", "xhigh"], "grok-4.6-fast": ["low", "medium", "high", "xhigh"], + // 4.7 live ids have no cursor- prefix and Fast follows effort; see + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4.7": ["low", "medium", "high", "xhigh"], + "grok-4.7-fast": ["low", "medium", "high", "xhigh"], "gpt-5.1": ["low", "high"], "gpt-5.1-codex-max": ["low", "medium", "high", "xhigh"], "gpt-5.1-codex-mini": ["low", "high"], diff --git a/src/adapters/cursor/request-builder.ts b/src/adapters/cursor/request-builder.ts index ec4fa07208c..6850b0cf3b2 100644 --- a/src/adapters/cursor/request-builder.ts +++ b/src/adapters/cursor/request-builder.ts @@ -209,8 +209,9 @@ export function cursorRequestEmitsFastVariant(parsed: OcxParsedRequest): boolean /** * Resolve a `cursor/` selection + Codex reasoning effort to Cursor's requested model shape. - * Most models encode effort in a flat id (`claude-4.6-opus-high`). Grok Fast is parameterized - * instead: current Cursor clients send the matching Grok base id plus `effort` and `fast` parameters. + * Most models encode effort in a flat id (`claude-4.6-opus-high`). Grok 4.5/4.6 Fast is + * parameterized: current Cursor clients send the matching base id plus `effort` and `fast` parameters; + * Grok 4.7 (no wirePrefix) instead uses the flattened effort-fast id. * A fully-qualified id (one that is not a known effort base) passes through unchanged. */ function normalizeCursorModelId(modelId: string, reasoning?: string, fast?: boolean, liveRosterScope?: string): { @@ -226,8 +227,8 @@ function normalizeCursorModelId(modelId: string, reasoning?: string, fast?: bool // resolver owns effort composition, variant dimensions, the synthetic -1m // marker (ultra -> Max Mode, evidence-gated), and the cursor- wire prefix. const id = selection.modelId; - // Grok Fast stays parameterized: current Cursor clients send the base id - // plus effort/fast parameters instead of the flattened -fast id. + // Grok 4.5/4.6 Fast stays parameterized: current Cursor clients send the base id + // plus effort/fast parameters; 4.7 (no wirePrefix) uses the flattened effort-fast id. const grokFast = cursorGrokFastSelection(id, reasoning, fast); if (grokFast) { return { diff --git a/src/adapters/devin/live-models.ts b/src/adapters/devin/live-models.ts index 7d15576ee2d..f9eaca88954 100644 --- a/src/adapters/devin/live-models.ts +++ b/src/adapters/devin/live-models.ts @@ -30,6 +30,7 @@ export const DEVIN_STATIC_MODELS = [ "glm-5-2", "kimi-k2-7", "grok-4-5", + "grok-4-7", ] as const; /** @@ -73,6 +74,9 @@ export const DEVIN_MODEL_CONTEXT_WINDOWS: Record = { "gemini-3-8-flash": 1_048_576, "grok-4-5": 500_000, "grok-4-6": 500_000, + // Live Devin catalog context_length, 2026-09-23: + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4-7": 500_000, }; /** @@ -135,6 +139,9 @@ export function sortDevinRungs(rungs: Iterable): string[] { */ export const DEVIN_MODEL_EFFORTS: Record = { "swe-2": ["medium", "high", "max"], + // Live Devin catalog, 2026-09-23: + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4-7": ["low", "medium", "high", "xhigh", "max"], }; /** diff --git a/src/generated/model-metadata.ts b/src/generated/model-metadata.ts index 9772cdd6e3b..f0824e56eab 100644 --- a/src/generated/model-metadata.ts +++ b/src/generated/model-metadata.ts @@ -49,9 +49,9 @@ const DATA: Record = { "moonshot": [["kimi-k2.5",262144,65536,"text,image",1,null,0,0,0,0]], "openai": [["codex-mini-latest",200000,100000,"text",1,null,1.5,6,0.375,0],["gpt-4",8192,8192,"text",0,null,30,60,0,0],["gpt-4-turbo",128000,4096,"text,image",0,null,10,30,0,0],["gpt-4.1",1047576,32768,"text,image",0,null,2,8,0.5,0],["gpt-4.1-mini",1047576,32768,"text,image",0,null,0.4,1.6,0.1,0],["gpt-4.1-nano",1047576,32768,"text,image",0,null,0.1,0.4,0.025,0],["gpt-4o",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-2024-05-13",128000,4096,"text,image",0,null,5,15,0,0],["gpt-4o-2024-08-06",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-2024-11-20",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-mini",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-chat-latest",128000,16384,"text,image",0,null,1.25,10,0.125,0],["gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-mini",400000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5-nano",400000,128000,"text,image",1,null,0.05,0.4,0.005,0],["gpt-5-pro",400000,272000,"text,image",1,null,15,120,0,0],["gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-chat-latest",128000,16384,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-mini",272000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5.2",400000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-chat-latest",128000,16384,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-pro",400000,128000,"text,image",1,null,21,168,0,0],["gpt-5.3-chat-latest",128000,16384,"text,image",0,null,1.75,14,0.175,0],["gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex-spark",128000,32000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.4",1050000,128000,"text,image",1,null,2.5,15,0.25,0],["gpt-5.4-mini",400000,128000,"text,image",1,null,0.75,4.5,0.075,0],["gpt-5.4-nano",400000,128000,"text,image",1,null,0.2,1.25,0.02,0],["gpt-5.4-pro",1050000,128000,"text,image",1,null,30,180,0,0],["gpt-5.5",1050000,128000,"text,image",1,null,5,30,0.5,0],["gpt-5.5-pro",1050000,128000,"text,image",1,null,30,180,0,0],["gpt-5.6",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-luna",373000,128000,"text,image",1,null,0.2,1.2,0.02,0.25],["gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-terra",373000,128000,"text,image",1,null,2,12,0.2,2.5],["gpt-6-luna",373000,128000,"text,image",1,null,0.1,0.5,0.01,0.125],["gpt-6-sol",373000,128000,"text,image",1,null,2,10,0.2,2.5],["gpt-realtime-2.1",128000,32000,"text,image",1,null,4,24,0.4,0],["o1",200000,100000,"text,image",1,null,15,60,7.5,0],["o1-pro",200000,100000,"text,image",1,null,150,600,0,0],["o3",200000,100000,"text,image",1,null,2,8,0.5,0],["o3-deep-research",200000,100000,"text,image",1,null,10,40,2.5,0],["o3-mini",200000,100000,"text",1,null,1.1,4.4,0.55,0],["o3-pro",200000,100000,"text,image",1,null,20,80,0,0],["o4-mini",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["o4-mini-deep-research",200000,100000,"text,image",1,null,2,8,0.5,0]], "openai-codex": [["codex-auto-review",1000000,128000,"text,image",1,null,0,0,0,0],["gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-codex-mini",272000,128000,"text,image",1,null,0,0,0,0],["gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.13,0],["gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-mini",272000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5.2",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex-spark",128000,128000,"text",1,null,1.75,14,0.175,0],["gpt-5.4",1000000,128000,"text,image",1,null,2.5,15,0.25,0],["gpt-5.4-mini",272000,128000,"text,image",1,null,0.75,4.5,0.075,0],["gpt-5.4-nano",272000,128000,"text,image",1,null,0.2,1.25,0.02,0],["gpt-5.5",272000,128000,"text,image",1,null,5,30,0.5,0],["gpt-5.6-luna",373000,128000,"text,image",1,null,0.2,1.2,0.02,0.25],["gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-terra",373000,128000,"text,image",1,null,2,12,0.2,2.5],["gpt-6-luna",373000,128000,"text,image",1,null,0.1,0.5,0.01,0.125],["gpt-6-sol",373000,128000,"text,image",1,null,2,10,0.2,2.5]], - "opencode-go": [["deepseek-v4-flash",1000000,384000,"text",1,null,0.14,0.28,0.0028,0],["deepseek-v4-pro",1000000,384000,"text",1,null,1.74,3.48,0.0145,0],["glm-5",204800,131072,"text",1,null,1,3.2,0.2,0],["glm-5.1",200000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.2",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.3",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.3-flash",1000000,131072,"text,image",1],["gpt-5.6-luna",1050000,128000,"text,image",1],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.5,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.5,0],["hy3",256000,64000,"text",1,null,0.14,0.58,0.035,0],["hy4-preview",1024000,64000,"text",1],["kimi-k2.5",262144,262144,"text,image",1,null,0.3,1.9,0,0],["kimi-k2.6",262144,262144,"text,image",1,null,0.95,4,0.2,0],["kimi-k2.7-code",262144,262144,"text,image",1,null,0.95,4,0.19,0],["kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["longcat-2.0",1000000,131072,"text",1],["mimo-v2-omni",262144,131072,"text,image",1,null,0.4,2,0.08,0],["mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.2,0],["mimo-v2.5",1048576,131072,"text,image",1,null,0.14,0.28,0.0028,0],["mimo-v2.5-pro",1048576,131072,"text",1,null,1.74,3.48,0.0145,0],["minimax-m2.5",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m2.7",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m3",512000,128000,"text,image",1,null,0.3,1.2,0.06,0],["muse-spark-1.2-contributor",1048576,131072,"text,image",1],["muse-spark-1.3-contributor",1048576,131072,"text,image",1],["omen-alpha",500000,128000,"text,image",1],["ox-alpha-free",1000000,131072,"text,image",1],["qwen3.5-plus",1000000,65536,"text,image",1,null,0.4,2.4,0,0],["qwen3.6-plus",1000000,65536,"text,image",1,null,2,6,0.2,2.5],["qwen3.7-max",1000000,65536,"text",1,null,2.5,7.5,0.5,3.125],["qwen3.7-plus",1000000,64000,"text,image",1,null,1.2,4.8,0.12,1.5],["qwen3.8-flash",1000000,131072,"text,image",1],["qwen3.8-max",1000000,131072,"text,image",1],["union-alpha",262144,131072,"text,image",1]], - "openrouter": [["~anthropic/claude-fable-latest",1000000,128000,"text,image",1,null,10,50,1,12.5],["~anthropic/claude-haiku-latest",200000,64000,"text,image",1,null,1,5,0.09999999999999999,1.25],["~anthropic/claude-opus-latest",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["~anthropic/claude-sonnet-latest",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["~google/gemini-flash-latest",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["~google/gemini-pro-latest",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["~moonshotai/kimi-latest",1048576,8888,"text,image",1,null,3,15,0.3,0],["~openai/gpt-latest",1050000,128000,"text,image",1,null,5,30,0.5,6.25],["~openai/gpt-mini-latest",400000,128000,"text,image",1,null,0.75,4.5,0.075,0],["~x-ai/grok-latest",500000,8888,"text,image",1,null,2,6,0.3,0],["ai21/jamba-large-1.7",256000,4096,"text",0,null,2,8,0,0],["aion-labs/aion-2.0",131072,32768,"text",1,null,0.7999999999999999,1.5999999999999999,0.19999999999999998,0],["aion-labs/aion-3.0",131072,32768,"text",1,null,3,6,0.75,0],["aion-labs/aion-3.0-mini",131072,32768,"text",1,null,0.7,1.4,0.18,0],["alibaba/tongyi-deepresearch-30b-a3b",131072,131072,"text",1,null,0.09,0.44999999999999996,0.09,0],["allenai/olmo-3.1-32b-instruct",65536,16384,"text",0,null,0.19999999999999998,0.6,0,0],["amazon/nova-2-lite-v1",1000000,65535,"text,image",1,null,0.3,2.5,0,0],["amazon/nova-lite-v1",300000,5120,"text,image",0,null,0.06,0.24,0,0],["amazon/nova-micro-v1",128000,5120,"text",0,null,0.035,0.14,0,0],["amazon/nova-premier-v1",1000000,32000,"text,image",0,null,2.5,12.5,0.625,0],["amazon/nova-pro-v1",300000,5120,"text,image",0,null,0.7999999999999999,3.1999999999999997,0,0],["anthropic/claude-3-haiku",200000,4096,"text,image",0,null,0.25,1.25,0.03,0.3],["anthropic/claude-3.5-haiku",200000,8192,"text,image",0,null,0.7999999999999999,4,0.08,1],["anthropic/claude-3.5-sonnet",200000,8192,"text,image",0,null,6,30,0.6,7.5],["anthropic/claude-3.7-sonnet",200000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-3.7-sonnet:thinking",200000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-fable-5",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-haiku-4.5",200000,64000,"text,image",0,null,1,5,0.09999999999999999,1.25],["anthropic/claude-opus-4",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.1",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.5",200000,64000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.7",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.7-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.8",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.8-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-opus-5",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-5-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-opus-5.5",1000000,128000,"text,image",1,null,4,20,0.2,5],["anthropic/claude-opus-5.5-fast",1000000,128000,"text,image",1,null,8,40,0.4,10],["anthropic/claude-sonnet-4",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.5",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.6",1000000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-5",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["arcee-ai/trinity-large-preview",131000,8888,"text",0,null,0.15,0.44999999999999996,0,0],["arcee-ai/trinity-large-preview:free",131000,8888,"text",0,null,0,0,0,0],["arcee-ai/trinity-large-thinking",262144,262144,"text",1,null,0.22,0.85,0.06,0],["arcee-ai/trinity-large-thinking:free",262144,80000,"text",1,null,0,0,0,0],["arcee-ai/trinity-mini",131072,131072,"text",1,null,0.045,0.15,0,0],["arcee-ai/trinity-mini:free",131072,8888,"text",1,null,0,0,0,0],["arcee-ai/virtuoso-large",131072,64000,"text",0,null,0.75,1.2,0,0],["auto",2000000,30000,"text,image",1,null,0,0,0,0],["baidu/cobuddy:free",131072,65536,"text",1,null,0,0,0,0],["baidu/ernie-4.5-21b-a3b",131072,8000,"text",0,null,0.07,0.28,0,0],["baidu/ernie-4.5-vl-28b-a3b",131072,8000,"text,image",1,null,0.14,0.56,0,0],["bytedance-seed/seed-1.6",262144,32768,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-1.6-flash",262144,32768,"text,image",1,null,0.075,0.3,0,0],["bytedance-seed/seed-2.0-lite",262144,131072,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-2.0-mini",262144,131072,"text,image",1,null,0.09999999999999999,0.39999999999999997,0,0],["cohere/command-r-08-2024",128000,4000,"text",0,null,0.15,0.6,0,0],["cohere/command-r-plus-08-2024",128000,4000,"text",0,null,2.5,10,0,0],["cohere/north-mini-code:free",256000,64000,"text",1,null,0,0,0,0],["deepseek/deepseek-chat",163840,16000,"text",0,null,0.20020000000000002,0.8000999999999999,0.15,0],["deepseek/deepseek-chat-v3-0324",163840,65536,"text",1,null,0.27,1.12,0.135,0],["deepseek/deepseek-chat-v3.1",163840,32768,"text",1,null,0.25,0.95,0.13,0],["deepseek/deepseek-r1",163840,16000,"text",1,null,0.7,2.5,0,0],["deepseek/deepseek-r1-0528",163840,32768,"text",1,null,0.5,2.1500000000000004,0.35,0],["deepseek/deepseek-v3.1-terminus",163840,32768,"text",1,null,0.27,1,0.135,0],["deepseek/deepseek-v3.1-terminus:exacto",163840,8888,"text",1,null,0.21,0.7899999999999999,0.16799999999999998,0],["deepseek/deepseek-v3.2",163840,65536,"text",1,null,0.26899999999999996,0.39999999999999997,0.13449999999999998,0],["deepseek/deepseek-v3.2-exp",163840,65536,"text",1,null,0.27,0.41,0,0],["deepseek/deepseek-v4-flash",1048576,384000,"text",1,null,0.09380000000000001,0.18760000000000002,0.01876,0],["deepseek/deepseek-v4-flash:free",1048576,384000,"text",1,null,0,0,0,0],["deepseek/deepseek-v4-pro",1048576,384000,"text",1,null,0.435,0.87,0.003625,0],["essentialai/rnj-1-instruct",32768,8888,"text",0,null,0.15,0.15,0,0],["google/gemini-2.0-flash-001",1048576,8192,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0.08333333333333334],["google/gemini-2.0-flash-lite-001",1048576,8192,"text,image",0,null,0.075,0.3,0,0],["google/gemini-2.5-flash",1048576,65535,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-flash-lite",1048576,65535,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-lite-preview-09-2025",1048576,65535,"text,image",1,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-preview-09-2025",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-pro",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview-05-06",1048576,65535,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-3-flash-preview",1048576,65535,"text,image",1,null,0.5,3,0.049999999999999996,0.08333333333333334],["google/gemini-3-pro-image",131072,32768,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3-pro-preview",1048000,64000,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-flash-lite",1048576,65536,"text,image",1,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-flash-lite-preview",1048576,65536,"text,image",0,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-pro-preview",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-pro-preview-customtools",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.5-flash",1048576,65536,"text,image",1,null,1.5,9,0.15,0.08333333333333334],["google/gemini-3.5-flash-lite",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-3.6-flash",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["google/gemma-3-12b-it",131072,16384,"text,image",0,null,0.049999999999999996,0.15,0,0],["google/gemma-3-27b-it",262144,131072,"text,image",1,null,0.08,0.44999999999999996,0.04,0],["google/gemma-3-27b-it:free",131072,8192,"text,image",0,null,0,0,0,0],["google/gemma-4-26b-a4b-it",262144,262144,"text,image",1,null,0.12,0.35,0.049999999999999996,0],["google/gemma-4-26b-a4b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["google/gemma-4-31b-it",262144,262144,"text,image",1,null,0.14,0.39999999999999997,0.09,0],["google/gemma-4-31b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["ibm-granite/granite-4.1-8b",131072,131072,"text",0,null,0.049999999999999996,0.09999999999999999,0.049999999999999996,0],["inception/mercury",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-2",128000,50000,"text",1,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-coder",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inclusionai/ling-2.6-1t",262144,32768,"text",0,null,0.075,0.625,0.015,0],["inclusionai/ling-2.6-1t:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-2.6-flash",262144,32768,"text",0,null,0.01,0.03,0.002,0],["inclusionai/ling-2.6-flash:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-3.0-flash:free",262144,32768,"text",1,null,0,0,0,0],["inclusionai/ring-2.6-1t",262144,65536,"text",1,null,0.075,0.625,0.015,0],["inclusionai/ring-2.6-1t:free",262144,65536,"text",1,null,0,0,0,0],["kwaipilot/kat-coder-air-v2.5",256000,80000,"text",0,null,0.15,0.6,0.03,0],["kwaipilot/kat-coder-pro",256000,128000,"text",0,null,0.207,0.828,0.0414,0],["kwaipilot/kat-coder-pro-v2",262144,80000,"text",0,null,0.3,1.2,0.06,0],["kwaipilot/kat-coder-pro-v2.5",256000,80000,"text",0,null,0.74,2.96,0.15,0],["liquid/lfm-2.5-1.2b-thinking:free",32768,8888,"text",1,null,0,0,0,0],["meituan/longcat-2.0",1048756,262144,"text",1,null,0.3,1.2,0.006,0],["meituan/longcat-flash-chat",131072,131072,"text",0,null,0.19999999999999998,0.7999999999999999,0.19999999999999998,0],["meta-llama/llama-3-8b-instruct",8192,16384,"text",0,null,0.03,0.04,0,0],["meta-llama/llama-3.1-405b-instruct",131000,8888,"text",0,null,4,4,0,0],["meta-llama/llama-3.1-70b-instruct",131072,16384,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["meta-llama/llama-3.1-8b-instruct",131072,131072,"text",0,null,0.049999999999999996,0.08,0.024999999999999998,0],["meta-llama/llama-3.3-70b-instruct",131072,128000,"text",0,null,0.13,0.39999999999999997,0,0],["meta-llama/llama-3.3-70b-instruct:free",131072,8888,"text",0,null,0,0,0,0],["meta-llama/llama-4-maverick",1048576,16384,"text,image",0,null,0.19999999999999998,0.7999999999999999,0,0],["meta-llama/llama-4-scout",1310720,16384,"text,image",0,null,0.09999999999999999,0.3,0,0],["meta/muse-spark-1.1",1048576,8888,"text,image",1,null,1.25,4.25,0.15,0],["minimax/minimax-m1",1000000,40000,"text",1,null,0.55,2.2,0,0],["minimax/minimax-m2",204800,131072,"text",1,null,0.255,1.02,0.03,0],["minimax/minimax-m2.1",204800,131072,"text",1,null,0.3,1.2,0.03,0],["minimax/minimax-m2.5",204800,196608,"text",1,null,0.15,0.8999999999999999,0.049999999999999996,0],["minimax/minimax-m2.5:free",262144,8192,"text",1,null,0,0,0,0],["minimax/minimax-m2.7",204800,131072,"text",1,null,0.25,1,0.049999999999999996,0],["minimax/minimax-m3",1048576,512000,"text,image",1,null,0.3,1.2,0.06,0],["mistralai/codestral-2508",256000,8888,"text",0,null,0.3,0.8999999999999999,0.03,0],["mistralai/devstral-2512",262144,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-medium",131072,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-small",131072,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/ministral-14b-2512",262144,8888,"text,image",0,null,0.19999999999999998,0.19999999999999998,0.02,0],["mistralai/ministral-3b-2512",131072,8888,"text,image",0,null,0.09999999999999999,0.09999999999999999,0.01,0],["mistralai/ministral-8b-2512",262144,8888,"text,image",0,null,0.15,0.15,0.015,0],["mistralai/mistral-large",128000,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2407",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2411",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2512",262144,8888,"text,image",0,null,0.5,1.5,0.049999999999999996,0],["mistralai/mistral-medium-3",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-medium-3-5",262144,8888,"text,image",1,null,1.5,7.5,0,0],["mistralai/mistral-medium-3.1",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-nemo",131072,16384,"text",0,null,0.019000000000000003,0.03,0,0],["mistralai/mistral-saba",32768,8888,"text",0,null,0.19999999999999998,0.6,0.02,0],["mistralai/mistral-small-24b-instruct-2501",32768,16384,"text",0,null,0.049999999999999996,0.08,0,0],["mistralai/mistral-small-2603",262144,8888,"text,image",1,null,0.15,0.6,0.015,0],["mistralai/mistral-small-3.1-24b-instruct",131072,131072,"text,image",0,null,0.03,0.11,0.015,0],["mistralai/mistral-small-3.1-24b-instruct:free",128000,8888,"text,image",0,null,0,0,0,0],["mistralai/mistral-small-3.2-24b-instruct",256000,8888,"text,image",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mistral-small-creative",32768,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mixtral-8x22b-instruct",65536,13108,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mixtral-8x7b-instruct",32768,16384,"text",0,null,0.54,0.54,0,0],["mistralai/pixtral-large-2411",131072,8888,"text,image",0,null,2,6,0.19999999999999998,0],["mistralai/voxtral-small-24b-2507",32000,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["moonshotai/kimi-k2",131072,100352,"text",0,null,0.5700000000000001,2.3,0,0],["moonshotai/kimi-k2-0905",262144,100352,"text",0,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2-0905:exacto",262144,8888,"text",0,null,0.6,2.5,0,0],["moonshotai/kimi-k2-thinking",262144,100352,"text",1,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2.5",262144,262144,"text,image",1,null,0.5700000000000001,2.8499999999999996,0.095,0],["moonshotai/kimi-k2.6",262144,262144,"text,image",1,null,0.646,2.7199999999999998,0.1088,0],["moonshotai/kimi-k2.6:free",262144,8888,"text,image",1,null,0,0,0,0],["moonshotai/kimi-k2.7-code",262144,262144,"text,image",1,null,0.78,3.5,0.15,0],["moonshotai/kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["nex-agi/deepseek-v3.1-nex-n1",131072,163840,"text",0,null,0.135,0.5,0,0],["nex-agi/nex-n2-mini",262144,262144,"text,image",1,null,0.024999999999999998,0.09999999999999999,0.0025,0],["nex-agi/nex-n2-pro",262144,262144,"text,image",1,null,0.25,1,0.024999999999999998,0],["nex-agi/nex-n2-pro:free",262144,262144,"text,image",1,null,0,0,0,0],["nousresearch/deephermes-3-mistral-24b-preview",32768,32768,"text",1,null,0.02,0.09999999999999999,0.01,0],["nousresearch/hermes-4-70b",131072,131072,"text",1,null,0.11,0.38,0.055,0],["nvidia/llama-3.1-nemotron-70b-instruct",131072,16384,"text",0,null,1.2,1.2,0,0],["nvidia/llama-3.3-nemotron-super-49b-v1.5",131072,16384,"text",1,null,0.39999999999999997,0.39999999999999997,0,0],["nvidia/nemotron-3-nano-30b-a3b",262144,228000,"text",1,null,0.049999999999999996,0.19999999999999998,0,0],["nvidia/nemotron-3-nano-30b-a3b:free",256000,8888,"text",1,null,0,0,0,0],["nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",256000,65536,"text,image",1,null,0,0,0,0],["nvidia/nemotron-3-super-120b-a12b",1000000,16384,"text",1,null,0.08499999999999999,0.39999999999999997,0.09999999999999999,0],["nvidia/nemotron-3-super-120b-a12b:free",262144,262144,"text",1,null,0,0,0,0],["nvidia/nemotron-3-ultra-550b-a55b",512288,65536,"text",1,null,0.6,3.5999999999999996,0.19999999999999998,0],["nvidia/nemotron-3-ultra-550b-a55b:free",1000000,65536,"text",1,null,0,0,0,0],["nvidia/nemotron-nano-12b-v2-vl:free",128000,128000,"text,image",1,null,0,0,0,0],["nvidia/nemotron-nano-9b-v2",131072,16384,"text",1,null,0.04,0.16,0,0],["nvidia/nemotron-nano-9b-v2:free",128000,8888,"text",1,null,0,0,0,0],["openai/gpt-3.5-turbo",16385,4096,"text",0,null,0.5,1.5,0,0],["openai/gpt-3.5-turbo-0613",4095,4096,"text",0,null,1,2,0,0],["openai/gpt-3.5-turbo-16k",16385,4096,"text",0,null,3,4,0,0],["openai/gpt-4",8191,8192,"text",0,null,30,60,0,0],["openai/gpt-4-0314",8191,4096,"text",0,null,30,60,0,0],["openai/gpt-4-1106-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4-turbo",128000,4096,"text,image",0,null,10,30,0,0],["openai/gpt-4-turbo-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4.1",1047576,32768,"text,image",0,null,2,8,0.5,0],["openai/gpt-4.1-mini",1047576,32768,"text,image",0,null,0.39999999999999997,1.5999999999999999,0.09999999999999999,0],["openai/gpt-4.1-nano",1047576,32768,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0],["openai/gpt-4o",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-05-13",128000,4096,"text,image",0,null,5,15,0,0],["openai/gpt-4o-2024-08-06",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-11-20",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-audio-preview",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-4o-mini",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o-mini-2024-07-18",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o:extended",128000,64000,"text,image",0,null,6,18,0,0],["openai/gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-image",400000,128000,"text,image",1,null,10,10,1.25,0],["openai/gpt-5-image-mini",400000,128000,"text,image",1,null,2.5,2,0.25,0],["openai/gpt-5-mini",400000,128000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5-nano",400000,128000,"text,image",1,null,0.049999999999999996,0.39999999999999997,0.005,0],["openai/gpt-5-pro",400000,128000,"text,image",1,null,15,120,0,0],["openai/gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-chat",128000,16384,"text,image",0,null,1.25,10,0.125,0],["openai/gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-mini",272000,100000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5.2",400000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-chat",128000,16384,"text,image",0,null,1.75,14,0.175,0],["openai/gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-pro",400000,128000,"text,image",1,null,21,168,0,0],["openai/gpt-5.3-chat",128000,16384,"text",0,null,1.75,14,0.175,0],["openai/gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.4",1050000,128000,"text,image",1,null,2.5,15,0.25,0],["openai/gpt-5.4-mini",400000,128000,"text",0,null,0.75,4.5,0.075,0],["openai/gpt-5.4-nano",400000,128000,"text",0,null,0.19999999999999998,1.25,0.02,0],["openai/gpt-5.4-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.5",1050000,128000,"text,image",1,null,5,30,0.5,0],["openai/gpt-5.5-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.6-luna",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-luna-pro",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-sol-pro",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-terra",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-5.6-terra-pro",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-6-luna",373000,128000,"text,image",1,null,0.1,0.5,0.01,0.125],["openai/gpt-6-sol",373000,128000,"text,image",1,null,2,10,0.2,2.5],["openai/gpt-audio",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-audio-mini",128000,16384,"text",0,null,0.6,2.4,0,0],["openai/gpt-chat-latest",400000,128000,"text,image",0,null,5,30,0.5,0],["openai/gpt-oss-120b",131072,131072,"text",1,null,0.037,0.16999999999999998,0,0],["openai/gpt-oss-120b:exacto",131072,8888,"text",1,null,0.039,0.19,0,0],["openai/gpt-oss-120b:free",131072,131072,"text",1,null,0,0,0,0],["openai/gpt-oss-20b",131072,131072,"text",1,null,0.03,0.13,0.03,0],["openai/gpt-oss-20b:free",131072,32768,"text",1,null,0,0,0,0],["openai/gpt-oss-safeguard-20b",131072,65536,"text",1,null,0.075,0.3,0.0375,0],["openai/o1",200000,100000,"text,image",1,null,15,60,7.5,0],["openai/o3",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o3-deep-research",200000,100000,"text,image",1,null,10,40,2.5,0],["openai/o3-mini",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-mini-high",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-pro",200000,100000,"text,image",1,null,20,80,0,0],["openai/o4-mini",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openai/o4-mini-deep-research",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o4-mini-high",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openrouter/aurora-alpha",128000,50000,"text",1,null,0,0,0,0],["openrouter/auto",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/auto-beta",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/elephant-alpha",262144,32768,"text",0,null,0,0,0,0],["openrouter/free",200000,8888,"text,image",1,null,0,0,0,0],["openrouter/healer-alpha",262144,32000,"text,image",1,null,0,0,0,0],["openrouter/hunter-alpha",1048576,32000,"text",1,null,0,0,0,0],["openrouter/owl-alpha",1048756,262144,"text",0,null,0,0,0,0],["poolside/laguna-m.1",262144,32768,"text",1,null,0.19999999999999998,0.39999999999999997,0.09999999999999999,0],["poolside/laguna-m.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-s-2.1",1048576,131072,"text",1,null,0.09999999999999999,0.19999999999999998,0.01,0],["poolside/laguna-s-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs-2.1",262144,32768,"text",1,null,0.06,0.12,0.03,0],["poolside/laguna-xs-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs.2",262144,32768,"text",1,null,0.09999999999999999,0.19999999999999998,0.049999999999999996,0],["poolside/laguna-xs.2:free",262144,32768,"text",1,null,0,0,0,0],["prime-intellect/intellect-3",131072,131072,"text",1,null,0.19999999999999998,1.1,0,0],["qwen/qwen-2.5-72b-instruct",32768,16384,"text",0,null,0.36,0.39999999999999997,0,0],["qwen/qwen-2.5-7b-instruct",32768,32768,"text",0,null,0.04,0.09999999999999999,0,0],["qwen/qwen-max",32768,8192,"text",0,null,1.04,4.16,0.20800000000000002,0],["qwen/qwen-plus",1000000,32768,"text",0,null,0.26,0.78,0.052000000000000005,0.325],["qwen/qwen-plus-2025-07-28",1000000,32768,"text",0,null,0.26,0.78,0,0.325],["qwen/qwen-plus-2025-07-28:thinking",1000000,32768,"text",1,null,0.26,0.78,0,0.325],["qwen/qwen-turbo",131072,8192,"text",0,null,0.0325,0.13,0.006500000000000001,0],["qwen/qwen-vl-max",131072,32768,"text,image",0,null,0.52,2.08,0,0],["qwen/qwen3-14b",131072,8192,"text",1,null,0.22749999999999998,0.9099999999999999,0,0],["qwen/qwen3-235b-a22b",131072,8192,"text",1,null,0.45499999999999996,1.8199999999999998,0,0],["qwen/qwen3-235b-a22b-2507",262144,16384,"text",1,null,0.09,0.55,0,0],["qwen/qwen3-235b-a22b-thinking-2507",262144,32768,"text",1,null,0.3,3,0.09999999999999999,0],["qwen/qwen3-30b-a3b",131072,8192,"text",1,null,0.13,0.52,0,0],["qwen/qwen3-30b-a3b-instruct-2507",262144,32000,"text",0,null,0.04815,0.19305,0,0],["qwen/qwen3-30b-a3b-thinking-2507",81920,32768,"text",1,null,0.13,1.56,0.08,0],["qwen/qwen3-32b",131072,16384,"text",1,null,0.08,0.28,0.04,0],["qwen/qwen3-4b",131072,8192,"text",1,null,0.0715,0.273,0,0],["qwen/qwen3-4b:free",40960,8888,"text",1,null,0,0,0,0],["qwen/qwen3-8b",131072,8192,"text",1,null,0.117,0.45499999999999996,0.049999999999999996,0],["qwen/qwen3-coder",262144,65536,"text",0,null,0.3,1,0.09999999999999999,0],["qwen/qwen3-coder-30b-a3b-instruct",262144,32768,"text",0,null,0.07,0.27,0,0],["qwen/qwen3-coder-flash",1000000,65536,"text",0,null,0.195,0.975,0.039,0.24375],["qwen/qwen3-coder-next",262144,262144,"text",0,null,0.11,0.7999999999999999,0.07,0],["qwen/qwen3-coder-plus",1000000,65536,"text",0,null,0.65,3.25,0.13,0.8125],["qwen/qwen3-coder:exacto",262144,65536,"text",0,null,0.22,1.7999999999999998,0.022,0],["qwen/qwen3-coder:free",1048576,262000,"text",0,null,0,0,0,0],["qwen/qwen3-max",262144,32768,"text",1,null,0.78,3.9,0.156,0.975],["qwen/qwen3-max-thinking",262144,32768,"text",1,null,0.78,3.9,0,0],["qwen/qwen3-next-80b-a3b-instruct",262144,262144,"text",0,null,0.09999999999999999,1.1,0.07,0],["qwen/qwen3-next-80b-a3b-instruct:free",262144,8888,"text",0,null,0,0,0,0],["qwen/qwen3-next-80b-a3b-thinking",262144,32768,"text",1,null,0.0975,0.78,0,0],["qwen/qwen3-vl-235b-a22b-instruct",262144,32768,"text,image",0,null,0.21,1.9,0.09999999999999999,0],["qwen/qwen3-vl-235b-a22b-thinking",131072,32768,"text,image",1,null,0.26,2.6,0,0],["qwen/qwen3-vl-30b-a3b-instruct",262144,16384,"text,image",0,null,0.15,0.6,0,0],["qwen/qwen3-vl-30b-a3b-thinking",262144,32768,"text,image",1,null,0.13,1.56,0,0],["qwen/qwen3-vl-32b-instruct",131072,32768,"text,image",0,null,0.10400000000000001,0.41600000000000004,0,0],["qwen/qwen3-vl-8b-instruct",262144,32768,"text,image",0,null,0.117,0.45499999999999996,0,0],["qwen/qwen3-vl-8b-thinking",131072,32768,"text,image",1,null,0.117,1.365,0,0],["qwen/qwen3.5-122b-a10b",262144,65536,"text,image",1,null,0.26,2.08,0,0],["qwen/qwen3.5-27b",262144,65536,"text,image",1,null,0.195,1.56,0,0],["qwen/qwen3.5-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.5-397b-a17b",262144,65536,"text,image",1,null,0.39,2.34,0.111,0],["qwen/qwen3.5-9b",262144,262144,"text,image",1,null,0.09999999999999999,0.15,0,0],["qwen/qwen3.5-flash-02-23",1000000,65536,"text,image",1,null,0.065,0.26,0,0.08125],["qwen/qwen3.5-plus-02-15",1000000,65536,"text,image",1,null,0.26,1.56,0,0.325],["qwen/qwen3.5-plus-20260420",1000000,65536,"text,image",1,null,0.3,1.7999999999999998,0,0.375],["qwen/qwen3.6-27b",262144,131072,"text,image",1,null,0.28900000000000003,2.4,0.15,0],["qwen/qwen3.6-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.6-flash",1000000,65536,"text,image",1,null,0.1875,1.125,0,0.234375],["qwen/qwen3.6-max-preview",262144,65536,"text",1,null,1.04,6.24,0,1.3],["qwen/qwen3.6-plus",1000000,65536,"text",1,null,0.325,1.95,0,0.40625],["qwen/qwen3.6-plus-preview:free",1000000,32000,"text",1,null,0,0,0,0],["qwen/qwen3.6-plus:free",1000000,65536,"text,image",1,null,0,0,0,0],["qwen/qwen3.7-max",1000000,65536,"text",1,null,1.475,4.425,0.295,1.84375],["qwen/qwen3.7-plus",1000000,65536,"text,image",1,null,0.32,1.28,0.064,0.39999999999999997],["qwen/qwq-32b",131072,131072,"text",1,null,0.15,0.58,0,0],["reka/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["rekaai/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["relace/relace-search",256000,128000,"text",0,null,1,3,0,0],["sakana/fugu-ultra",1000000,128000,"text,image",1,null,5,30,0.5,0],["sao10k/l3-euryale-70b",8192,8192,"text",0,null,1.48,1.48,0,0],["sao10k/l3.1-euryale-70b",131072,16384,"text",0,null,0.85,0.85,0,0],["stepfun/step-3.5-flash",262144,65536,"text",0,null,0.09999999999999999,0.3,0.02,0],["stepfun/step-3.5-flash:free",256000,256000,"text",1,null,0,0,0,0],["stepfun/step-3.7-flash",262144,256000,"text,image",1,null,0.19999999999999998,1.15,0.04,0],["tencent/hy3",262144,128000,"text",1,null,0.13199999999999998,0.5279999999999999,0.032999999999999995,0],["tencent/hy3-preview",262144,64000,"text",1,null,0.063,0.21,0.020999999999999998,0],["tencent/hy3-preview:free",262144,262144,"text",1,null,0,0,0,0],["tencent/hy3:free",262144,262144,"text",1,null,0,0,0,0],["thedrummer/rocinante-12b",32768,32768,"text",0,null,0.16999999999999998,0.43,0,0],["thedrummer/unslopnemo-12b",32768,32768,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["thinkingmachines/inkling",1048576,8888,"text,image",1,null,1,4.05,0.16999999999999998,0],["tngtech/deepseek-r1t2-chimera",163840,163840,"text",1,null,0.3,1.1,0.15,0],["tngtech/tng-r1t-chimera",163840,65536,"text",1,null,0.25,0.85,0.125,0],["upstage/solar-pro-3",128000,8888,"text",1,null,0.15,0.6,0.015,0],["upstage/solar-pro-3:free",128000,8888,"text",1,null,0,0,0,0],["x-ai/grok-3",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-beta",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-mini",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-3-mini-beta",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-4",256000,64000,"text,image",1,null,3,15,0.75,0],["x-ai/grok-4-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.1-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.20",2000000,8888,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.20-beta",2000000,8888,"text,image",1,null,2,6,0.19999999999999998,0],["x-ai/grok-4.3",1000000,1000000,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.19999999999999998,0],["x-ai/grok-code-fast-1",256000,10000,"text",1,null,0.19999999999999998,1.5,0.02,0],["xiaomi/mimo-v2-flash",262144,65536,"text",1,null,0.09999999999999999,0.3,0.01,0],["xiaomi/mimo-v2-omni",262144,65536,"text,image",1,null,0.39999999999999997,2,0.08,0],["xiaomi/mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.19999999999999998,0],["xiaomi/mimo-v2.5",1050000,131072,"text,image",1,null,0.14,0.28,0.0028,0],["xiaomi/mimo-v2.5-pro",1050000,131072,"text",1,null,0.435,0.87,0.0036,0],["z-ai/glm-4-32b",128000,8888,"text",0,null,0.09999999999999999,0.09999999999999999,0,0],["z-ai/glm-4.5",131072,98304,"text",1,null,0.6,2.2,0.11,0],["z-ai/glm-4.5-air",131072,98304,"text",1,null,0.13,0.85,0.024999999999999998,0],["z-ai/glm-4.5-air:free",131072,96000,"text",1,null,0,0,0,0],["z-ai/glm-4.5v",65536,16384,"text,image",1,null,0.6,1.7999999999999998,0.11,0],["z-ai/glm-4.6",204800,131072,"text",1,null,0.5,2,0.09999999999999999,0],["z-ai/glm-4.6:exacto",204800,131072,"text",1,null,0.44,1.76,0.11,0],["z-ai/glm-4.6v",131072,32768,"text,image",1,null,0.3,0.8999999999999999,0.055,0],["z-ai/glm-4.7",204800,131072,"text",1,null,0.39999999999999997,1.75,0.08,0],["z-ai/glm-4.7-flash",202752,16384,"text",1,null,0.06,0.39999999999999997,0.01,0],["z-ai/glm-5",204800,131072,"text",1,null,0.95,2.5500000000000003,0.19999999999999998,0],["z-ai/glm-5-turbo",202752,131072,"text",1,null,1.2,4,0.24,0],["z-ai/glm-5.1",204800,128000,"text",1,null,0.966,3.036,0.1794,0],["z-ai/glm-5.2",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5.3",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5v-turbo",202752,131072,"text,image",1,null,1.2,4,0.24,0]], - "xai": [["grok-2",131072,8192,"text",0,null,2,10,2,0],["grok-2-1212",131072,8192,"text",0,null,2,10,2,0],["grok-2-latest",131072,8192,"text",0,null,2,10,2,0],["grok-2-vision",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-1212",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-latest",8192,4096,"text,image",0,null,2,10,2,0],["grok-3",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-fast",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-fast-latest",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-latest",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-mini",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-3-mini-fast",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-fast-latest",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-latest",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-4",256000,64000,"text",1,null,3,15,0.75,0],["grok-4-1-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-1-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4.20-0309-non-reasoning",1000000,30000,"text,image",0,null,1.25,2.5,0.2,0],["grok-4.20-0309-reasoning",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-beta-latest-non-reasoning",2000000,30000,"text,image",0,null,2,6,0.2,0],["grok-4.20-beta-latest-reasoning",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.20-multi-agent-0309",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-multi-agent-beta-latest",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.3",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-beta",131072,4096,"text",0,null,5,15,5,0],["grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.2,0],["grok-code-fast-1",256000,10000,"text",1,null,0.2,1.5,0.02,0],["grok-composer-2.5-fast",200000,64000,"text",1,null,0,0,0,0],["grok-vision-beta",8192,4096,"text,image",0,null,5,15,5,0]], + "opencode-go": [["deepseek-v4-flash",1000000,384000,"text",1,null,0.14,0.28,0.0028,0],["deepseek-v4-pro",1000000,384000,"text",1,null,1.74,3.48,0.0145,0],["glm-5",204800,131072,"text",1,null,1,3.2,0.2,0],["glm-5.1",200000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.2",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.3",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.3-flash",1000000,131072,"text,image",1],["gpt-5.6-luna",1050000,128000,"text,image",1],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.5,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.5,0],["grok-4.7",500000,500000,"text,image",1,null,2,6,0.5,0],["hy3",256000,64000,"text",1,null,0.14,0.58,0.035,0],["hy4-preview",1024000,64000,"text",1],["kimi-k2.5",262144,262144,"text,image",1,null,0.3,1.9,0,0],["kimi-k2.6",262144,262144,"text,image",1,null,0.95,4,0.2,0],["kimi-k2.7-code",262144,262144,"text,image",1,null,0.95,4,0.19,0],["kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["longcat-2.0",1000000,131072,"text",1],["mimo-v2-omni",262144,131072,"text,image",1,null,0.4,2,0.08,0],["mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.2,0],["mimo-v2.5",1048576,131072,"text,image",1,null,0.14,0.28,0.0028,0],["mimo-v2.5-pro",1048576,131072,"text",1,null,1.74,3.48,0.0145,0],["minimax-m2.5",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m2.7",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m3",512000,128000,"text,image",1,null,0.3,1.2,0.06,0],["muse-spark-1.2-contributor",1048576,131072,"text,image",1],["muse-spark-1.3-contributor",1048576,131072,"text,image",1],["omen-alpha",500000,128000,"text,image",1],["ox-alpha-free",1000000,131072,"text,image",1],["qwen3.5-plus",1000000,65536,"text,image",1,null,0.4,2.4,0,0],["qwen3.6-plus",1000000,65536,"text,image",1,null,2,6,0.2,2.5],["qwen3.7-max",1000000,65536,"text",1,null,2.5,7.5,0.5,3.125],["qwen3.7-plus",1000000,64000,"text,image",1,null,1.2,4.8,0.12,1.5],["qwen3.8-flash",1000000,131072,"text,image",1],["qwen3.8-max",1000000,131072,"text,image",1],["union-alpha",262144,131072,"text,image",1]], + "openrouter": [["~anthropic/claude-fable-latest",1000000,128000,"text,image",1,null,10,50,1,12.5],["~anthropic/claude-haiku-latest",200000,64000,"text,image",1,null,1,5,0.09999999999999999,1.25],["~anthropic/claude-opus-latest",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["~anthropic/claude-sonnet-latest",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["~google/gemini-flash-latest",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["~google/gemini-pro-latest",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["~moonshotai/kimi-latest",1048576,8888,"text,image",1,null,3,15,0.3,0],["~openai/gpt-latest",1050000,128000,"text,image",1,null,5,30,0.5,6.25],["~openai/gpt-mini-latest",400000,128000,"text,image",1,null,0.75,4.5,0.075,0],["~x-ai/grok-latest",500000,8888,"text,image",1,null,2,6,0.3,0],["ai21/jamba-large-1.7",256000,4096,"text",0,null,2,8,0,0],["aion-labs/aion-2.0",131072,32768,"text",1,null,0.7999999999999999,1.5999999999999999,0.19999999999999998,0],["aion-labs/aion-3.0",131072,32768,"text",1,null,3,6,0.75,0],["aion-labs/aion-3.0-mini",131072,32768,"text",1,null,0.7,1.4,0.18,0],["alibaba/tongyi-deepresearch-30b-a3b",131072,131072,"text",1,null,0.09,0.44999999999999996,0.09,0],["allenai/olmo-3.1-32b-instruct",65536,16384,"text",0,null,0.19999999999999998,0.6,0,0],["amazon/nova-2-lite-v1",1000000,65535,"text,image",1,null,0.3,2.5,0,0],["amazon/nova-lite-v1",300000,5120,"text,image",0,null,0.06,0.24,0,0],["amazon/nova-micro-v1",128000,5120,"text",0,null,0.035,0.14,0,0],["amazon/nova-premier-v1",1000000,32000,"text,image",0,null,2.5,12.5,0.625,0],["amazon/nova-pro-v1",300000,5120,"text,image",0,null,0.7999999999999999,3.1999999999999997,0,0],["anthropic/claude-3-haiku",200000,4096,"text,image",0,null,0.25,1.25,0.03,0.3],["anthropic/claude-3.5-haiku",200000,8192,"text,image",0,null,0.7999999999999999,4,0.08,1],["anthropic/claude-3.5-sonnet",200000,8192,"text,image",0,null,6,30,0.6,7.5],["anthropic/claude-3.7-sonnet",200000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-3.7-sonnet:thinking",200000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-fable-5",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-haiku-4.5",200000,64000,"text,image",0,null,1,5,0.09999999999999999,1.25],["anthropic/claude-opus-4",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.1",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.5",200000,64000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.7",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.7-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.8",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.8-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-opus-5",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-5-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-opus-5.5",1000000,128000,"text,image",1,null,4,20,0.2,5],["anthropic/claude-opus-5.5-fast",1000000,128000,"text,image",1,null,8,40,0.4,10],["anthropic/claude-sonnet-4",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.5",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.6",1000000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-5",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["arcee-ai/trinity-large-preview",131000,8888,"text",0,null,0.15,0.44999999999999996,0,0],["arcee-ai/trinity-large-preview:free",131000,8888,"text",0,null,0,0,0,0],["arcee-ai/trinity-large-thinking",262144,262144,"text",1,null,0.22,0.85,0.06,0],["arcee-ai/trinity-large-thinking:free",262144,80000,"text",1,null,0,0,0,0],["arcee-ai/trinity-mini",131072,131072,"text",1,null,0.045,0.15,0,0],["arcee-ai/trinity-mini:free",131072,8888,"text",1,null,0,0,0,0],["arcee-ai/virtuoso-large",131072,64000,"text",0,null,0.75,1.2,0,0],["auto",2000000,30000,"text,image",1,null,0,0,0,0],["baidu/cobuddy:free",131072,65536,"text",1,null,0,0,0,0],["baidu/ernie-4.5-21b-a3b",131072,8000,"text",0,null,0.07,0.28,0,0],["baidu/ernie-4.5-vl-28b-a3b",131072,8000,"text,image",1,null,0.14,0.56,0,0],["bytedance-seed/seed-1.6",262144,32768,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-1.6-flash",262144,32768,"text,image",1,null,0.075,0.3,0,0],["bytedance-seed/seed-2.0-lite",262144,131072,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-2.0-mini",262144,131072,"text,image",1,null,0.09999999999999999,0.39999999999999997,0,0],["cohere/command-r-08-2024",128000,4000,"text",0,null,0.15,0.6,0,0],["cohere/command-r-plus-08-2024",128000,4000,"text",0,null,2.5,10,0,0],["cohere/north-mini-code:free",256000,64000,"text",1,null,0,0,0,0],["deepseek/deepseek-chat",163840,16000,"text",0,null,0.20020000000000002,0.8000999999999999,0.15,0],["deepseek/deepseek-chat-v3-0324",163840,65536,"text",1,null,0.27,1.12,0.135,0],["deepseek/deepseek-chat-v3.1",163840,32768,"text",1,null,0.25,0.95,0.13,0],["deepseek/deepseek-r1",163840,16000,"text",1,null,0.7,2.5,0,0],["deepseek/deepseek-r1-0528",163840,32768,"text",1,null,0.5,2.1500000000000004,0.35,0],["deepseek/deepseek-v3.1-terminus",163840,32768,"text",1,null,0.27,1,0.135,0],["deepseek/deepseek-v3.1-terminus:exacto",163840,8888,"text",1,null,0.21,0.7899999999999999,0.16799999999999998,0],["deepseek/deepseek-v3.2",163840,65536,"text",1,null,0.26899999999999996,0.39999999999999997,0.13449999999999998,0],["deepseek/deepseek-v3.2-exp",163840,65536,"text",1,null,0.27,0.41,0,0],["deepseek/deepseek-v4-flash",1048576,384000,"text",1,null,0.09380000000000001,0.18760000000000002,0.01876,0],["deepseek/deepseek-v4-flash:free",1048576,384000,"text",1,null,0,0,0,0],["deepseek/deepseek-v4-pro",1048576,384000,"text",1,null,0.435,0.87,0.003625,0],["essentialai/rnj-1-instruct",32768,8888,"text",0,null,0.15,0.15,0,0],["google/gemini-2.0-flash-001",1048576,8192,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0.08333333333333334],["google/gemini-2.0-flash-lite-001",1048576,8192,"text,image",0,null,0.075,0.3,0,0],["google/gemini-2.5-flash",1048576,65535,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-flash-lite",1048576,65535,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-lite-preview-09-2025",1048576,65535,"text,image",1,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-preview-09-2025",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-pro",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview-05-06",1048576,65535,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-3-flash-preview",1048576,65535,"text,image",1,null,0.5,3,0.049999999999999996,0.08333333333333334],["google/gemini-3-pro-image",131072,32768,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3-pro-preview",1048000,64000,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-flash-lite",1048576,65536,"text,image",1,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-flash-lite-preview",1048576,65536,"text,image",0,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-pro-preview",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-pro-preview-customtools",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.5-flash",1048576,65536,"text,image",1,null,1.5,9,0.15,0.08333333333333334],["google/gemini-3.5-flash-lite",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-3.6-flash",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["google/gemma-3-12b-it",131072,16384,"text,image",0,null,0.049999999999999996,0.15,0,0],["google/gemma-3-27b-it",262144,131072,"text,image",1,null,0.08,0.44999999999999996,0.04,0],["google/gemma-3-27b-it:free",131072,8192,"text,image",0,null,0,0,0,0],["google/gemma-4-26b-a4b-it",262144,262144,"text,image",1,null,0.12,0.35,0.049999999999999996,0],["google/gemma-4-26b-a4b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["google/gemma-4-31b-it",262144,262144,"text,image",1,null,0.14,0.39999999999999997,0.09,0],["google/gemma-4-31b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["ibm-granite/granite-4.1-8b",131072,131072,"text",0,null,0.049999999999999996,0.09999999999999999,0.049999999999999996,0],["inception/mercury",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-2",128000,50000,"text",1,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-coder",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inclusionai/ling-2.6-1t",262144,32768,"text",0,null,0.075,0.625,0.015,0],["inclusionai/ling-2.6-1t:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-2.6-flash",262144,32768,"text",0,null,0.01,0.03,0.002,0],["inclusionai/ling-2.6-flash:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-3.0-flash:free",262144,32768,"text",1,null,0,0,0,0],["inclusionai/ring-2.6-1t",262144,65536,"text",1,null,0.075,0.625,0.015,0],["inclusionai/ring-2.6-1t:free",262144,65536,"text",1,null,0,0,0,0],["kwaipilot/kat-coder-air-v2.5",256000,80000,"text",0,null,0.15,0.6,0.03,0],["kwaipilot/kat-coder-pro",256000,128000,"text",0,null,0.207,0.828,0.0414,0],["kwaipilot/kat-coder-pro-v2",262144,80000,"text",0,null,0.3,1.2,0.06,0],["kwaipilot/kat-coder-pro-v2.5",256000,80000,"text",0,null,0.74,2.96,0.15,0],["liquid/lfm-2.5-1.2b-thinking:free",32768,8888,"text",1,null,0,0,0,0],["meituan/longcat-2.0",1048756,262144,"text",1,null,0.3,1.2,0.006,0],["meituan/longcat-flash-chat",131072,131072,"text",0,null,0.19999999999999998,0.7999999999999999,0.19999999999999998,0],["meta-llama/llama-3-8b-instruct",8192,16384,"text",0,null,0.03,0.04,0,0],["meta-llama/llama-3.1-405b-instruct",131000,8888,"text",0,null,4,4,0,0],["meta-llama/llama-3.1-70b-instruct",131072,16384,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["meta-llama/llama-3.1-8b-instruct",131072,131072,"text",0,null,0.049999999999999996,0.08,0.024999999999999998,0],["meta-llama/llama-3.3-70b-instruct",131072,128000,"text",0,null,0.13,0.39999999999999997,0,0],["meta-llama/llama-3.3-70b-instruct:free",131072,8888,"text",0,null,0,0,0,0],["meta-llama/llama-4-maverick",1048576,16384,"text,image",0,null,0.19999999999999998,0.7999999999999999,0,0],["meta-llama/llama-4-scout",1310720,16384,"text,image",0,null,0.09999999999999999,0.3,0,0],["meta/muse-spark-1.1",1048576,8888,"text,image",1,null,1.25,4.25,0.15,0],["minimax/minimax-m1",1000000,40000,"text",1,null,0.55,2.2,0,0],["minimax/minimax-m2",204800,131072,"text",1,null,0.255,1.02,0.03,0],["minimax/minimax-m2.1",204800,131072,"text",1,null,0.3,1.2,0.03,0],["minimax/minimax-m2.5",204800,196608,"text",1,null,0.15,0.8999999999999999,0.049999999999999996,0],["minimax/minimax-m2.5:free",262144,8192,"text",1,null,0,0,0,0],["minimax/minimax-m2.7",204800,131072,"text",1,null,0.25,1,0.049999999999999996,0],["minimax/minimax-m3",1048576,512000,"text,image",1,null,0.3,1.2,0.06,0],["mistralai/codestral-2508",256000,8888,"text",0,null,0.3,0.8999999999999999,0.03,0],["mistralai/devstral-2512",262144,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-medium",131072,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-small",131072,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/ministral-14b-2512",262144,8888,"text,image",0,null,0.19999999999999998,0.19999999999999998,0.02,0],["mistralai/ministral-3b-2512",131072,8888,"text,image",0,null,0.09999999999999999,0.09999999999999999,0.01,0],["mistralai/ministral-8b-2512",262144,8888,"text,image",0,null,0.15,0.15,0.015,0],["mistralai/mistral-large",128000,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2407",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2411",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2512",262144,8888,"text,image",0,null,0.5,1.5,0.049999999999999996,0],["mistralai/mistral-medium-3",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-medium-3-5",262144,8888,"text,image",1,null,1.5,7.5,0,0],["mistralai/mistral-medium-3.1",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-nemo",131072,16384,"text",0,null,0.019000000000000003,0.03,0,0],["mistralai/mistral-saba",32768,8888,"text",0,null,0.19999999999999998,0.6,0.02,0],["mistralai/mistral-small-24b-instruct-2501",32768,16384,"text",0,null,0.049999999999999996,0.08,0,0],["mistralai/mistral-small-2603",262144,8888,"text,image",1,null,0.15,0.6,0.015,0],["mistralai/mistral-small-3.1-24b-instruct",131072,131072,"text,image",0,null,0.03,0.11,0.015,0],["mistralai/mistral-small-3.1-24b-instruct:free",128000,8888,"text,image",0,null,0,0,0,0],["mistralai/mistral-small-3.2-24b-instruct",256000,8888,"text,image",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mistral-small-creative",32768,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mixtral-8x22b-instruct",65536,13108,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mixtral-8x7b-instruct",32768,16384,"text",0,null,0.54,0.54,0,0],["mistralai/pixtral-large-2411",131072,8888,"text,image",0,null,2,6,0.19999999999999998,0],["mistralai/voxtral-small-24b-2507",32000,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["moonshotai/kimi-k2",131072,100352,"text",0,null,0.5700000000000001,2.3,0,0],["moonshotai/kimi-k2-0905",262144,100352,"text",0,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2-0905:exacto",262144,8888,"text",0,null,0.6,2.5,0,0],["moonshotai/kimi-k2-thinking",262144,100352,"text",1,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2.5",262144,262144,"text,image",1,null,0.5700000000000001,2.8499999999999996,0.095,0],["moonshotai/kimi-k2.6",262144,262144,"text,image",1,null,0.646,2.7199999999999998,0.1088,0],["moonshotai/kimi-k2.6:free",262144,8888,"text,image",1,null,0,0,0,0],["moonshotai/kimi-k2.7-code",262144,262144,"text,image",1,null,0.78,3.5,0.15,0],["moonshotai/kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["nex-agi/deepseek-v3.1-nex-n1",131072,163840,"text",0,null,0.135,0.5,0,0],["nex-agi/nex-n2-mini",262144,262144,"text,image",1,null,0.024999999999999998,0.09999999999999999,0.0025,0],["nex-agi/nex-n2-pro",262144,262144,"text,image",1,null,0.25,1,0.024999999999999998,0],["nex-agi/nex-n2-pro:free",262144,262144,"text,image",1,null,0,0,0,0],["nousresearch/deephermes-3-mistral-24b-preview",32768,32768,"text",1,null,0.02,0.09999999999999999,0.01,0],["nousresearch/hermes-4-70b",131072,131072,"text",1,null,0.11,0.38,0.055,0],["nvidia/llama-3.1-nemotron-70b-instruct",131072,16384,"text",0,null,1.2,1.2,0,0],["nvidia/llama-3.3-nemotron-super-49b-v1.5",131072,16384,"text",1,null,0.39999999999999997,0.39999999999999997,0,0],["nvidia/nemotron-3-nano-30b-a3b",262144,228000,"text",1,null,0.049999999999999996,0.19999999999999998,0,0],["nvidia/nemotron-3-nano-30b-a3b:free",256000,8888,"text",1,null,0,0,0,0],["nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",256000,65536,"text,image",1,null,0,0,0,0],["nvidia/nemotron-3-super-120b-a12b",1000000,16384,"text",1,null,0.08499999999999999,0.39999999999999997,0.09999999999999999,0],["nvidia/nemotron-3-super-120b-a12b:free",262144,262144,"text",1,null,0,0,0,0],["nvidia/nemotron-3-ultra-550b-a55b",512288,65536,"text",1,null,0.6,3.5999999999999996,0.19999999999999998,0],["nvidia/nemotron-3-ultra-550b-a55b:free",1000000,65536,"text",1,null,0,0,0,0],["nvidia/nemotron-nano-12b-v2-vl:free",128000,128000,"text,image",1,null,0,0,0,0],["nvidia/nemotron-nano-9b-v2",131072,16384,"text",1,null,0.04,0.16,0,0],["nvidia/nemotron-nano-9b-v2:free",128000,8888,"text",1,null,0,0,0,0],["openai/gpt-3.5-turbo",16385,4096,"text",0,null,0.5,1.5,0,0],["openai/gpt-3.5-turbo-0613",4095,4096,"text",0,null,1,2,0,0],["openai/gpt-3.5-turbo-16k",16385,4096,"text",0,null,3,4,0,0],["openai/gpt-4",8191,8192,"text",0,null,30,60,0,0],["openai/gpt-4-0314",8191,4096,"text",0,null,30,60,0,0],["openai/gpt-4-1106-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4-turbo",128000,4096,"text,image",0,null,10,30,0,0],["openai/gpt-4-turbo-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4.1",1047576,32768,"text,image",0,null,2,8,0.5,0],["openai/gpt-4.1-mini",1047576,32768,"text,image",0,null,0.39999999999999997,1.5999999999999999,0.09999999999999999,0],["openai/gpt-4.1-nano",1047576,32768,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0],["openai/gpt-4o",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-05-13",128000,4096,"text,image",0,null,5,15,0,0],["openai/gpt-4o-2024-08-06",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-11-20",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-audio-preview",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-4o-mini",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o-mini-2024-07-18",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o:extended",128000,64000,"text,image",0,null,6,18,0,0],["openai/gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-image",400000,128000,"text,image",1,null,10,10,1.25,0],["openai/gpt-5-image-mini",400000,128000,"text,image",1,null,2.5,2,0.25,0],["openai/gpt-5-mini",400000,128000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5-nano",400000,128000,"text,image",1,null,0.049999999999999996,0.39999999999999997,0.005,0],["openai/gpt-5-pro",400000,128000,"text,image",1,null,15,120,0,0],["openai/gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-chat",128000,16384,"text,image",0,null,1.25,10,0.125,0],["openai/gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-mini",272000,100000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5.2",400000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-chat",128000,16384,"text,image",0,null,1.75,14,0.175,0],["openai/gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-pro",400000,128000,"text,image",1,null,21,168,0,0],["openai/gpt-5.3-chat",128000,16384,"text",0,null,1.75,14,0.175,0],["openai/gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.4",1050000,128000,"text,image",1,null,2.5,15,0.25,0],["openai/gpt-5.4-mini",400000,128000,"text",0,null,0.75,4.5,0.075,0],["openai/gpt-5.4-nano",400000,128000,"text",0,null,0.19999999999999998,1.25,0.02,0],["openai/gpt-5.4-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.5",1050000,128000,"text,image",1,null,5,30,0.5,0],["openai/gpt-5.5-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.6-luna",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-luna-pro",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-sol-pro",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-terra",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-5.6-terra-pro",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-6-luna",373000,128000,"text,image",1,null,0.1,0.5,0.01,0.125],["openai/gpt-6-sol",373000,128000,"text,image",1,null,2,10,0.2,2.5],["openai/gpt-audio",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-audio-mini",128000,16384,"text",0,null,0.6,2.4,0,0],["openai/gpt-chat-latest",400000,128000,"text,image",0,null,5,30,0.5,0],["openai/gpt-oss-120b",131072,131072,"text",1,null,0.037,0.16999999999999998,0,0],["openai/gpt-oss-120b:exacto",131072,8888,"text",1,null,0.039,0.19,0,0],["openai/gpt-oss-120b:free",131072,131072,"text",1,null,0,0,0,0],["openai/gpt-oss-20b",131072,131072,"text",1,null,0.03,0.13,0.03,0],["openai/gpt-oss-20b:free",131072,32768,"text",1,null,0,0,0,0],["openai/gpt-oss-safeguard-20b",131072,65536,"text",1,null,0.075,0.3,0.0375,0],["openai/o1",200000,100000,"text,image",1,null,15,60,7.5,0],["openai/o3",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o3-deep-research",200000,100000,"text,image",1,null,10,40,2.5,0],["openai/o3-mini",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-mini-high",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-pro",200000,100000,"text,image",1,null,20,80,0,0],["openai/o4-mini",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openai/o4-mini-deep-research",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o4-mini-high",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openrouter/aurora-alpha",128000,50000,"text",1,null,0,0,0,0],["openrouter/auto",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/auto-beta",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/elephant-alpha",262144,32768,"text",0,null,0,0,0,0],["openrouter/free",200000,8888,"text,image",1,null,0,0,0,0],["openrouter/healer-alpha",262144,32000,"text,image",1,null,0,0,0,0],["openrouter/hunter-alpha",1048576,32000,"text",1,null,0,0,0,0],["openrouter/owl-alpha",1048756,262144,"text",0,null,0,0,0,0],["poolside/laguna-m.1",262144,32768,"text",1,null,0.19999999999999998,0.39999999999999997,0.09999999999999999,0],["poolside/laguna-m.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-s-2.1",1048576,131072,"text",1,null,0.09999999999999999,0.19999999999999998,0.01,0],["poolside/laguna-s-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs-2.1",262144,32768,"text",1,null,0.06,0.12,0.03,0],["poolside/laguna-xs-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs.2",262144,32768,"text",1,null,0.09999999999999999,0.19999999999999998,0.049999999999999996,0],["poolside/laguna-xs.2:free",262144,32768,"text",1,null,0,0,0,0],["prime-intellect/intellect-3",131072,131072,"text",1,null,0.19999999999999998,1.1,0,0],["qwen/qwen-2.5-72b-instruct",32768,16384,"text",0,null,0.36,0.39999999999999997,0,0],["qwen/qwen-2.5-7b-instruct",32768,32768,"text",0,null,0.04,0.09999999999999999,0,0],["qwen/qwen-max",32768,8192,"text",0,null,1.04,4.16,0.20800000000000002,0],["qwen/qwen-plus",1000000,32768,"text",0,null,0.26,0.78,0.052000000000000005,0.325],["qwen/qwen-plus-2025-07-28",1000000,32768,"text",0,null,0.26,0.78,0,0.325],["qwen/qwen-plus-2025-07-28:thinking",1000000,32768,"text",1,null,0.26,0.78,0,0.325],["qwen/qwen-turbo",131072,8192,"text",0,null,0.0325,0.13,0.006500000000000001,0],["qwen/qwen-vl-max",131072,32768,"text,image",0,null,0.52,2.08,0,0],["qwen/qwen3-14b",131072,8192,"text",1,null,0.22749999999999998,0.9099999999999999,0,0],["qwen/qwen3-235b-a22b",131072,8192,"text",1,null,0.45499999999999996,1.8199999999999998,0,0],["qwen/qwen3-235b-a22b-2507",262144,16384,"text",1,null,0.09,0.55,0,0],["qwen/qwen3-235b-a22b-thinking-2507",262144,32768,"text",1,null,0.3,3,0.09999999999999999,0],["qwen/qwen3-30b-a3b",131072,8192,"text",1,null,0.13,0.52,0,0],["qwen/qwen3-30b-a3b-instruct-2507",262144,32000,"text",0,null,0.04815,0.19305,0,0],["qwen/qwen3-30b-a3b-thinking-2507",81920,32768,"text",1,null,0.13,1.56,0.08,0],["qwen/qwen3-32b",131072,16384,"text",1,null,0.08,0.28,0.04,0],["qwen/qwen3-4b",131072,8192,"text",1,null,0.0715,0.273,0,0],["qwen/qwen3-4b:free",40960,8888,"text",1,null,0,0,0,0],["qwen/qwen3-8b",131072,8192,"text",1,null,0.117,0.45499999999999996,0.049999999999999996,0],["qwen/qwen3-coder",262144,65536,"text",0,null,0.3,1,0.09999999999999999,0],["qwen/qwen3-coder-30b-a3b-instruct",262144,32768,"text",0,null,0.07,0.27,0,0],["qwen/qwen3-coder-flash",1000000,65536,"text",0,null,0.195,0.975,0.039,0.24375],["qwen/qwen3-coder-next",262144,262144,"text",0,null,0.11,0.7999999999999999,0.07,0],["qwen/qwen3-coder-plus",1000000,65536,"text",0,null,0.65,3.25,0.13,0.8125],["qwen/qwen3-coder:exacto",262144,65536,"text",0,null,0.22,1.7999999999999998,0.022,0],["qwen/qwen3-coder:free",1048576,262000,"text",0,null,0,0,0,0],["qwen/qwen3-max",262144,32768,"text",1,null,0.78,3.9,0.156,0.975],["qwen/qwen3-max-thinking",262144,32768,"text",1,null,0.78,3.9,0,0],["qwen/qwen3-next-80b-a3b-instruct",262144,262144,"text",0,null,0.09999999999999999,1.1,0.07,0],["qwen/qwen3-next-80b-a3b-instruct:free",262144,8888,"text",0,null,0,0,0,0],["qwen/qwen3-next-80b-a3b-thinking",262144,32768,"text",1,null,0.0975,0.78,0,0],["qwen/qwen3-vl-235b-a22b-instruct",262144,32768,"text,image",0,null,0.21,1.9,0.09999999999999999,0],["qwen/qwen3-vl-235b-a22b-thinking",131072,32768,"text,image",1,null,0.26,2.6,0,0],["qwen/qwen3-vl-30b-a3b-instruct",262144,16384,"text,image",0,null,0.15,0.6,0,0],["qwen/qwen3-vl-30b-a3b-thinking",262144,32768,"text,image",1,null,0.13,1.56,0,0],["qwen/qwen3-vl-32b-instruct",131072,32768,"text,image",0,null,0.10400000000000001,0.41600000000000004,0,0],["qwen/qwen3-vl-8b-instruct",262144,32768,"text,image",0,null,0.117,0.45499999999999996,0,0],["qwen/qwen3-vl-8b-thinking",131072,32768,"text,image",1,null,0.117,1.365,0,0],["qwen/qwen3.5-122b-a10b",262144,65536,"text,image",1,null,0.26,2.08,0,0],["qwen/qwen3.5-27b",262144,65536,"text,image",1,null,0.195,1.56,0,0],["qwen/qwen3.5-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.5-397b-a17b",262144,65536,"text,image",1,null,0.39,2.34,0.111,0],["qwen/qwen3.5-9b",262144,262144,"text,image",1,null,0.09999999999999999,0.15,0,0],["qwen/qwen3.5-flash-02-23",1000000,65536,"text,image",1,null,0.065,0.26,0,0.08125],["qwen/qwen3.5-plus-02-15",1000000,65536,"text,image",1,null,0.26,1.56,0,0.325],["qwen/qwen3.5-plus-20260420",1000000,65536,"text,image",1,null,0.3,1.7999999999999998,0,0.375],["qwen/qwen3.6-27b",262144,131072,"text,image",1,null,0.28900000000000003,2.4,0.15,0],["qwen/qwen3.6-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.6-flash",1000000,65536,"text,image",1,null,0.1875,1.125,0,0.234375],["qwen/qwen3.6-max-preview",262144,65536,"text",1,null,1.04,6.24,0,1.3],["qwen/qwen3.6-plus",1000000,65536,"text",1,null,0.325,1.95,0,0.40625],["qwen/qwen3.6-plus-preview:free",1000000,32000,"text",1,null,0,0,0,0],["qwen/qwen3.6-plus:free",1000000,65536,"text,image",1,null,0,0,0,0],["qwen/qwen3.7-max",1000000,65536,"text",1,null,1.475,4.425,0.295,1.84375],["qwen/qwen3.7-plus",1000000,65536,"text,image",1,null,0.32,1.28,0.064,0.39999999999999997],["qwen/qwq-32b",131072,131072,"text",1,null,0.15,0.58,0,0],["reka/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["rekaai/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["relace/relace-search",256000,128000,"text",0,null,1,3,0,0],["sakana/fugu-ultra",1000000,128000,"text,image",1,null,5,30,0.5,0],["sao10k/l3-euryale-70b",8192,8192,"text",0,null,1.48,1.48,0,0],["sao10k/l3.1-euryale-70b",131072,16384,"text",0,null,0.85,0.85,0,0],["stepfun/step-3.5-flash",262144,65536,"text",0,null,0.09999999999999999,0.3,0.02,0],["stepfun/step-3.5-flash:free",256000,256000,"text",1,null,0,0,0,0],["stepfun/step-3.7-flash",262144,256000,"text,image",1,null,0.19999999999999998,1.15,0.04,0],["tencent/hy3",262144,128000,"text",1,null,0.13199999999999998,0.5279999999999999,0.032999999999999995,0],["tencent/hy3-preview",262144,64000,"text",1,null,0.063,0.21,0.020999999999999998,0],["tencent/hy3-preview:free",262144,262144,"text",1,null,0,0,0,0],["tencent/hy3:free",262144,262144,"text",1,null,0,0,0,0],["thedrummer/rocinante-12b",32768,32768,"text",0,null,0.16999999999999998,0.43,0,0],["thedrummer/unslopnemo-12b",32768,32768,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["thinkingmachines/inkling",1048576,8888,"text,image",1,null,1,4.05,0.16999999999999998,0],["tngtech/deepseek-r1t2-chimera",163840,163840,"text",1,null,0.3,1.1,0.15,0],["tngtech/tng-r1t-chimera",163840,65536,"text",1,null,0.25,0.85,0.125,0],["upstage/solar-pro-3",128000,8888,"text",1,null,0.15,0.6,0.015,0],["upstage/solar-pro-3:free",128000,8888,"text",1,null,0,0,0,0],["x-ai/grok-3",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-beta",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-mini",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-3-mini-beta",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-4",256000,64000,"text,image",1,null,3,15,0.75,0],["x-ai/grok-4-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.1-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.20",2000000,8888,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.20-beta",2000000,8888,"text,image",1,null,2,6,0.19999999999999998,0],["x-ai/grok-4.3",1000000,1000000,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-4.7",500000,450000,"text,image",1,null,1.6,4.8,0.4,0],["x-ai/grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.19999999999999998,0],["x-ai/grok-code-fast-1",256000,10000,"text",1,null,0.19999999999999998,1.5,0.02,0],["xiaomi/mimo-v2-flash",262144,65536,"text",1,null,0.09999999999999999,0.3,0.01,0],["xiaomi/mimo-v2-omni",262144,65536,"text,image",1,null,0.39999999999999997,2,0.08,0],["xiaomi/mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.19999999999999998,0],["xiaomi/mimo-v2.5",1050000,131072,"text,image",1,null,0.14,0.28,0.0028,0],["xiaomi/mimo-v2.5-pro",1050000,131072,"text",1,null,0.435,0.87,0.0036,0],["z-ai/glm-4-32b",128000,8888,"text",0,null,0.09999999999999999,0.09999999999999999,0,0],["z-ai/glm-4.5",131072,98304,"text",1,null,0.6,2.2,0.11,0],["z-ai/glm-4.5-air",131072,98304,"text",1,null,0.13,0.85,0.024999999999999998,0],["z-ai/glm-4.5-air:free",131072,96000,"text",1,null,0,0,0,0],["z-ai/glm-4.5v",65536,16384,"text,image",1,null,0.6,1.7999999999999998,0.11,0],["z-ai/glm-4.6",204800,131072,"text",1,null,0.5,2,0.09999999999999999,0],["z-ai/glm-4.6:exacto",204800,131072,"text",1,null,0.44,1.76,0.11,0],["z-ai/glm-4.6v",131072,32768,"text,image",1,null,0.3,0.8999999999999999,0.055,0],["z-ai/glm-4.7",204800,131072,"text",1,null,0.39999999999999997,1.75,0.08,0],["z-ai/glm-4.7-flash",202752,16384,"text",1,null,0.06,0.39999999999999997,0.01,0],["z-ai/glm-5",204800,131072,"text",1,null,0.95,2.5500000000000003,0.19999999999999998,0],["z-ai/glm-5-turbo",202752,131072,"text",1,null,1.2,4,0.24,0],["z-ai/glm-5.1",204800,128000,"text",1,null,0.966,3.036,0.1794,0],["z-ai/glm-5.2",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5.3",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5v-turbo",202752,131072,"text,image",1,null,1.2,4,0.24,0]], + "xai": [["grok-2",131072,8192,"text",0,null,2,10,2,0],["grok-2-1212",131072,8192,"text",0,null,2,10,2,0],["grok-2-latest",131072,8192,"text",0,null,2,10,2,0],["grok-2-vision",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-1212",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-latest",8192,4096,"text,image",0,null,2,10,2,0],["grok-3",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-fast",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-fast-latest",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-latest",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-mini",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-3-mini-fast",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-fast-latest",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-latest",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-4",256000,64000,"text",1,null,3,15,0.75,0],["grok-4-1-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-1-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4.20-0309-non-reasoning",1000000,30000,"text,image",0,null,1.25,2.5,0.2,0],["grok-4.20-0309-reasoning",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-beta-latest-non-reasoning",2000000,30000,"text,image",0,null,2,6,0.2,0],["grok-4.20-beta-latest-reasoning",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.20-multi-agent-0309",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-multi-agent-beta-latest",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.3",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-4.7",500000,500000,"text,image",1,null,2,6,0.5,0],["grok-beta",131072,4096,"text",0,null,5,15,5,0],["grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.2,0],["grok-code-fast-1",256000,10000,"text",1,null,0.2,1.5,0.02,0],["grok-composer-2.5-fast",200000,64000,"text",1,null,0,0,0,0],["grok-vision-beta",8192,4096,"text,image",0,null,5,15,5,0]], "xiaomi": [["mimo-v2-flash",262144,65536,"text",1,null,0.14,0.28,0.0028,0],["mimo-v2-omni",262144,131072,"text,image",1,null,0.14,0.28,0.0028,0],["mimo-v2-pro",1048576,131072,"text",1,null,0.435,0.87,0.0036,0],["mimo-v2.5",1048576,131072,"text,image",1,null,0.14,0.28,0.0028,0],["mimo-v2.5-pro",1048576,131072,"text",1,null,0.435,0.87,0.0036,0],["mimo-v2.5-pro-ultraspeed",1048576,131072,"text",1,null,1.305,2.61,0.0108,0]], "zai": [["glm-4.5",131072,98304,"text",1,null,0,0,0,0],["glm-4.5-air",131072,98304,"text",1,null,0,0,0,0],["glm-4.5-flash",131072,98304,"text",1,null,0,0,0,0],["glm-4.5v",64000,16384,"text,image",1,null,0,0,0,0],["glm-4.6",204800,131072,"text",1,null,0,0,0,0],["glm-4.6v",128000,32768,"text,image",1,null,0,0,0,0],["glm-4.7",204800,131072,"text",1,null,0,0,0,0],["glm-4.7-flash",200000,131072,"text",1,null,0,0,0,0],["glm-4.7-flashx",200000,131072,"text",1,null,0.07,0.4,0.01,0],["glm-5",204800,131072,"text",1,null,0,0,0,0],["glm-5-turbo",200000,131072,"text",1,null,0,0,0,0],["glm-5.1",200000,131072,"text",1,null,0,0,0,0],["glm-5.2",1000000,131072,"text",1,null,0,0,0,0],["glm-5.3",1000000,131072,"text",1,null,0,0,0,0],["glm-5v-turbo",200000,131072,"text,image",1,null,0,0,0,0]], }; diff --git a/src/providers/registry/entries-core.ts b/src/providers/registry/entries-core.ts index 1c4161fe80a..a8efda3bce5 100644 --- a/src/providers/registry/entries-core.ts +++ b/src/providers/registry/entries-core.ts @@ -167,7 +167,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // (it is the current catalog, so its default ordering wins), then the ids // only the old devin entry carried. Degraded-mode seed only either way — // `liveModels` discovers the account's real roster. - models: ["swe-2", "swe-1-7", "gpt-5-6-sol", "gpt-6-astra", "gpt-6-sol", "gpt-6-luna", "claude-opus-5-5", "claude-opus-5", "claude-fable-5-1", "claude-sonnet-5", "glm-5-3", "kimi-k3", "gemini-3-8-flash", "grok-4-6", "swe-1-7-lightning", "gpt-5-6-luna", "gpt-5-6-terra", "claude-opus-4-8", "glm-5-2", "kimi-k2-7", "grok-4-5"], + models: ["swe-2", "swe-1-7", "gpt-5-6-sol", "gpt-6-astra", "gpt-6-sol", "gpt-6-luna", "claude-opus-5-5", "claude-opus-5", "claude-fable-5-1", "claude-sonnet-5", "glm-5-3", "kimi-k3", "gemini-3-8-flash", "grok-4-6", "grok-4-7", "swe-1-7-lightning", "gpt-5-6-luna", "gpt-5-6-terra", "claude-opus-4-8", "glm-5-2", "kimi-k2-7", "grok-4-5"], liveModels: true, defaultModel: "swe-2", modelContextWindows: DEVIN_MODEL_CONTEXT_WINDOWS, @@ -198,7 +198,10 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // the OAuth lane. grok-4.20-multi-agent-0309 is deliberately absent: the gateway accepts // the field but answers service_tier "default" — a live downgrade, not a fast tier. // Unlisted and future-discovered ids stay unclassified. + // grok-4.7 applied and confirmed priority on OAuth Responses in the 2026-09-23 + // live probe: devlog/_plan/260923_grok47_parity/010_probe-evidence.md. modelSupportsServiceTier: { + "grok-4.7": true, "grok-4.6": true, "grok-4.5": true, "grok-4.3": true, @@ -253,14 +256,19 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // than the seeded ones do. supportsVerbosity: false, defaultModel: "grok-4.5", - // Grok 4.6/4.5 subscription Responses callers use the native wire with the existing + // Grok 4.7/4.6/4.5 subscription Responses callers use the native wire with the existing // namespace/web-search/replay normalization. Chat remains an explicit modelAdapters // opt-in. Multi-agent has no Chat wire and uses Responses under both auth modes. - // grok-4.6/4.5 are classified OAuth fast-tier models (modelSupportsServiceTier above), + // grok-4.7/4.6/4.5 are classified OAuth fast-tier models (modelSupportsServiceTier above), // so a caller-sent service_tier:"priority" forwards on this lane — the Codex fast-toggle // path. Multi-agent keeps its pin: probed 2026-09-13, the gateway downgrades its tier to // "default", so forwarding a caller tier would advertise a tier it does not get. modelWireDefaults: { + "grok-4.7": { + wire: "openai-responses", + inbound: ["responses"], + authModes: ["oauth"], + }, "grok-4.6": { wire: "openai-responses", inbound: ["responses"], @@ -303,6 +311,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // the app blocks attachments client-side. grok-build-0.1 / grok-composer-2.5-fast stay out // (they are already listed in noVisionModels below). modelInputModalities: { + "grok-4.7": ["text", "image"], "grok-4.6": ["text", "image"], "grok-4.5": ["text", "image"], "grok-4.3": ["text", "image"], @@ -315,18 +324,24 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // reasoning_content as the top cause of prompt-cache misses on multi-turn conversations // (docs.x.ai prompt-caching/multi-turn, verified 2026-07-13 — devlog/_plan/260713_grok_caching). // Models that never emit reasoning simply have no thinking parts to replay (no-op). - preserveReasoningContentModels: ["grok-4.6", "grok-4.5", "grok-4.3", "grok-4.20-0309-reasoning"], + preserveReasoningContentModels: ["grok-4.7", "grok-4.6", "grok-4.5", "grok-4.3", "grok-4.20-0309-reasoning"], // grok-4.5 reasoning is always-on with low/medium/high (no off tier, no xhigh). // grok-4.6 adds xhigh per docs.x.ai/developers/model-capabilities/text/reasoning; // multi-agent accepts the same four wire values to select 4 or 16 collaborators. xAI // documents high as the 4.6 default but no multi-agent default, so do not invent one. modelReasoningEfforts: { + // 2026-09-23 live probe accepted low..xhigh and rejected max on both wires; + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4.7": ["low", "medium", "high", "xhigh"], "grok-4.6": ["low", "medium", "high", "xhigh"], "grok-4.5": ["low", "medium", "high"], "grok-4.20-multi-agent-0309": ["low", "medium", "high", "xhigh"], }, - modelDefaultReasoningEfforts: { "grok-4.6": "high" }, + modelDefaultReasoningEfforts: { "grok-4.7": "high", "grok-4.6": "high" }, modelContextWindows: { + // 500k confirmed by context_length_exceeded: + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "grok-4.7": 500_000, "grok-4.6": 500_000, "grok-4.5": 500_000, "grok-4.3": 1_000_000, @@ -680,7 +695,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ // Use explicit replay history and the existing stateless Responses policy. statelessResponses: true, /* [Decision Log] - - 목적과 의도: Route the exact models OpenCode Go documents on the Responses endpoint — GPT 5.6 Luna, Grok 4.6, and Muse Spark Contributor (#2617). + - 목적과 의도: Route the exact models OpenCode Go documents on the Responses endpoint — GPT 5.6 Luna, Grok 4.6/4.7, and Muse Spark Contributor (#2617; opencode.ai/docs/go). - 기존 구현 및 제약 조건: The provider is mixed-wire but its provider-wide `openai-chat` adapter sent Luna to `/chat/completions`; explicit user `modelAdapters` entries must remain authoritative. - 검토한 주요 대안: Change the whole provider to Responses; infer the wire from model-family names; add one registry-only exact-model default. - 선택한 방식: Declare only the named models as `openai-responses` through the existing registry default mechanism; the map stays an exact-model allowlist rather than a family or provider-wide rule. @@ -690,6 +705,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ modelWireDefaults: { "gpt-5.6-luna": "openai-responses", "grok-4.6": "openai-responses", + "grok-4.7": "openai-responses", "muse-spark-1.3-contributor": "openai-responses", "muse-spark-1.2-contributor": "openai-responses", }, @@ -750,6 +766,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ modelReasoningEfforts: { "gpt-5.6-luna": OPENAI_API_GPT56_REASONING_EFFORTS, "grok-4.6": ["low", "medium", "high", "xhigh"], + "grok-4.7": ["low", "medium", "high", "xhigh"], "glm-5.3": ZAI_GLM_53_REASONING_EFFORTS, "glm-5.3-flash": ZAI_GLM_53_REASONING_EFFORTS, "glm-5.2": ZAI_GLM_52_REASONING_EFFORTS, @@ -761,7 +778,7 @@ export const PROVIDER_REGISTRY_CORE: readonly ProviderRegistryEntry[] = [ ...Object.fromEntries(OPENCODE_GO_THINKING_BUDGET_MODELS.map(id => [id, THINKING_BUDGET_EFFORTS])), ...Object.fromEntries(DEEPSEEK_GATEWAY_THINKING_MODELS.map(id => [id, deepseekThinkingEffortsFor(id)])), }, - modelDefaultReasoningEfforts: { "grok-4.6": "high", "kimi-k3": "max" }, + modelDefaultReasoningEfforts: { "grok-4.6": "high", "grok-4.7": "high", "kimi-k3": "max" }, // glm-5.2 uses identity labels now that `max` is a native Codex level (no alias map); // the thinking-toggle map is a REAL wire alias (effort -> enabled/disabled) and stays. modelReasoningEffortMap: { diff --git a/src/providers/registry/model-seeds.ts b/src/providers/registry/model-seeds.ts index 856b2b9ca05..10407d88890 100644 --- a/src/providers/registry/model-seeds.ts +++ b/src/providers/registry/model-seeds.ts @@ -231,6 +231,7 @@ export const OPENAI_DAYBREAK_REASONING_EFFORTS: Record = Objec ); export const OPENROUTER_GPT56_MODELS = OPENAI_GPT56_MODELS.map(id => `openai/${id}`); export const XAI_MODELS = [ + "grok-4.7", "grok-4.6", "grok-4.5", "grok-4.3", @@ -329,7 +330,7 @@ export const DEEPSEEK_VISION_PREVIEW_MODEL = "deepseek-v4-flash-vision-exp"; * CommandCode routes verified to accept image input end-to-end (#2406). * * Verified-negative and therefore deliberately ABSENT: deepseek/deepseek-v4-flash, - * zai-org/GLM-5.2, zai-org/GLM-5.3, xai/grok-4.6. Those + * zai-org/GLM-5.2, zai-org/GLM-5.3. Those * routes accept the request and drop the image, which is worse than declining it — the * model answers about an image it never saw. Do not add an id here on family resemblance; * capability intersection trusts this map. @@ -351,10 +352,16 @@ export const COMMAND_CODE_IMAGE_MODELS = [ "meta/muse-spark-1.3-contributor", "meta/muse-spark-1.2", "meta/muse-spark-1.2-contributor", + // Live 2026-09-23 3x3 random-color grid (180x180) via ocx 2.62.0: + // 4.7 read 9/9 in user messages and tool results; 4.6 read 9/9 and 8/9. + // Neither route requested a vision sidecar. Evidence: + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + "xai/grok-4.6", + "xai/grok-4.7", // Native Z.AI VLM (docs.z.ai/guides/vlm/glm-5.3-flash). This exact id is already // classified as natively vision-capable in NVIDIA_NIM_VISION_MODELS in this file; // it is not one of the verified-negative ids the header names (those are - // deepseek/deepseek-v4-flash, zai-org/GLM-5.2, zai-org/GLM-5.3, xai/grok-4.6 — + // deepseek/deepseek-v4-flash, zai-org/GLM-5.2, zai-org/GLM-5.3 — // different ids). Adding it on the shared GLM-5.3 prefix would be the family- // resemblance mistake the header forbids; the VLM docs are the evidence (#4505). "z-ai/glm-5.3-flash", diff --git a/src/usage/expected-prices.ts b/src/usage/expected-prices.ts index 18b686cf227..782f0d0175a 100644 --- a/src/usage/expected-prices.ts +++ b/src/usage/expected-prices.ts @@ -440,6 +440,14 @@ export const VERIFIED_PRICE_OVERRIDES: readonly ExpectedPriceOverlay[] = [ verifiedAt: "2026-08-18", status: "verified", }, + { + provider: "xai", + modelId: "grok-4.7", + cost4: { input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0 }, + source: "https://docs.x.ai/developers/models/grok-4.7", + verifiedAt: "2026-09-23", + status: "verified", + }, ]; export function findVerifiedPriceOverride( @@ -529,13 +537,13 @@ export const PRIORITY_PRICING_RULES: readonly PriorityPricingRule[] = [ source: "https://developers.openai.com/api/docs/pricing (derived from the virtual selection's base wire model)", verifiedAt: "2026-09-05", })), - ...["grok-4.5", "grok-4.6"].map((modelId): PriorityPricingRule => ({ + ...["grok-4.5", "grok-4.6", "grok-4.7"].map((modelId): PriorityPricingRule => ({ provider: "xai", modelId, multiplier: 2, requiresResponseConfirmation: true, source: XAI_PRIORITY_PRICING, - verifiedAt: "2026-08-18", + verifiedAt: modelId === "grok-4.7" ? "2026-09-23" : "2026-08-18", })), ]; @@ -662,6 +670,19 @@ export const CONTEXT_TIERS: readonly ContextTier[] = [ source: "https://docs.x.ai/developers/pricing", verifiedAt: "2026-08-18", }, + { + // xAI documents the same whole-request >=200k band for grok-4.7; + // priority stacking remains a lower bound. See + // devlog/_plan/260923_grok47_parity/010_probe-evidence.md. + provider: "xai", + modelId: "grok-4.7", + thresholdInputTokens: 200_000, + inclusive: true, + multiplier: UNIFORM_DOUBLE, + confirmedPriorityRelation: "lower-bound", + source: "https://docs.x.ai/developers/models/grok-4.7", + verifiedAt: "2026-09-23", + }, ...["minimax", "minimax-cn"].map((provider): ContextTier => ({ provider, modelId: "MiniMax-M3", diff --git a/structure/adapters/registry.md b/structure/adapters/registry.md index ffa5b86d95b..caaed1dd3eb 100644 --- a/structure/adapters/registry.md +++ b/structure/adapters/registry.md @@ -85,6 +85,9 @@ Some adapters share another adapter's routed-tool semantics while retaining inde rows each base model's collapsed UID gathers — the EFFORT_TOKENS suffixes, tier rows like `-1m` included: unmeasured rows abstain, unanimous measured rows advertise `["text"]` or `["text", "image"]`, and measured disagreement stays unadvertised. + The degraded static roster includes `grok-4-7` with its catalog-measured ladder but + omits `grok-4-6` until a Devin-specific ladder is measured; live discovery can still + return 4.6 for an account that offers it. At dispatch the adapter reads the same per-account/host cache once more for the exact selected wire UID and forwards `completionOpts.maxInputTokens`: the smallest diff --git a/structure/providers/cursor.md b/structure/providers/cursor.md index 30ef6cfb9f8..8a37089cbf3 100644 --- a/structure/providers/cursor.md +++ b/structure/providers/cursor.md @@ -42,11 +42,15 @@ All four route to the `default` Cursor wire model. Explicit variants additionall parameterized-model channel used by current Cursor clients. Router rows are static capabilities and must survive a live `GetUsableModels` response that omits `default`. -`cursor/grok-4.5-fast` and `cursor/grok-4.6-fast` are stable Codex-facing rows, but current Cursor -clients do not request them as flat model slugs. OpenCodex sends the matching Grok base id through +`cursor/grok-4.5-fast`, `cursor/grok-4.6-fast`, and `cursor/grok-4.7-fast` are stable Codex-facing rows. +For 4.5 and 4.6 Fast, OpenCodex sends the matching Grok base id through `requested_model` with separate `effort` and `fast=true` parameters, leaving legacy `model_details` -unset for that parameterized external selection. Grok 4.5 stops at `high`; Grok 4.6 additionally -advertises and sends `xhigh`. Live discovery recognizes Cursor's flattened +unset for that parameterized external selection. Grok 4.7 instead sends its flattened, unprefixed +`grok-4.7-{effort}-fast` id directly. Grok 4.5 stops at `high`; Grok 4.6 and 4.7 additionally +advertise and send `xhigh`. The 2026-09-23 Cursor roster and probes in +`devlog/_plan/260923_grok47_parity/010_probe-evidence.md` show unprefixed +`grok-4.7-{low,medium,high,xhigh}` and `grok-4.7-{low,medium,high,xhigh}-fast` wire ids; +the bare `grok-4.7-fast` id is rejected. For 4.5 and 4.6, live discovery recognizes Cursor's flattened `cursor-grok-{version}-{effort}-fast` variants, plus the older `grok-{version}-fast-{effort}` ordering, as availability evidence only. diff --git a/structure/providers/xai-grok.md b/structure/providers/xai-grok.md index 4dfa27723f0..32dfe1ad41c 100644 --- a/structure/providers/xai-grok.md +++ b/structure/providers/xai-grok.md @@ -157,7 +157,8 @@ Renamed fixed-key providers receive [missing reasoning metadata](../catalog.md#r xAI's Priority Processing (`service_tier: "priority"` on Chat Completions and Responses, documented for the API-key product) is honored by the Grok OAuth subscription gateway on a -probed model set (live probe 2026-09-13, `devlog/_fin/260913_xai_oauth_fast/`): grok-4.6, +probed model set (live probes 2026-09-13 and 2026-09-23, `devlog/_fin/260913_xai_oauth_fast/` +and `devlog/_plan/260923_grok47_parity/010_probe-evidence.md`): grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-4.20-0309-reasoning, grok-4.20-0309-non-reasoning, grok-build-0.1 and grok-composer-2.5-fast each echoed `priority` upstream. The registry entry classifies exactly that set in `modelSupportsServiceTier` and declares `chatServiceTier: true`, so the OAuth lane diff --git a/structure/transports/responses.md b/structure/transports/responses.md index 023bddbe114..b2eeefb287a 100644 --- a/structure/transports/responses.md +++ b/structure/transports/responses.md @@ -409,13 +409,14 @@ different custom destination does not inherit its upstream assumptions. Object-f also narrow the decision by inbound protocol and authentication mode; an auth-scoped default must not leak from a subscription transport into an API-key or forwarded-credential route. -xAI keeps `openai-chat` as its provider-wide compatibility wire, but Grok 4.5/4.6 subscription +xAI keeps `openai-chat` as its provider-wide compatibility wire, but Grok 4.5/4.6/4.7 subscription Responses requests default to native `openai-responses`. Existing namespace, hosted-search and reasoning-replay normalization remains in force. The reserved `xai` OAuth transport is name-pinned to the Grok CLI gateway even if its saved base URL differs; custom provider IDs do not inherit this default. API-key requests, translated Chat/Anthropic defaults and other Grok models retain their existing wire and tier policy. The OAuth lane is service-tier classified per model -(`modelSupportsServiceTier` on the registry entry, live-probed 2026-09-13): grok-4.6, grok-4.5, +(`modelSupportsServiceTier` on the registry entry, live-probed 2026-09-13 and 2026-09-23; +`devlog/_plan/260923_grok47_parity/010_probe-evidence.md` records 4.7): grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-4.20-0309-reasoning, grok-4.20-0309-non-reasoning, grok-build-0.1 and grok-composer-2.5-fast accept `service_tier: "priority"` over Grok OAuth and echo it, so those routes resolve Fast-eligible, publish `--fast` rows, and forward a caller-sent tier on either diff --git a/tests/providers/command-code-provider.test.ts b/tests/providers/command-code-provider.test.ts index 692bbf45586..52458ce8704 100644 --- a/tests/providers/command-code-provider.test.ts +++ b/tests/providers/command-code-provider.test.ts @@ -211,12 +211,13 @@ describe("Command Code provider", () => { "meta/muse-spark-1.3-contributor", "meta/muse-spark-1.2", "meta/muse-spark-1.2-contributor", + "xai/grok-4.6", + "xai/grok-4.7", ]; const verifiedTextOnlyModels = [ "deepseek/deepseek-v4-flash", "zai-org/GLM-5.2", "zai-org/GLM-5.3", - "xai/grok-4.6", ]; expect(apiKey?.modelInputModalities).toEqual(oauth?.modelInputModalities); diff --git a/tests/providers/cursor/cursor-discovery.test.ts b/tests/providers/cursor/cursor-discovery.test.ts index 9dd64b68d64..9a1a46bb08f 100644 --- a/tests/providers/cursor/cursor-discovery.test.ts +++ b/tests/providers/cursor/cursor-discovery.test.ts @@ -76,6 +76,9 @@ describe("Cursor discovery metadata", () => { expect(ids).toContain("gpt-5.5-extra"); expect(ids).toContain("grok-4.6"); expect(ids).not.toContain("grok-4.6-fast"); + expect(ids).toContain("grok-4.7"); + expect(ids).not.toContain("grok-4.7-fast"); + expect(cursorModelContextWindows(CURSOR_STATIC_MODELS)["grok-4.7"]).toBe(500_000); expect(ids).not.toContain("composer-2"); // `auto` mirrors the jawcode SOT `default` entry (200k), not the generic fallback window. for (const id of CURSOR_ROUTER_MODEL_IDS) { @@ -139,6 +142,10 @@ describe("Cursor discovery metadata", () => { expect(isCursorModelAvailableForAccount("grok-4.6", ["cursor-grok-4.6-xhigh"])).toBe(true); expect(isCursorModelAvailableForAccount("grok-4.6-fast", ["cursor-grok-4.6-xhigh-fast"])).toBe(true); expect(isCursorModelAvailableForAccount("grok-4.6", ["cursor-grok-4.6-xhigh-fast"])).toBe(true); + expect(isCursorModelAvailableForAccount("grok-4.7", ["grok-4.7-xhigh"])).toBe(true); + expect(isCursorModelAvailableForAccount("grok-4.7-fast", ["grok-4.7-xhigh-fast"])).toBe(true); + expect(isCursorModelAvailableForAccount("grok-4.7", ["grok-4.7-xhigh-fast"])).toBe(true); + expect(isCursorModelAvailableForAccount("grok-4.7", ["cursor-grok-4.6-xhigh"])).toBe(false); expect(isCursorModelAvailableForAccount("gpt-5.4", ["cursor-gpt-5.4-high"])).toBe(true); // Prefixed sibling rejection: cursor- prefix must not bypass sibling-model checks. expect(isCursorModelAvailableForAccount("gpt-5.5", ["cursor-gpt-5.5-extra-high"])).toBe(false); @@ -161,6 +168,12 @@ describe("Cursor discovery metadata", () => { ["cursor-grok-4.6-xhigh", "cursor-grok-4.6-xhigh-fast"], ); expect(grok46.map(model => model.id)).toEqual(["grok-4.6", "grok-4.6-fast"]); + + const grok47 = filterCursorConfiguredModelsByLiveDiscovery( + [{ id: "grok-4.7" }, { id: "grok-4.7-fast" }], + ["grok-4.7-xhigh", "grok-4.7-xhigh-fast"], + ); + expect(grok47.map(model => model.id)).toEqual(["grok-4.7", "grok-4.7-fast"]); }); test("live discovery filter always keeps all router levels when GetUsableModels omits them", () => { @@ -206,6 +219,8 @@ describe("Cursor discovery metadata", () => { expect(inferCursorContextWindow("glm-5.2")).toBe(1_000_000); expect(inferCursorContextWindow("grok-4.3")).toBe(256_000); expect(inferCursorContextWindow("grok-4.6")).toBe(500_000); + expect(inferCursorContextWindow("grok-4.7")).toBe(500_000); + expect(inferCursorContextWindow("grok-4.7-xhigh-fast")).toBe(500_000); expect(inferCursorContextWindow("gpt-5.5")).toBe(272_000); }); @@ -226,6 +241,8 @@ describe("Cursor discovery metadata", () => { { id: "grok-4.3", supportsReasoningEffort: true }, { id: "grok-4.6", supportsReasoningEffort: true }, { id: "grok-4.6-fast", supportsReasoningEffort: true }, + { id: "grok-4.7", supportsReasoningEffort: true }, + { id: "grok-4.7-fast", supportsReasoningEffort: true }, { id: "unknown-reasoning-model", supportsReasoningEffort: true }, { id: "composer-2.5", supportsReasoningEffort: false }, ]); @@ -237,6 +254,8 @@ describe("Cursor discovery metadata", () => { expect(efforts["grok-4.3"]).toEqual([]); expect(efforts["grok-4.6"]).toEqual(["low", "medium", "high", "xhigh"]); expect(efforts["grok-4.6-fast"]).toEqual(["low", "medium", "high", "xhigh"]); + expect(efforts["grok-4.7"]).toEqual(["low", "medium", "high", "xhigh"]); + expect(efforts["grok-4.7-fast"]).toEqual(["low", "medium", "high", "xhigh"]); expect(efforts["unknown-reasoning-model"]).toEqual([]); expect(efforts["composer-2.5"]).toEqual([]); }); diff --git a/tests/providers/cursor/cursor-display-names.test.ts b/tests/providers/cursor/cursor-display-names.test.ts index 3751601445c..73dd355e957 100644 --- a/tests/providers/cursor/cursor-display-names.test.ts +++ b/tests/providers/cursor/cursor-display-names.test.ts @@ -36,6 +36,7 @@ describe("cursor picker labels reach the catalog", () => { } // Cursor's own product name stays; a third-party model keeps its `cursor/` slug. expect(labels["grok-4.6"]).toBe("Cursor Grok 4.6"); + expect(labels["grok-4.7"]).toBe("Cursor Grok 4.7"); expect(labels["grok-4.5"]).toBe("Cursor Grok 4.5"); expect(labels).not.toHaveProperty("kimi-k3"); expect(labels).not.toHaveProperty("claude-opus-5"); @@ -46,6 +47,7 @@ describe("cursor picker labels reach the catalog", () => { test("a fresh seed exposes only the branded labels through configuredModelDisplayName", () => { const seeded = providerConfigSeed(cursorEntry()); expect(configuredModelDisplayName(seeded, "grok-4.6")).toBe("Cursor Grok 4.6"); + expect(configuredModelDisplayName(seeded, "grok-4.7")).toBe("Cursor Grok 4.7"); expect(configuredModelDisplayName(seeded, "kimi-k3")).toBeUndefined(); expect(configuredModelDisplayName(seeded, "claude-4-sonnet-1m")).toBeUndefined(); expect(configuredModelDisplayName(seeded, "composer-2.5-fast")).toBeUndefined(); @@ -62,6 +64,7 @@ describe("cursor picker labels reach the catalog", () => { expect(configuredModelDisplayName(existing, "kimi-k3")).toBe("My K3"); // ...the branded row gains its label, and an unbranded row stays on its routed slug. expect(configuredModelDisplayName(existing, "grok-4.6")).toBe("Cursor Grok 4.6"); + expect(configuredModelDisplayName(existing, "grok-4.7")).toBe("Cursor Grok 4.7"); expect(configuredModelDisplayName(existing, "claude-opus-5")).toBeUndefined(); }); }); diff --git a/tests/providers/cursor/cursor-effort-suffix.test.ts b/tests/providers/cursor/cursor-effort-suffix.test.ts index c5ef08c7784..39868e07509 100644 --- a/tests/providers/cursor/cursor-effort-suffix.test.ts +++ b/tests/providers/cursor/cursor-effort-suffix.test.ts @@ -26,6 +26,19 @@ const RECORDED_CURSOR_GROK_46_DISCOVERY_IDS = [ "cursor-grok-4.6-xhigh-fast", ] as const; +// Live GetUsableModels roster (live calls accepted grok-4.7-low and grok-4.7-xhigh-fast): +// devlog/_plan/260923_grok47_parity/010_probe-evidence.md. +const RECORDED_CURSOR_GROK_47_DISCOVERY_IDS = [ + "grok-4.7-low", + "grok-4.7-medium", + "grok-4.7-high", + "grok-4.7-xhigh", + "grok-4.7-low-fast", + "grok-4.7-medium-fast", + "grok-4.7-high-fast", + "grok-4.7-xhigh-fast", +] as const; + function modelIdFor(modelId: string, reasoning?: string): string { const parsed: OcxParsedRequest = { modelId, @@ -188,6 +201,24 @@ describe("Cursor per-model reasoning-effort suffix", () => { expect(RECORDED_CURSOR_GROK_46_DISCOVERY_IDS).toContain("cursor-grok-4.6-xhigh-fast"); }); + test("grok-4.7 regular and Fast requests use the unprefixed live ids", () => { + for (const effort of ["low", "medium", "high", "xhigh"] as const) { + const regular = selectionFor("cursor/grok-4.7", effort); + const fast = selectionFor("cursor/grok-4.7-fast", effort); + expect(regular).toEqual({ modelId: `grok-4.7-${effort}`, parameters: undefined }); + expect(fast).toEqual({ modelId: `grok-4.7-${effort}-fast`, parameters: undefined }); + expect(RECORDED_CURSOR_GROK_47_DISCOVERY_IDS).toContain(regular.modelId); + expect(RECORDED_CURSOR_GROK_47_DISCOVERY_IDS).toContain(fast.modelId); + expect(cursorWireModelIdWithEffort("grok-4.7-fast", effort)).toBe(fast.modelId); + } + expect(modelIdFor("cursor/grok-4.7", "max")).toBe("grok-4.7-xhigh"); + expect(modelIdFor("cursor/grok-4.7-fast", "max")).toBe("grok-4.7-xhigh-fast"); + expect(modelIdFor("cursor/grok-4.7-fast")).toBe("grok-4.7-xhigh-fast"); + expect(RECORDED_CURSOR_GROK_47_DISCOVERY_IDS).not.toContain("grok-4.7-fast"); + expect(cursorModelEffortLadder("grok-4.7")).toEqual(["low", "medium", "high", "xhigh"]); + expect(cursorModelEffortLadder("grok-4.7-fast")).toEqual(["low", "medium", "high", "xhigh"]); + }); + test("kimi-k3 maps to its live effort-suffixed variants", () => { expect(modelIdFor("cursor/kimi-k3", "low")).toBe("kimi-k3-low"); expect(modelIdFor("cursor/kimi-k3", "medium")).toBe("kimi-k3-high"); diff --git a/tests/providers/cursor/cursor-fast-listing.test.ts b/tests/providers/cursor/cursor-fast-listing.test.ts index 8a67badf533..a53683a67f9 100644 --- a/tests/providers/cursor/cursor-fast-listing.test.ts +++ b/tests/providers/cursor/cursor-fast-listing.test.ts @@ -38,6 +38,7 @@ describe("global fast switch lists -fast identities outside Codex", () => { test("a thinking-default base lists its thinking-fast id, a regular-default base its fast id", () => { expect(cursorFastIdFor("claude-opus-5")).toBe("claude-opus-5-thinking-fast"); expect(cursorFastIdFor("grok-4.6")).toBe("grok-4.6-fast"); + expect(cursorFastIdFor("grok-4.7")).toBe("grok-4.7-fast"); }); test("a base with no fast variant yields no fast id at all", () => { @@ -58,6 +59,8 @@ describe("global fast switch lists -fast identities outside Codex", () => { .toContain("claude-ocx-cursor--claude-opus-5-thinking-fast"); expect(listIds([cursorModel("grok-4.6", 500_000)], true)) .toContain("claude-ocx-cursor--grok-4.6-fast"); + expect(listIds([cursorModel("grok-4.7", 500_000)], true)) + .toContain("claude-ocx-cursor--grok-4.7-fast"); }); test("the switch leaves a base without a fast variant alone", () => { @@ -79,6 +82,7 @@ describe("global fast switch lists -fast identities outside Codex", () => { expect(decide("claude-opus-5", true)).toEqual({ kind: "set", value: "fast" }); expect(decide("grok-4.6", true)).toEqual({ kind: "set", value: "fast" }); + expect(decide("grok-4.7", true)).toEqual({ kind: "set", value: "fast" }); expect(decide("kimi-k3", true)).toEqual({ kind: "drop" }); // And the switch off must not promote. expect(decide("claude-opus-5", false)).toEqual({ kind: "drop" }); diff --git a/tests/providers/cursor/cursor-fast-tier.test.ts b/tests/providers/cursor/cursor-fast-tier.test.ts index bcdcc9c47f3..729cbe0ae48 100644 --- a/tests/providers/cursor/cursor-fast-tier.test.ts +++ b/tests/providers/cursor/cursor-fast-tier.test.ts @@ -52,6 +52,7 @@ describe("Codex Fast reaches Cursor's fast variant", () => { expect(decide("claude-opus-5")).toEqual(FAST_DECISION); expect(decide("grok-4.6")).toEqual(FAST_DECISION); + expect(decide("grok-4.7")).toEqual(FAST_DECISION); expect(decide("kimi-k3")).toEqual({ kind: "drop" }); }); @@ -77,6 +78,15 @@ describe("Codex Fast reaches Cursor's fast variant", () => { .toBe("cursor-grok-4.6-high"); }); + test("grok-4.7 Fast sends the live flattened id with no cursor prefix", () => { + const fast = createCursorRequest(parsedFor("cursor/grok-4.7", "xhigh", FAST_DECISION)); + expect(fast.modelId).toBe("grok-4.7-xhigh-fast"); + expect(fast.requestedModelParameters).toBeUndefined(); + expect(createCursorRequest(parsedFor("cursor/grok-4.7", "xhigh")).modelId) + .toBe("grok-4.7-xhigh"); + expect(cursorRequestEmitsFastVariant(parsedFor("cursor/grok-4.7", "xhigh", FAST_DECISION))).toBe(true); + }); + test("a base without a fast variant is byte-identical with the toggle on", () => { const off = createCursorRequest(parsedFor("cursor/kimi-k3", "max")); const on = createCursorRequest(parsedFor("cursor/kimi-k3", "max", FAST_DECISION)); diff --git a/tests/providers/cursor/cursor-umbrella-rows.test.ts b/tests/providers/cursor/cursor-umbrella-rows.test.ts index f616f7f5055..ce0f42f7020 100644 --- a/tests/providers/cursor/cursor-umbrella-rows.test.ts +++ b/tests/providers/cursor/cursor-umbrella-rows.test.ts @@ -36,6 +36,8 @@ describe("cursor umbrella picker rows (devlog 260828_cursor_umbrella_catalog)", expect(ids).not.toContain("claude-opus-5-fast"); expect(ids).not.toContain("grok-4.5-fast"); expect(ids).not.toContain("grok-4.6-fast"); + expect(ids).not.toContain("grok-4.7-fast"); + expect(ids.filter(id => id === "grok-4.7")).toHaveLength(1); expect(ids).not.toContain("claude-fable-5.1"); expect(ids).not.toContain("claude-5.1-fable"); expect(ids.filter(id => id === "claude-fable-5-1")).toHaveLength(1); @@ -111,6 +113,12 @@ describe("cursor umbrella picker rows (devlog 260828_cursor_umbrella_catalog)", ]); }); + test("grok-4.7 fast alias resolves to an effort-suffixed flat wire id", () => { + const request = createCursorRequest(parsedFor("cursor/grok-4.7-fast", "xhigh")); + expect(request.modelId).toBe("grok-4.7-xhigh-fast"); + expect(request.requestedModelParameters).toBeUndefined(); + }); + test("kimi-k3-1m alias still arms Max Mode", () => { const request = createCursorRequest(parsedFor("cursor/kimi-k3-1m", "max")); expect(request.maxMode).toBe(true); diff --git a/tests/providers/devin-effort-ladder.test.ts b/tests/providers/devin-effort-ladder.test.ts index 0b800c11a8f..57149a02a46 100644 --- a/tests/providers/devin-effort-ladder.test.ts +++ b/tests/providers/devin-effort-ladder.test.ts @@ -2,6 +2,7 @@ import { describe, expect, test } from "bun:test"; import { DEVIN_DEFAULT_EFFORTS, DEVIN_MODEL_EFFORTS, + DEVIN_STATIC_MODELS, collapseDevinModelUid, devinReasoningRungsOf, sortDevinRungs, @@ -56,6 +57,12 @@ describe("devin advertises a ladder instead of inheriting the generic one", () = expect(DEVIN_MODEL_EFFORTS["swe-2"]).toEqual(["medium", "high", "max"]); }); + test("degraded Grok roster excludes 4.6 until its Devin ladder is measured", () => { + expect(DEVIN_STATIC_MODELS).not.toContain("grok-4-6"); + expect(DEVIN_STATIC_MODELS).toContain("grok-4-7"); + expect(DEVIN_MODEL_EFFORTS["grok-4-7"]).toEqual(["low", "medium", "high", "xhigh", "max"]); + }); + test("the fallback ladder omits ultra, which Cognition has no lane for", () => { expect(DEVIN_DEFAULT_EFFORTS).not.toContain("ultra"); expect(DEVIN_DEFAULT_EFFORTS).toContain("medium"); diff --git a/tests/providers/opencode-go-grok46-responses.test.ts b/tests/providers/opencode-go-grok46-responses.test.ts index cadea0a9b5a..c48fbf13079 100644 --- a/tests/providers/opencode-go-grok46-responses.test.ts +++ b/tests/providers/opencode-go-grok46-responses.test.ts @@ -43,12 +43,14 @@ function build(modelId: string, rawBody: Record, configuredProv return JSON.parse(request.body) as Record; } -describe("OpenCode Go Grok 4.6 Responses compatibility", () => { - test("routes only the documented Grok model to Responses", () => { +describe("OpenCode Go Grok Responses compatibility", () => { + test("routes the documented Grok models to Responses", () => { const configured = providerConfigSeed(registryEntry); expect(resolveWireProtocolOverride("opencode-go", "grok-4.6", configured).adapter) .toBe("openai-responses"); + expect(resolveWireProtocolOverride("opencode-go", "grok-4.7", configured).adapter) + .toBe("openai-responses"); expect(resolveWireProtocolOverride("opencode-go", "grok-4.5", configured).adapter) .toBe("openai-chat"); }); @@ -60,6 +62,11 @@ describe("OpenCode Go Grok 4.6 Responses compatibility", () => { expect(registryEntry.modelReasoningEfforts?.["grok-4.6"]) .toEqual(["low", "medium", "high", "xhigh"]); expect(registryEntry.modelDefaultReasoningEfforts?.["grok-4.6"]).toBe("high"); + expect(registryEntry.modelReasoningEfforts?.["grok-4.7"]) + .toEqual(["low", "medium", "high", "xhigh"]); + expect(registryEntry.modelDefaultReasoningEfforts?.["grok-4.7"]).toBe("high"); + expect(build("grok-4.7", { reasoning: { effort: "max" } }).reasoning) + .toEqual({ effort: "xhigh" }); }); test("drops the hosted search tool that this exact destination rejects", () => { diff --git a/tests/providers/provider-registry-parity.test.ts b/tests/providers/provider-registry-parity.test.ts index 87a701a7a5b..834bbcaf89c 100644 --- a/tests/providers/provider-registry-parity.test.ts +++ b/tests/providers/provider-registry-parity.test.ts @@ -1250,13 +1250,17 @@ describe("provider registry parity", () => { } expect(OAUTH_PROVIDERS.xai.providerConfig.defaultModel).toBe("grok-4.5"); expect(OAUTH_PROVIDERS.xai.providerConfig.liveModels).toBe(true); + expect(OAUTH_PROVIDERS.xai.providerConfig.models?.[0]).toBe("grok-4.7"); expect(OAUTH_PROVIDERS.xai.providerConfig.models).toContain("grok-4.6"); expect(OAUTH_PROVIDERS.xai.providerConfig.models).toContain("grok-4.5"); + expect(OAUTH_PROVIDERS.xai.providerConfig.modelContextWindows?.["grok-4.7"]).toBe(500_000); expect(OAUTH_PROVIDERS.xai.providerConfig.modelContextWindows?.["grok-4.6"]).toBe(500_000); expect(OAUTH_PROVIDERS.xai.providerConfig.modelContextWindows?.["grok-4.5"]).toBe(500_000); + expect(OAUTH_PROVIDERS.xai.providerConfig.modelReasoningEfforts?.["grok-4.7"]).toEqual(["low", "medium", "high", "xhigh"]); expect(OAUTH_PROVIDERS.xai.providerConfig.modelReasoningEfforts?.["grok-4.6"]).toEqual(["low", "medium", "high", "xhigh"]); expect(OAUTH_PROVIDERS.xai.providerConfig.modelReasoningEfforts?.["grok-4.5"]).toEqual(["low", "medium", "high"]); - expect(OAUTH_PROVIDERS.xai.providerConfig.modelDefaultReasoningEfforts).toEqual({ "grok-4.6": "high" }); + expect(OAUTH_PROVIDERS.xai.providerConfig.modelDefaultReasoningEfforts).toEqual({ "grok-4.7": "high", "grok-4.6": "high" }); + expect(OAUTH_PROVIDERS.xai.providerConfig.modelInputModalities?.["grok-4.7"]).toEqual(["text", "image"]); expect(OAUTH_PROVIDERS.xai.providerConfig.modelReasoningEffortMap).toBeUndefined(); expect(OAUTH_PROVIDERS.xai.providerConfig.noVisionModels).toContain("grok-build-0.1"); const antigravityRegistry = PROVIDER_REGISTRY.find(entry => entry.id === "google-antigravity"); @@ -1483,6 +1487,30 @@ describe("provider registry parity", () => { expect(entry?.default_reasoning_level).toBe("high"); }); + test("grok-4.7 carries measured context and the four-rung picker ladder", () => { + const xai = PROVIDER_REGISTRY.find(entry => entry.id === "xai"); + const seed = providerConfigSeed(xai!); + const model = applyProviderConfigHints("xai", seed, { id: "grok-4.7", provider: "xai" }); + expect(model.contextWindow).toBe(500_000); + expect(model.reasoningEfforts).toEqual(["low", "medium", "high", "xhigh"]); + expect(model.inputModalities).toEqual(["text", "image"]); + + const entries = buildCatalogEntries(nativeTemplate() as never, [], [model]); + const entry = entries.find(e => e.slug === "xai/grok-4.7"); + expect(entry?.context_window).toBe(500_000); + expect((entry?.supported_reasoning_levels as { effort: string }[]).map(l => l.effort)) + .toEqual(["low", "medium", "high", "xhigh", "max", "ultra"]); + expect(entry?.default_reasoning_level).toBe("high"); + }); + + test("Devin grok-4-7 degraded-mode seed carries its catalog window and ladder", () => { + const devin = PROVIDER_REGISTRY.find(entry => entry.id === "devin"); + expect(devin?.models).toContain("grok-4-7"); + expect(devin?.modelContextWindows?.["grok-4-7"]).toBe(500_000); + expect(devin?.modelReasoningEfforts?.["grok-4-7"]) + .toEqual(["low", "medium", "high", "xhigh", "max"]); + }); + // The id-list assertion above only proves the preset exists. Pin the contract a user actually // depends on: which endpoint the key is sent to, which adapter parses the stream, and that the // vendor-namespaced seed models survive into a real catalog entry. diff --git a/tests/providers/xai/xai-transport.test.ts b/tests/providers/xai/xai-transport.test.ts index 9eb21fcacde..157d38f71b2 100644 --- a/tests/providers/xai/xai-transport.test.ts +++ b/tests/providers/xai/xai-transport.test.ts @@ -84,6 +84,19 @@ describe("xAI effective wire control state", () => { expect(xaiResponsesOptInState({ ...provider("oauth"), modelAdapters: { "grok-4.6": "invalid" } })).toBe(true); expect(xaiResponsesOptInState({ ...provider("oauth"), modelAdapters: { "grok-4.6": "openai-chat", "grok-4.5": "openai-chat" } })).toBe(false); }); + + test("grok-4.7 defaults OAuth Responses inbound and honors explicit Chat", () => { + const oauth = provider("oauth"); + expect(resolveWireProtocolOverride("xai", "grok-4.7", oauth, "responses").adapter) + .toBe("openai-responses"); + expect(resolveWireProtocolOverride("xai", "grok-4.7", provider("key"), "responses").adapter) + .toBe("openai-chat"); + expect(resolveWireProtocolOverride("xai", "grok-4.7", { + ...oauth, + modelAdapters: { "grok-4.7": "openai-chat" }, + }, "responses").adapter).toBe("openai-chat"); + expect(XAI_RESPONSES_OPT_IN_MODELS).not.toContain("grok-4.7"); + }); }); describe("xAI auth-mode transport selection", () => { @@ -620,6 +633,7 @@ describe("xAI reasoning_content cache preservation", () => { test("registry preset exposes multi-agent only on Responses without claiming replay material", () => { const entry = getProviderRegistryEntry("xai"); expect(entry?.preserveReasoningContentModels).toEqual([ + "grok-4.7", "grok-4.6", "grok-4.5", "grok-4.3", diff --git a/tests/service/service-tier-capability.test.ts b/tests/service/service-tier-capability.test.ts index 87bff20708e..30726496190 100644 --- a/tests/service/service-tier-capability.test.ts +++ b/tests/service/service-tier-capability.test.ts @@ -123,6 +123,7 @@ describe("xAI Fast capability follows the captured authentication transport", () // (devlog/_fin/260913_xai_oauth_fast/020_probe-evidence.md), never provider-wide. expect(entry.chatServiceTier).toBe(true); expect(entry.modelSupportsServiceTier).toEqual({ + "grok-4.7": true, "grok-4.6": true, "grok-4.5": true, "grok-4.3": true, @@ -146,6 +147,11 @@ describe("xAI Fast capability follows the captured authentication transport", () eligibility: "eligible", forwardCallerTier: true, }); + expect(fastPolicyForModel(xaiProvider("oauth"), "grok-4.7", "xai")).toMatchObject({ + capability: true, + eligibility: "eligible", + forwardCallerTier: true, + }); // Probed but downgraded by the gateway (answers service_tier "default" when sent // "priority"), so it stays unclassified and keeps its caller-tier pin. diff --git a/tests/usage/usage-cost.test.ts b/tests/usage/usage-cost.test.ts index d47479eded1..8721e5edf7f 100644 --- a/tests/usage/usage-cost.test.ts +++ b/tests/usage/usage-cost.test.ts @@ -936,11 +936,12 @@ describe("xAI Priority Processing pricing", () => { test("xAI rules declare exact 2x premiums with official provenance", () => { const xaiRules = PRIORITY_PRICING_RULES.filter(rule => rule.provider === "xai"); - expect(xaiRules.map(rule => rule.modelId)).toEqual(["grok-4.5", "grok-4.6"]); + expect(xaiRules.map(rule => rule.modelId)).toEqual(["grok-4.5", "grok-4.6", "grok-4.7"]); expect(xaiRules.every(rule => rule.multiplier === 2)).toBe(true); expect(xaiRules.every(rule => rule.requiresResponseConfirmation === true)).toBe(true); expect(xaiRules.every(rule => rule.source === "https://docs.x.ai/developers/advanced-api-usage/priority-processing")).toBe(true); expect(findPriorityPricingRule("xai", "grok-4.6")?.multiplier).toBe(2); + expect(findPriorityPricingRule("xai", "grok-4.7")?.verifiedAt).toBe("2026-09-23"); expect(findPriorityPricingRule("openrouter", "grok-4.6")).toBeUndefined(); expect(resolveMatchedPrice("openrouter", "grok-4.6")?.cost4).toEqual({ input: 2, @@ -975,6 +976,14 @@ describe("xAI Priority Processing pricing", () => { expect(confirmed.priorityMultiplier).toBe(2); }); + test("grok-4.7 uses the published base price and whole-request long-context band", () => { + expect(resolveMatchedPrice("xai", "grok-4.7")?.cost4).toEqual({ + input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0, + }); + expect(CONTEXT_TIERS.find(tier => tier.provider === "xai" && tier.modelId === "grok-4.7")) + .toMatchObject({ thresholdInputTokens: 200_000, inclusive: true, confirmedPriorityRelation: "lower-bound" }); + }); + test("an assumed priority outcome stays at the standard price", () => { const assumedOutcome = outcome(); const assumed = estimate(assumedOutcome);