docs: GLM-5.3 Flash, the missing GLM-5.3 row, and counts 71→72 / 95→96 - #57
Merged
Conversation
Z.AI's glm-5.3-flash, probed live 2026-08-27 against api.z.ai before listing:
real completions, tool calls, streaming, and image input all verified.
price $0.15 in / $0.50 out — docs.z.ai/guides/overview/pricing, the
international USD LIST rate. Z.AI is running a 50% launch
promotion ($0.075/$0.25) that ends 2026-09-09; chat sells at
cost, so listing the promo rate would put us under COGS the
morning it lapses.
context 1M
maxOutput 131072 — the API's hard cap (error 1210 at 131073), not the
context window.
thinking always on, cannot be disabled. Unlike 5/5.1/5.2 it returns
content alongside reasoning, so it needs no workaround.
The Z.AI reference table was also missing glm-5.3 entirely — the 08-19 launch
swept counts but never added the row. Added, and 5.2 loses the "(flagship)"
tag it kept after 5.3 shipped.
Counts swept with brand-numbers.docs.test.ts's OWN regex (40 counts, 22 files),
so prices and dates were untouched. README/ECOSYSTEM carry br: markers and are
refreshed by the weekly brand-sync workflow instead.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Step 4 of the model-launch checklist for
zai/glm-5.3-flash.New model
zai/glm-5.3-flash— $0.15/$0.50 per 1M, 1M context, 131,072 max output, native image input, always-on reasoning. Probed live against api.z.ai before listing: completions, tool calls, streaming, and vision.Backfill
zai/glm-5.3row — the 2026-08-19 launch (docs: model counts 70→71 chat, 94→95 total (GLM-5.3) #51) swept counts but skipped the table. Added, andglm-5.2loses the "(flagship)" tag it kept after 5.3 shipped.Counts
brand-numbers.docs.test.ts's own regex (40 counts, 22 files) rather than by hand, so prices and dates were untouched.README.md/ECOSYSTEM.mdcarrybr:markers and are refreshed by the weeklybrand-syncworkflow — not touched here.Guards green in the blockrun tree against this branch.
🤖 Generated with Claude Code