Skip to content

[Workers AI] Add GLM 5.3 Flash model - #33041

Merged
mchenco merged 2 commits into
productionfrom
mchen/glm-5.3-flash
Aug 26, 2026
Merged

[Workers AI] Add GLM 5.3 Flash model#33041
mchenco merged 2 commits into
productionfrom
mchen/glm-5.3-flash

Conversation

@mchenco

@mchenco mchenco commented Aug 26, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds the GLM-5.3 Flash model launch docs for Workers AI:

  • New model page data (glm-5.3-flash.json, pulled from the catalog API)
  • Pricing page updates: added GLM-5.3 Flash to the paid-models note and the pricing table
  • New changelog announcement

GLM-5.3 Flash is a 320B-parameter MoE model (18B active) with vision, reasoning, and function calling. It has a 1,048,576 token context window and requires the Workers Paid plan or AI Gateway credits.

Documentation checklist

@cloudflare-docs-bot

cloudflare-docs-bot Bot commented Aug 26, 2026

Copy link
Copy Markdown
Contributor

Review

⚠️ 1 warning found in commit 87adfe8.

👉 Fix in your agent 👈
Fix the following review findings in PR #33041 (https://github.com/cloudflare/cloudflare-docs/pull/33041).

Before making changes, review each finding and present a brief summary table:
- For each finding, state whether you agree, disagree, or need clarification
- If you disagree (e.g. the fix requires disproportionate effort for minimal benefit,
  or the finding is factually incorrect), explain why
- If you need clarification before deciding, ask those questions
- Then share your plan for which issues to tackle and in what order

After triaging, follow this order:
1. Post a comment on this PR for any findings you are skipping, with the finding ID and your reasoning.
2. Then commit the fixes for the legitimate findings.

The comment must come before the commit — the bot reads PR comments when a new
push triggers a review, so skip comments posted after the push will be missed.

---

## Code Review

### Warnings (1)

#### CR-0880ef0a93e3 · Capability mismatch in model schema
- **File:** `src/content/workers-ai-models/glm-5.3-flash.json` line 25
- **Issue:** The model declares `"vision": "true"`, but the `messages[*].content` schema only permits a string or an array of text parts (lines 166–188). There is no `image_url` (or `video_url`) content part, so the schema does not reflect the advertised multimodal capability.
- **Fix:** Add `image_url` (and any other applicable modalities such as `video_url`) as content part options in `messages[*].content.items`, matching the richer schema used by other vision models like `glm-5.2.json`.

Code Review

This code review is in beta and may not always be helpful — use your judgment.

Warnings (1)
File Issue
workers-ai-models/glm-5.3-flash.json line 25 Capability mismatch in model schema — The model declares "vision": "true", but the messages[\*].content schema only permits a string or an array of text parts (lines 166–188). There is no image_url (or video_url) content part, so the schema does not reflect the advertised multimodal capability. Fix: Add image_url (and any other applicable modalities such as video_url) as content part options in messages[\*].content.items, matching the richer schema used by other vision models like glm-5.2.json.

Conventions

No convention issues found.

Style Guide Review

No style-guide issues found.

Commands

Only codeowners can run commands. Post a comment with the command to trigger it.

Command Description
/review Runs a review now. Incremental if a prior review exists, full if not.
/full-review Re-reviews the entire PR diff from scratch, ignoring incremental history. Useful after a rebase, when you want a fresh review, or if the bot gets out of sync and reports issues that no longer exist.
/ignore-review-limit Permanently lifts the 2-review automatic limit for this PR. Future pushes will trigger reviews as normal.
/disable-auto-review Stops automatic reviews from triggering on future pushes to this PR. Codeowners can still run /review or /full-review manually.
/rebase Rebases the PR branch against production. On conflict, attempts to resolve automatically using AI. Stops with an explanation if confidence is not high enough.
@cloudflare-workers-and-pages

cloudflare-workers-and-pages Bot commented Aug 26, 2026

Copy link
Copy Markdown

🚀 Deploying Preview to Cloudflare 🚀

Preview URL: https://mchen-glm-5-3-flash.previews.developers.cloudflare.com (commit 87adfe8)

This URL reflects your latest Preview deployment

Preview Deployments by commit

Status Deployment URL Commit Updated (UTC) See this deployment's details
  • Build: Success ✅
  • Deployment: Success ✅

View logs ↗
https://6402ff2f.previews.developers.cloudflare.com 87adfe8 2026-08-26T19:34:47.951Z Visit the dashboard ↗
  • Build: Success ✅
  • Deployment: Success ✅

View logs ↗
https://602c43d0.previews.developers.cloudflare.com 8c591e7 2026-08-26T15:31:39.972Z Visit the dashboard ↗
@github-actions

Copy link
Copy Markdown
Contributor

This pull request requires reviews from CODEOWNERS as it changes files that match the following patterns:

Pattern Owners
/src/content/changelog/ @cloudflare/pm-changelogs, @cloudflare/product-owners
/src/content/docs/workers-ai/ @rita3ko, @craigsdennis, @mchenco, @zeke, @superhighfives, @shridhar-cf, @mattrothenberg, @ethulia, @aninibread, @kflansburg, @cloudflare/product-owners
/src/content/workers-ai-models/ @craigsdennis, @mchenco, @superhighfives, @shridhar-cf, @ethulia, @kflansburg, @cloudflare/product-owners, @kodster28
@mchenco
mchenco merged commit 266475c into production Aug 26, 2026
18 checks passed
@mchenco
mchenco deleted the mchen/glm-5.3-flash branch August 26, 2026 20:02
rpots pushed a commit that referenced this pull request Aug 28, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

3 participants