update models catalog in docs by ethulia · Pull Request #30998 · cloudflare/cloudflare-docs

ethulia · 2026-05-21T17:45:33Z

Summary

Screenshots (optional)

Documentation checklist

Is there a changelog entry (guidelines)? If you don't add one for something awesome and new (however small) — how will our customers find out? Changelogs are automatically posted to RSS feeds, the Discord, and X.
The change adheres to the documentation style guide.
If a larger change - such as adding a new page- an issue has been opened in relation to any incorrect or out of date information that this PR fixes.
Files which have changed name or location have been allocated redirects.

github-actions · 2026-05-21T17:46:41Z

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

Pattern	Owners
`/src/content/catalog-models/`	`@abhishekkankani`, `@palashgo`, `@thebongy`, `@roerohan`, `@kathayl`, `@mchenco`, `@zeke`, `@superhighfives`, `@bfirsh`, `@mattrothenberg`, `@ethulia`, `@cloudflare/content-engineering`, `@cloudflare/product-owners`

ask-bonk

PR description is empty. Please add a brief summary of what changed (new models, removed example outputs, added curl snippets).

HIGH — New curl snippets systematically mismatch their example input blocks across text-generation models:

max_completion_tokens: 8192 is hardcoded in many curl snippets while the example input uses max_tokens: 500 or 300.
temperature is present in input and TypeScript but omitted from many curl snippets.

See inline comments on representative examples.

MEDIUM — openai-gpt-5.4-pro.json still contains output/raw_response objects while the rest of the OpenAI catalog was stripped of them in this PR. If the intent was a bulk cleanup, this file may have been missed.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-5\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful coding assistant specializing in Python.\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"How do I read a JSON file in Python?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


Missing temperature: 0.3 in the curl snippet — it is present in the input block above.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-5\",\n  \"max_completion_tokens\": 8192,\n  \"messages\": [\n    {\n      \"content\": \"I need help planning a road trip from San Francisco to Los Angeles.\",\n      \"role\": \"user\"\n    },\n    {\n      \"content\": \"I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?\",\n      \"role\": \"assistant\"\n    },\n    {\n      \"content\": \"Yes, what are some good places to stop?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


The curl snippet uses max_completion_tokens: 8192, but the example input specifies max_tokens: 500.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-5\",\n  \"max_completion_tokens\": 8192,\n  \"messages\": [\n    {\n      \"content\": \"Write a short story opening about a detective finding an unusual clue.\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


The curl snippet uses max_completion_tokens: 8192, but the example input specifies max_tokens: 300 and temperature: 0.8.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"alibaba/qwen3.5-397b-a17b\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful coding assistant specializing in Python.\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"How do I read a JSON file in Python?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


Missing temperature: 0.3 in the curl snippet — it is present in the input block above.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"alibaba/qwen3.5-397b-a17b\",\n  \"max_completion_tokens\": 8192,\n  \"messages\": [\n    {\n      \"content\": \"I need help planning a road trip from San Francisco to Los Angeles.\",\n      \"role\": \"user\"\n    },\n    {\n      \"content\": \"I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?\",\n      \"role\": \"assistant\"\n    },\n    {\n      \"content\": \"Yes, what are some good places to stop?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


The curl snippet uses max_completion_tokens: 8192, but the example input specifies max_tokens: 500.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"alibaba/qwen3.5-397b-a17b\",\n  \"max_completion_tokens\": 8192,\n  \"messages\": [\n    {\n      \"content\": \"Write a short story opening about a detective finding an unusual clue.\",\n      \"role\": \"user\"\n    }\n  ]\n}'"


The curl snippet uses max_completion_tokens: 8192, but the example input specifies max_tokens: 300 and temperature: 0.8.

ask-bonk · 2026-05-21T17:58:12Z

+				{
+					"label": "curl",
+					"language": "bash",
+					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"anthropic/claude-opus-4.7\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"How do I read a JSON file in Python?\",\n      \"role\": \"user\"\n    }\n  ],\n  \"system\": \"You are a helpful coding assistant specializing in Python.\"\n}'"


Missing temperature: 0.3 in the curl snippet — it is present in the input block above.

ask-bonk · 2026-05-21T17:58:37Z

Labels applied: documentation, triage

What this PR changes

This is a bulk update of 64 catalog model JSON files in src/content/catalog-models/:

5 new models added: bytedance/seedance-2.0, bytedance/seedance-2.0-fast, recraft/recraftv3, xai/grok-imagine-image, xai/grok-imagine-video.
61 existing models updated: example output and raw_response objects were removed (reducing the diff by ~63k lines), curl code snippets were added alongside existing TypeScript snippets, and some example parameters were adjusted (e.g. max_completion_tokens → max_tokens).
A few metadata tweaks (e.g. keySource updated for openai/gpt-image-2, created_at timestamps refreshed).

pnpm run check passes cleanly. Prettier formatting issues in these JSON files are pre-existing and not introduced by this PR.

Issues flagged

HIGH — Empty PR description
The PR body is just the template with no summary. For a 64-file change, a brief description of intent (e.g. “sync with latest catalog export, strip verbose API responses, add curl snippets”) would help reviewers.

HIGH — curl snippets systematically mismatch example parameters
New curl examples across text-generation models have two recurring errors:

Hardcoded max_completion_tokens: 8192 in curl while the example input specifies max_tokens: 500 or 300. This affects OpenAI and Alibaba models.
temperature omitted from curl snippets even though it is present in the input block and the TypeScript snippet.

I posted 7 inline review comments on representative files (openai-gpt-5.json, alibaba-qwen3.5-397b-a17b.json, anthropic-claude-opus-4.7.json) highlighting these mismatches. The author should regenerate the snippets so that curl matches the input parameters.

MEDIUM — Possible bulk-cleanup omission
openai-gpt-5.4-pro.json still contains large output/raw_response objects, while the rest of the OpenAI catalog was stripped of them. If the intent was a uniform cleanup, this file appears to have been missed.

LOW — No changelog needed
Because this PR only updates JSON data files (not MDX docs pages), a changelog entry is not strictly required.

github run

github-actions · 2026-05-21T18:08:20Z

Preview URL: https://e90f9c56.preview.developers.cloudflare.com
Preview Branch URL: https://ml-update-models.preview.developers.cloudflare.com

update models catalog in docs

e90f9c5

github-actions Bot added the size/xl label May 21, 2026

github-actions Bot assigned kathayl, mattrothenberg, mchenco, palashgo, roerohan, superhighfives, thebongy and zeke May 21, 2026

ethulia marked this pull request as ready for review May 21, 2026 17:46

ethulia requested review from a team, kathayl, mattrothenberg, mchenco, palashgo, roerohan, superhighfives and zeke as code owners May 21, 2026 17:46

ask-bonk Bot added documentation Documentation edits triage Waiting for a docs team review. labels May 21, 2026

mchenco approved these changes May 21, 2026

View reviewed changes

ask-bonk Bot reviewed May 21, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

update models catalog in docs#30998

update models catalog in docs#30998
ethulia wants to merge 1 commit into
productionfrom
ml/update-models

ethulia commented May 21, 2026

Uh oh!

github-actions Bot commented May 21, 2026

Uh oh!

ask-bonk Bot left a comment

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot May 21, 2026

Uh oh!

ask-bonk Bot commented May 21, 2026

Uh oh!

github-actions Bot commented May 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

9 participants

Conversation

ethulia commented May 21, 2026

Summary

Screenshots (optional)

Documentation checklist

Uh oh!

github-actions Bot commented May 21, 2026

Uh oh!

ask-bonk Bot left a comment

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot May 21, 2026

Choose a reason for hiding this comment

Uh oh!

ask-bonk Bot commented May 21, 2026

What this PR changes

Issues flagged

Uh oh!

github-actions Bot commented May 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

9 participants