[AI Gateway] Add Qwen and LTX model catalog entries

[shridhar-cf]

Summary

Adds five AI Gateway model catalog entries for Qwen 3.7 Max, Qwen 3.7 Plus, Qwen 3.8 Max, Qwen Image 3.0 Pro, and LTX 2.5 Fast.

Documentation checklist

• The change adheres to the documentation style guide.

[cloudflare-docs-bot]

Review

🚨 1 critical, ⚠️ 4 warnings found in commit 3318e38.

👉 Fix in your agent 👈

Fix the following review findings in PR #32677 (https://github.com/cloudflare/cloudflare-docs/pull/32677).

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

### Critical (1)

#### CR-9eaf3a686e97 · Non-existent or unverified model
- **File:** `src/content/catalog-models/alibaba-qwen3.7-max.json` line 4
- **Issue:** The model name 'Qwen 3.7 Max' and model_id 'alibaba/qwen3.7-max' do not correspond to any known model in Alibaba's Qwen family. Known models include qwen-max, qwen-plus, qwen-turbo, qwen2.5-max, qwen3, etc., but there is no recognized 'Qwen 3.7' series.
- **Fix:** Verify the exact model ID and name with Alibaba's published model catalog before merging; if this is a typo, correct it to the real model name/ID.

### Warnings (4)

#### CR-0240056f2823 · Inconsistent context length
- **File:** `src/content/catalog-models/alibaba-qwen3.7-max.json` line 13
- **Issue:** context_length is null on line 13, but metadata on line 54 claims a 'Context Window' of '1M tokens'. These two fields contradict each other.
- **Fix:** Set context_length to the actual numeric value if the context window is known, or remove the metadata claim if it is not verified.

#### CR-85a3ec5be621 · Likely unsupported request format
- **File:** `src/content/catalog-models/alibaba-qwen3.7-max.json` line 58
- **Issue:** request_formats lists 'responses' on line 58. The responses API is a newer OpenAI-specific format, and there is no indication that Alibaba's DashScope endpoint supports it.
- **Fix:** Remove 'responses' from request_formats unless the provider explicitly documents support for this API format.

#### CR-5c9fd7009a55 · Audio schema copied into text model
- **File:** `src/content/catalog-models/alibaba-qwen3.7-max.json` line 152
- **Issue:** The input schema starting at line 152 includes 'modalities' and 'audio' fields with OpenAI voice/format enums, and the output schema at line 321 includes audio output fields. This model is listed as a 'Text Generation' task and described as a text/code/reasoning model, so audio-specific schema fields are likely erroneous.
- **Fix:** Remove the audio and modalities fields from both input and output schemas unless this model genuinely supports audio input/output.

#### CR-03ecd35ea130 · Schema claims unsupported audio capability
- **File:** `src/content/catalog-models/alibaba-qwen3.7-plus.json` line 152
- **Issue:** The model description only advertises text, image, and video understanding, with no mention of audio. However, the input schema declares `modalities: ["text", "audio"]` and an `audio` object containing OpenAI-specific voice names (`alloy`, `ash`, `ballad`, etc.) and formats, and the output schema at line 321 also declares `audio` output fields.
- **Fix:** Remove the `modalities`, `audio`, and output-schema `audio` properties unless Qwen 3.7 Plus actually supports audio through DashScope; if audio is supported, use the correct DashScope voice/format identifiers rather than OpenAI-specific ones.

Code Review

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

Critical (1)

File

Issue

catalog-models/alibaba-qwen3.7-max.json line 4

Non-existent or unverified model — The model name 'Qwen 3.7 Max' and model_id 'alibaba/qwen3.7-max' do not correspond to any known model in Alibaba's Qwen family. Known models include qwen-max, qwen-plus, qwen-turbo, qwen2.5-max, qwen3, etc., but there is no recognized 'Qwen 3.7' series. Fix: Verify the exact model ID and name with Alibaba's published model catalog before merging; if this is a typo, correct it to the real model name/ID.

Warnings (4)

File	Issue
catalog-models/alibaba-qwen3.7-max.json line 13	Inconsistent context length — context_length is null on line 13, but metadata on line 54 claims a 'Context Window' of '1M tokens'. These two fields contradict each other. Fix: Set context_length to the actual numeric value if the context window is known, or remove the metadata claim if it is not verified.
catalog-models/alibaba-qwen3.7-max.json line 58	Likely unsupported request format — request_formats lists 'responses' on line 58. The responses API is a newer OpenAI-specific format, and there is no indication that Alibaba's DashScope endpoint supports it. Fix: Remove 'responses' from request_formats unless the provider explicitly documents support for this API format.
catalog-models/alibaba-qwen3.7-max.json line 152	Audio schema copied into text model — The input schema starting at line 152 includes 'modalities' and 'audio' fields with OpenAI voice/format enums, and the output schema at line 321 includes audio output fields. This model is listed as a 'Text Generation' task and described as a text/code/reasoning model, so audio-specific schema fields are likely erroneous. Fix: Remove the audio and modalities fields from both input and output schemas unless this model genuinely supports audio input/output.
catalog-models/alibaba-qwen3.7-plus.json line 152	Schema claims unsupported audio capability — The model description only advertises text, image, and video understanding, with no mention of audio. However, the input schema declares modalities: ["text", "audio"] and an audio object containing OpenAI-specific voice names (alloy, ash, ballad, etc.) and formats, and the output schema at line 321 also declares audio output fields. Fix: Remove the modalities, audio, and output-schema audio properties unless Qwen 3.7 Plus actually supports audio through DashScope; if audio is supported, use the correct DashScope voice/format identifiers rather than OpenAI-specific ones.

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.