Skip to content

[Workers AI] Clarify OpenAI Chat Completions vs Responses API support#32116

Open
KastanDay wants to merge 2 commits into
cloudflare:productionfrom
KastanDay:kastan/workeres-ai-responses-api
Open

[Workers AI] Clarify OpenAI Chat Completions vs Responses API support#32116
KastanDay wants to merge 2 commits into
cloudflare:productionfrom
KastanDay:kastan/workeres-ai-responses-api

Conversation

@KastanDay

@KastanDay KastanDay commented Jul 16, 2026

Copy link
Copy Markdown

Note: I'm a recent Cloudflare hire on the Workers AI team 👋 ☁️🧡

Summary

Update slightly misleading docs; clarify that Workers AI is 99% Chat Completions, with the exception of GPT-OSS[20b,120b] that are the only ones that support the Responses API, and only non-streaming.

  • clarify that most Workers AI text generation models use the Chat Completions endpoint
  • document non-streaming Responses API support for GPT-OSS 120B and 20B

Validation

  • astro check (0 errors)
  • Prettier check for both modified MDX files
  • local page preview

@github-actions github-actions Bot added product:workers-ai Workers AI: https://developers.cloudflare.com/workers-ai/ size/s labels Jul 16, 2026
@cloudflare-docs-bot

cloudflare-docs-bot Bot commented Jul 16, 2026

Copy link
Copy Markdown
Contributor

Review

💡 3 suggestions found in commit 7216490.

Fix in your agent
Fix the following review findings in PR #32116 (https://github.com/cloudflare/cloudflare-docs/pull/32116).

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, fix all legitimate findings. For any you decide to skip,
post a comment on this PR with the finding ID and your reasoning.

---

## Style Guide Review

### Suggestions (3)

#### SG-8f6e0ca937ed · Passive voice
- **File:** `src/content/partials/workers-ai/openai-compatibility.mdx` line 5
- **Issue:** The Responses API (`/v1/responses`) is available only for GPT-OSS models
- **Fix:** Rewrite in active voice: Only GPT-OSS models support the Responses API (`/v1/responses`)

#### SG-f68833f0df2b · Avoid passive voice
- **File:** `src/content/docs/workers-ai/configuration/open-ai-compatibility.mdx` line 62
- **Issue:** Line uses passive voice (`is supported only by...`, `is supported`).
- **Fix:** Rewrite in active voice, e.g., `Only the ... models support the Responses API. Responses requests must be non-streaming; use stream: false.`

#### SG-dd357934728e · Use TypeScriptExample component for JavaScript examples
- **File:** `src/content/docs/workers-ai/configuration/open-ai-compatibility.mdx` line 64
- **Issue:** Raw ` ```js ` fenced block used for a code example in a docs MDX file.
- **Fix:** Replace the ` ```js ` block with the `<TypeScriptExample>` component.

Code Review

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

No code review issues found.

Conventions

No convention issues found.

Style Guide Review

Suggestions (3)
File Issue
partials/workers-ai/openai-compatibility.mdx line 5 Passive voice — The Responses API (/v1/responses) is available only for GPT-OSS models Fix: Rewrite in active voice: Only GPT-OSS models support the Responses API (/v1/responses)
workers-ai/configuration/open-ai-compatibility.mdx line 62 Avoid passive voice — Line uses passive voice (is supported only by..., is supported). Fix: Rewrite in active voice, e.g., Only the ... models support the Responses API. Responses requests must be non-streaming; use stream: false.
workers-ai/configuration/open-ai-compatibility.mdx line 64 Use TypeScriptExample component for JavaScript examples — Raw ```js fenced block used for a code example in a docs MDX file. Fix: Replace the ```js block with the <TypeScriptExample> component.
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.

@KastanDay KastanDay changed the title [Workers AI] Clarify OpenAI-compatible API support [Workers AI] Clarify OpenAI Chat Completions vs Responses API support Jul 16, 2026
@KastanDay

Copy link
Copy Markdown
Author

Looks ready to merge from my POV. Thanks team.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

product:workers-ai Workers AI: https://developers.cloudflare.com/workers-ai/ size/s

Projects

None yet

Development

Successfully merging this pull request may close these issues.

10 participants