openai-sdk changedcli-sdks-libraries/libraries/openai-sdk
Nearest release: v2.1.321, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+30added
Lines−28removed
From line
5
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits22to this page, all time
The whole hunk
from line 5, old and new numbered
/
from line 5
55featureMetadata:
66 status: stable
77 supportedModels:
8 - claude-fable-5-2
9 - claude-mythos-5-2
810 - claude-fable-5-1
911 - claude-mythos-5-1
1012 - claude-fable-5
from line 317
315317
316318#### Simple fields
317319
318| Field | Support status |
319| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
320| `model` | Use Claude model names |
321| `max_tokens` | Fully supported |
322| `max_completion_tokens` | Fully supported |
323| `stream` | Fully supported |
324| `stream_options` | Fully supported |
325| `top_p` | Passed through to the model. Claude 4.7 and later models and Claude Mythos Preview return a 400 error for any value other than `0.99`, the default, so omit it. A request that sets both `temperature` and `top_p` also returns a 400 error. See [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). |
326| `parallel_tool_calls` | Fully supported |
327| `tool_choice` | Supported with limits. `"required"` and a named function force a tool call. Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 don’t support forced tool use and return a 400 error, so use `"auto"` on those models. See [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use). |
328| `stop` | All non-whitespace stop sequences work |
329| `temperature` | Between 0 and 1 (inclusive). Values greater than 1 are capped at 1. On Claude 4.7 and later models and Claude Mythos Preview, any value below 1 returns a 400 error, so omit it. See [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). |
330| `n` | Must be exactly 1. Any other value returns a 400 error. |
331| `response_format` | Supported with limits. Only `json_schema` with `strict: true` is accepted, and the structured outputs [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations) apply. Any other value, including `json_object` and `text`, returns a 400 error. |
332| `logprobs` | Ignored |
333| `metadata` | Ignored |
334| `prediction` | Ignored |
335| `presence_penalty` | Ignored |
336| `frequency_penalty` | Ignored |
337| `seed` | Ignored |
338| `service_tier` | Ignored |
339| `audio` | Ignored |
340| `logit_bias` | Ignored |
341| `store` | Ignored |
342| `user` | Ignored |
343| `modalities` | Ignored |
344| `top_logprobs` | Ignored |
345| `reasoning_effort` | Ignored |
320| Field | Support status |
321| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
322| `model` | Use Claude model names |
323| `max_tokens` | Fully supported |
324| `max_completion_tokens` | Fully supported |
325| `stream` | Fully supported |
326| `stream_options` | Fully supported |
327| `top_p` | Passed through to the model. Claude 4.7 and later models and Claude Mythos Preview return a 400 error for any value other than `0.99`, the default, so omit it. A request that sets both `temperature` and `top_p` also returns a 400 error. See [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). |
328| `parallel_tool_calls` | Fully supported |
329| `tool_choice` | Supported with limits. `"required"` and a named function force a tool call. Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 don’t support forced tool use and return a 400 error, so use `"auto"` on those models. See [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use). |
330| `stop` | All non-whitespace stop sequences work |
331| `temperature` | Between 0 and 1 (inclusive). Values greater than 1 are capped at 1. On Claude 4.7 and later models and Claude Mythos Preview, any value below 1 returns a 400 error, so omit it. See [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). |
332| `n` | Must be exactly 1. Any other value returns a 400 error. |
333| `response_format` | Supported with limits. Only `json_schema` with `strict: true` is accepted, and the structured outputs [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations) apply. Any other value, including `json_object` and `text`, returns a 400 error. |
334| `logprobs` | Ignored |
335| `metadata` | Ignored |
336| `prediction` | Ignored |
337| `presence_penalty` | Ignored |
338| `frequency_penalty` | Ignored |
339| `seed` | Ignored |
340| `service_tier` | Ignored |
341| `audio` | Ignored |
342| `logit_bias` | Ignored |
343| `store` | Ignored |
344| `user` | Ignored |
345| `modalities` | Ignored |
346| `top_logprobs` | Ignored |
347| `reasoning_effort` | Ignored |
346348
347349#### `tools` / `functions` fields
348350
No line in this hunk matches that.