claude-fable-5
Creates a model response for the given chat conversation. Adaptive thinking is always on — no configuration needed. May return finish_reason: "refusal" when safety classifiers decline a request; use fallbacks for automatic retry on other models.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Model ID
claude-fable-5 "claude-fable-5"
A list of messages comprising the conversation so far.
1[{ "role": "user", "content": "Hello!" }]The maximum number of tokens to generate.
1 <= x <= 8192Sampling temperature. Higher values make output more random.
0 <= x <= 21
Penalizes repeated tokens based on their frequency in the text so far.
-2 <= x <= 2Penalizes tokens that have already appeared in the text.
-2 <= x <= 2If true, stream partial message deltas using SSE.
Sequences where the model will stop generating further tokens.