Skip to content

Claude Fable 5.5

POST/v1/messages

Claude Fable 5.5 is the expected successor to Claude Fable 5.1, Anthropic's tier above Opus for repository-scale coding, long-running agents and high-stakes review. Anthropic has not officially released it yet; specifications, pricing and API availability will be confirmed at launch.

Request body

Parameters supported by this model. Values, defaults, and limits are read from the model registry.

stringmodelrequired

Model identifier. Set to anthropic/claude-fable-5.5.

Default: anthropic/claude-fable-5.5

array<object>messagesrequired

Conversation messages in system, user, or assistant order.

Optional<integer>max_tokens

Maximum number of tokens the model may generate in the response.

Maximum: 128000

Optional<number>temperature

Sampling temperature. Lower values are more deterministic; higher values are more creative.

Range: 0 to 2

Default: 1

Optional<boolean>stream

When true, returns incremental Server-Sent Events instead of one completed response.

Default: false

Optional<array>tools

Tool definitions that the model may call during the response.

Optional<string>tool_choice

Controls whether the model may call a tool and, when supported, which tool it must call.

Optional<object>response_format

Controls the response format, including JSON mode or structured JSON output when supported.

Optional<array<string>>stop

Sequences that stop generation when the model produces one of them.

Response Schema

Fields returned by this model API response.

array<object>contentrequired

Assistant content blocks.

stringidrequired

Unique message identifier.

stringmodelrequired

Model that generated the message.

stringrolerequired

Message role returned by the assistant.

Optional<string>stop_reason

Reason generation stopped.

stringtyperequired

Response object type.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: chat, vision, reasoning, structured_output, function_calling, coming-soon

stringexecution_moderequired

Execution mode declared by the model registry.

Default: sync