Claude Sonnet 4.5
/v1/messagesClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.
Request body
Parameters supported by this model. Values, defaults, and limits are read from the model registry.
Model identifier. Set to anthropic/claude-sonnet-4.5.
Default: anthropic/claude-sonnet-4.5
Conversation messages in system, user, or assistant order.
Maximum number of tokens the model may generate in the response.
Range: −∞ to 64000
Sampling temperature. Lower values are more deterministic; higher values are more creative.
Range: 0 to 2
Default: 1
Nucleus sampling threshold. Use this or temperature, but usually not both.
Range: 0 to 1
When true, returns incremental Server-Sent Events instead of one completed response.
Default: false
Tool definitions that the model may call during the response.
Controls whether the model may call a tool and, when supported, which tool it must call.
Controls the response format, including JSON mode or structured JSON output when supported.
Sequences that stop generation when the model produces one of them.
Request parameter supported by this model.
Range: 0 to ∞
Response Schema
Fields returned by this model API response.
Assistant content blocks.
Unique message identifier.
Model that generated the message.
Message role returned by the assistant.
Reason generation stopped.
Response object type.
Model capabilities
Capabilities declared by the model registry.
Default: chat, vision, reasoning, structured_output, function_calling
Maximum context window accepted by this model.
Default: 1000000 tokens
Execution mode declared by the model registry.
Default: sync

