Try Claude Sonnet 5.5 in the Workbench
Run this model interactively, tune parameters, and compare outputs.
claude-sonnet-5-5
Claude Sonnet 5.5 is Anthropic’s Sonnet-tier Multimodal LLM for everyday coding, agent tasks, and knowledge work, and the fastest Sonnet model to date. It is a clear upgrade over Claude Sonnet 5, generating output more than 30% faster while typically needing far fewer tokens per task, at the same per-token pricing.
Adaptive thinking is steered by the effort parameter (defaulting to high), and the model ships with a native 1M-token context window and up to 128k output tokens, with a reliable knowledge cutoff of June 2026. Migrating from Sonnet 5 requires attention to breaking changes: forced tool use returns an error, thinking blocks are readable only by the model that produced them, and text between tool calls is returned in thinking blocks. It is the first Sonnet model to launch with the cyber safeguards developed for Anthropic’s most capable models.
Example request
- Minimal
- Basic parameters
Fetch model details
The models endpoint returns the full model object, including itsjson_request_schema.