Claude hosted models and the native Messages API. Compare tool loops, streaming and thinking controls on the actual endpoint.
Official documentation ↗The September 2026 Sonnet release, announced across the Claude API and supported cloud platforms.
Use the exact Claude endpoint and current model documentation for limits and prices. Cache-read pricing changed on October 7, 2026; a launch-era estimate can be stale.
An October 2026 Claude release aimed at high-volume, latency-sensitive work, with adaptive thinking.
Migration from Haiku 4.5 needs attention: manual budget_tokens thinking, sampling parameters and assistant prefill can return 400 errors on Haiku 5.5.
A September 2026 Claude release for long-running agentic coding and knowledge work.
Always-on adaptive thinking affects output usage and latency. Announced model limits and standard prices do not describe every cloud platform or inference configuration.
A hosted Claude model introduced for coding and agent workflows.
Native Messages requests differ from OpenAI Chat Completions. A compatibility layer must map tool and streaming behavior correctly.
The publisher identifies the model family or checkpoint. An inference operator selects a runtime, quantization and service configuration. The API endpoint defines the accepted request shape and operational limits. Compare all three when planning a migration.
Official release notes can announce previews, general availability, retirement and alias changes. A model appearing in an API list is an observation of access, not necessarily a new public release.
Open the release radar →