What this error means

Claude API 400 Bad Request — service_tier rewritten to deprecated 'speed' field is a Anthropic API failure pattern reported for developers trying to fix anthropic api 400 error when using service_tier through portkey gateway. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Official Portkey-AI/gateway GitHub issue. Portkey gateway translates OpenAI-style service_tier to Anthropic's deprecated 'speed' field per docs-core #869, but Anthropic's Messages API no longer accepts 'speed' — it uses service_tier natively. Result: any request with service_tier set returns HTTP 400. Priority Tier unreachable through gateway.

Common causes

  • Developers using Portkey as an LLM gateway to route requests to the Anthropic API receive HTTP 400 errors because Portkey incorrectly translates OpenAI-style service_tier to Anthropic's deprecated 'speed' field. This makes Priority Tier (fast mode) completely unreachable through the gateway, blocking production workloads that depend on reduced latency.
  • Official Portkey-AI/gateway GitHub issue. Portkey gateway translates OpenAI-style service_tier to Anthropic's deprecated 'speed' field per docs-core #869, but Anthropic's Messages API no longer accepts 'speed' — it uses service_tier natively. Result: any request with service_tier set returns HTTP 400. Priority Tier unreachable through gateway.

Quick fixes

  1. Confirm the exact error signature matches Claude API 400 Bad Request — service_tier rewritten to deprecated 'speed' field.
  2. Check the Anthropic API account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

  • Verify the command, editor, extension, or API client that produced the error.
  • Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
  • Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

  • Keep provider/tool configuration documented.
  • Record non-secret diagnostics such as tool version, provider name, model name, and command path.
  • Add a lightweight check before CI or production workflows depend on the tool.