What this error means
anthropic.claude-3-haiku-20240307-v1:0 with on-demand throughput isn't supported. Retry your request with the ID or ARN of an inference profile is a Anthropic API failure pattern reported for developers trying to fix aws bedrock anthropic claude haiku on-demand throughput not supported error. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
AWS Bedrock InvokeModel throws ValidationException: 'Invocation of model ID anthropic.claude-3-haiku-20240307-v1:0 with on-demand throughput isn't supported.' Must use inference profile ARN instead. Migration guide needed.
Common causes
- Developers migrating to AWS Bedrock for Claude models get ValidationException because model ID format changed; requires inference profile ARN instead of model ID
- AWS Bedrock InvokeModel throws ValidationException: 'Invocation of model ID anthropic.claude-3-haiku-20240307-v1:0 with on-demand throughput isn't supported.' Must use inference profile ARN instead. Migration guide needed.
Quick fixes
- Confirm the exact error signature matches
anthropic.claude-3-haiku-20240307-v1:0 with on-demand throughput isn't supported. Retry your request with the ID or ARN of an inference profile. - Check the Anthropic API account, local tool state, and provider configuration involved in the failing workflow.
- 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
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- 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.