What this error means
openai.NotFoundError: Error code: 404 - Resource not found — Azure OpenAI preview api-version builds incorrect URL with duplicated /openai/deployments/ path is a OpenAI API failure pattern reported for developers trying to fix azure openai sdk build_request adding /deployments/{model} to base_url that already contains /openai/v1/, producing malformed urls like /openai/v1/openai/deployments/gpt-5-chat/chat/completions when using preview api-version. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Specific error pattern discovered while fetching openai-python issue list. Root cause: Azure changed preview API version to use base_url approach, but SDK still appends /deployments/{model} regardless of whether base_url already includes the path prefix. Causes 404 on gpt-5 and other newer models. Requires conditional logic to skip appending when /deployments already present in base_url path.
Common causes
- Specific error pattern discovered while fetching openai-python issue list. Root cause: Azure changed preview API version to use base_url approach, but SDK still appends /deployments/{model} regardless of whether base_url already includes the path prefix. Causes 404 on gpt-5 and other newer models. Requires conditional logic to skip appending when /deployments already present in base_url path.
Quick fixes
- Confirm the exact error signature matches
openai.NotFoundError: Error code: 404 - Resource not found — Azure OpenAI preview api-version builds incorrect URL with duplicated /openai/deployments/ path. - Check the OpenAI API account, local tool state, and provider configuration involved in the failing workflow.
- Check the build output, project root, and deployment platform configuration before redeploying.
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.