Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Cohere API error

Cohere API 404 Not Found: what it means and how to fix it

Error message
404 Not Found

Retry? Not statedLast verified 1 documented fix1 source

What it means

404 responses are sent when the requested resource is not found. This can happen when the model, dataset, or connector ID is incorrect, or when the resource has been deleted.

Causes

  • Incorrect model ID or no access to the model ("model 'xyz' not found, make sure the correct model ID was used and that you have access to the model.")
  • Incorrect dataset or connector ID
  • Fine-tuned model not found
  • Resource has been deleted

How to fix it

  1. Fix 1.

    Make sure the correct model, dataset, or connector ID was used and that you have access to the resource.

More Cohere API errors

HTTP 404 at other providers

Compare 404 across providers

FAQ

What does the Cohere API error "404 Not Found" mean?

404 responses are sent when the requested resource is not found. This can happen when the model, dataset, or connector ID is incorrect, or when the resource has been deleted.

How do I fix Cohere API "404 Not Found"?

Make sure the correct model, dataset, or connector ID was used and that you have access to the resource.

Should I retry Cohere API "404 Not Found"?

Not stated. The official docs do not say whether this error is retryable.

Which other AI APIs return HTTP 404?

Per their official error docs: Amazon Bedrock (404 ResourceNotFoundException; 404 FTUFormNotFilled), Anthropic API (404 not_found_error), Azure OpenAI (404 Not Found), Gemini API (404 not_found; 404 model_not_found; 404 NOT_FOUND), Groq API (404 Not Found), Mistral API (404 Not found), OpenAI API (404 NotFoundError), OpenRouter (404 image_not_found; 404 not_found), Vertex AI (404 NOT_FOUND), xAI API (404 Not Found).

Sources

Last verified against 1 source: Cohere API's official docs and official SDK repositories.

Newsletter

Know when the APIs change

One email per week. New model releases, API changes, what broke, and how developers are working around it.