Microsoft Foundry / Azure OpenAI · model
Cohere-rerank-v3.5 deprecation: shutdown date & replacement
- Provider
- Microsoft Foundry / Azure OpenAI
- Type
- model
- Announced
- —
- Shutdown
- Replacement
Cohere-rerank-v4.0-pro,Cohere-rerank-v4.0-fast- Source
- Official Microsoft Foundry / Azure OpenAI notice
Azure lifecycle stage: Retired. Version 1.
How to migrate off Cohere-rerank-v3.5
- Find every place that references it:
grep -rn --exclude-dir={node_modules,.git,dist} "Cohere-rerank-v3.5" . - Replace the model ID:
- model: "Cohere-rerank-v3.5" + model: "Cohere-rerank-v4.0-pro" - Re-run your evals or a sample of real prompts — output style, token usage and pricing can change between models.
- Check config outside code too: environment variables, feature flags, prompt-management tools, and fine-tuned model references.
- Deploy before May 14, 2026, and add the CI scanner so it cannot come back.
Questions
Is Cohere-rerank-v3.5 deprecated?
Yes. Microsoft Foundry / Azure OpenAI has deprecated Cohere-rerank-v3.5. It was shut down on May 14, 2026.
When does Cohere-rerank-v3.5 shut down?
May 14, 2026, according to Microsoft Foundry / Azure OpenAI's official deprecation notice.
What should I use instead of Cohere-rerank-v3.5?
Microsoft Foundry / Azure OpenAI recommends Cohere-rerank-v4.0-pro, Cohere-rerank-v4.0-fast. Switch the model ID and re-test your prompts, since outputs, pricing and limits can differ.
What happens to requests to Cohere-rerank-v3.5 after the shutdown?
Requests using the retired model ID fail with an error, so any code still calling it breaks. Update and deploy before the shutdown date.