# deepseek-r1-distill-llama-70b

Calls to the model deepseek-r1-distill-llama-70b on Groq stopped working on October 2, 2025.

## The error Groq returns once deepseek-r1-distill-llama-70b is gone

HTTP 404

```json
{"error":{"message":"The model `deepseek-r1-distill-llama-70b` does not exist or you do not have access to it.","type":"invalid_request_error","code":"model_not_found"}}
```

## What to use instead

Move to openai/gpt-oss-120b. llama-3.3-70b-versatile, also named, stopped working on 2026-08-16.

- API: Groq (api.groq.com)
- Model: deepseek-r1-distill-llama-70b
- Released: January 1, 2025 (models.dev)
- Kind: Model retirement
- Takes effect: October 2, 2025
- Calls after that day: fail
- Calls it hits: `model deepseek-r1-distill-llama-70b`
- Source: [Deprecations page](https://console.groq.com/docs/deprecations)
- Verified: November 6, 2026, against Groq's own pages
- Page: https://www.okapi.bot/models/groq/deepseek-r1-distill-llama-70b/

## Groq's words

> Deprecated Model: deepseek-r1-distill-llama-70b; Shutdown Date: 10/02/25; Recommended Replacement Model ID: llama-3.3-70b-versatile or openai/gpt-oss-120b

Okapi finds the calls this change hits in your repo and opens the pull request with the fix: https://github.com/apps/okapi-agent