Groq
deepseek-r1-distill-llama-70b model retirement
Stopped workingSubscribe to GroqShare
Calls to the model deepseek-r1-distill-llama-70b on Groq stopped working on October 2, 2025.
The error you get
What Groq answers a call to deepseek-r1-distill-llama-70b once the model is gone, as recorded from real responses:
{"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 of deepseek-r1-distill-llama-70b
Move to openai/gpt-oss-120b. llama-3.3-70b-versatile, also named, stopped working on 2026-08-16.
In 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
Facts
- 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
- Source
- Deprecations page
- Last updated
- Verified
- , against Groq's own pages
Questions
When does deepseek-r1-distill-llama-70b shut down?
Calls to the model deepseek-r1-distill-llama-70b on Groq stopped working on October 2, 2025.
What happens to calls after October 2, 2025?
They have failed since October 2, 2025.
What error does deepseek-r1-distill-llama-70b return once it is shut down?
Groq answers HTTP 404: "The model `deepseek-r1-distill-llama-70b` does not exist or you do not have access to it.". Send another model to fix it.
When was deepseek-r1-distill-llama-70b released?
deepseek-r1-distill-llama-70b was released on January 1, 2025, according to models.dev.
How do I find the calls this hits in my code?
Okapi reads your repository, finds the calls this change hits and opens a pull request with the fix. It never commits to your branches: every change comes as a pull request you review.
deepseek-r1-distill-llama-70b on other APIs 5
-
Together AI
deepseek-ai/deepseek-r1-distill-llama-70bModel retirement Stopped working -
SambaNova Cloud
deepseek-r1-distill-llama-70bModel retirement Stopped working -
Scaleway Generative APIs
deepseek-r1-distill-llama-70bModel retirement Stopped working -
DeepInfra
deepseek-ai/deepseek-r1-distill-llama-70bModel retirement Stopped working -
Novita AI
deepseek/deepseek-r1-distill-llama-70bModel retirement Stopped working
More from Groq 10
-
llama-guard-3-8bModel retirement Stopped working -
qwen-qwq-32bModel retirement Stopped working -
mistral-saba-24bModel retirement Stopped working -
distil-whisper-large-v3-enModel retirement Stopped working -
llama3-70b-8192Model retirement Stopped working -
llama3-8b-8192Model retirement Stopped working -
gemma2-9b-itModel retirement Stopped working -
moonshotai/kimi-k2-instructModel retirement Stopped working -
playai-ttsModel retirement Stopped working -
playai-tts-arabicModel retirement Stopped working
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.