DeepInfra
meta-llama/llama-3.3-70b-instruct model retirement
Stopped workingSubscribe to DeepInfraShare
Calls to the model meta-llama/llama-3.3-70b-instruct on DeepInfra stopped working on November 6, 2025.
What to use instead of meta-llama/llama-3.3-70b-instruct
Move to meta-llama/Llama-3.3-70B-Instruct-Turbo, which is recommended by DeepInfra.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
meta-llama/llama-3.3-70b-instruct- Released
- December 6, 2024 (models.dev)
- Kind
- Model retirement
- Takes effect
- November 6, 2025
- Calls after that day
- Fail
- Source
- Model list
- Last updated
- Verified
- , against DeepInfra's own pages
Questions
When does meta-llama/llama-3.3-70b-instruct shut down?
Calls to the model meta-llama/llama-3.3-70b-instruct on DeepInfra stopped working on November 6, 2025.
What happens to calls after November 6, 2025?
They have failed since November 6, 2025.
When was meta-llama/llama-3.3-70b-instruct released?
meta-llama/llama-3.3-70b-instruct was released on December 6, 2024, 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.
meta-llama/llama-3.3-70b-instruct on other APIs 3
-
Nebius
meta-llama/llama-3.3-70b-instructModel retirement Stopped working -
Novita AI
meta-llama/llama-3.3-70b-instructModel retirement Stops workingin 20 days -
Azure AI Foundry
llama-3.3-70b-instructModel retirement Stops workingin 86 days
More from DeepInfra 10
-
qwen/qwen3-vl-235b-a22b-thinkingModel retirement Stopped working -
qwen/qwq-32bModel retirement Stopped working -
deepinfra/airoboros-70bModel retirement Stopped working -
lizpreciatior/lzlv_70b_fp16_hfModel retirement Stopped working -
qwen/qwen2-7b-instructModel retirement Stopped working -
qwen/qwen2.5-7b-instructModel retirement Stopped working -
qwen/qwen2.5-coder-7bModel retirement Stopped working -
qwen/qwen3-vl-30b-a3b-thinkingModel retirement Stopped working -
qwen/qwen3-vl-4b-instructModel retirement Stopped working -
qwen/qwen3-vl-4b-thinkingModel 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.