DeepInfra
nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 model retirement
Stopped workingSubscribe to DeepInfraShare
DeepInfra retired the model nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 on June 26, 2026. Calls specifying this model fail since that day.
What to use instead of nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16
DeepInfra recommends moving to nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16- Released
- June 4, 2026 (models.dev)
- Kind
- Model retirement
- Takes effect
- June 26, 2026
- Calls after that day
- Fail
- Source
- Model list
- Last updated
- Verified
- , against DeepInfra's own pages
Questions
When does nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 shut down?
Calls to the model nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 on DeepInfra stopped working on June 26, 2026.
What happens to calls after June 26, 2026?
They have failed since June 26, 2026.
When was nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 released?
nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 was released on June 4, 2026, 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.
More from DeepInfra 10
-
deepseek-ai/deepseek-r1-distill-llama-70bModel retirement Stopped working -
deepseek-ai/deepseek-r1-distill-qwen-32bModel retirement Stopped working -
qwen/qwen3.5-0.8bModel retirement Stopped working -
qwen/qwen3.5-2bModel retirement Stopped working -
qwen/qwen3.5-4bModel retirement Stopped working -
qwen/qwq-32b-previewModel retirement Stopped working -
fastvideo/ltx2-distilled-diffusersModel retirement Stopped working -
qwen/qwen3-embedding-0.6b-batchModel retirement Stopped working -
qwen/qwen3-embedding-4b-batchModel retirement Stopped working -
qwen/qwen3-embedding-8b-batchModel 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.