DeepInfra · Model retirement
qwen/qwen3-embedding-4b-batch
Stopped working
Calls to the model qwen/qwen3-embedding-4b-batch on DeepInfra stopped working on July 6, 2026.
What to use instead of qwen/qwen3-embedding-4b-batch
Move to Qwen/Qwen3-Embedding-4B, recommended by DeepInfra.
Embeddings from another model are not comparable with this one's: vectors the code stores must all be computed again with the new model.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
qwen/qwen3-embedding-4b-batch- Kind
- Model retirement
- Takes effect
- July 6, 2026
- Calls after that day
- Fail
- Source
- Lifecycle page
- Last updated
More from DeepInfra
- qwen/qwen3-embedding-0.6b-batch Stopped working
- qwen/qwen3-embedding-8b-batch Stopped working
- meta-llama/meta-llama-3.1-8b-instruct Stopped working
- microsoft/phi-3-medium-4k-instruct Stopped working
- nvidia/llama-3.1-nemotron-70b-instruct Stopped working
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Stopped working