MODEL 01 · QWEN
Qwen/Qwen3-VL-Embedding-8B
qwen3-vl-embedding-8b
Image + text embeddings
SELF-HOSTED · MULTIMODAL API
Build semantic search, image similarity and multimodal retrieval with two dedicated embedding models behind an authenticated API.
Embedding requests require a Bearer token. Public health and model metadata do not confirm GPU readiness.
Choose the model and embedding settings that fit your application. Vectors from different models are not interchangeable.
MODEL 01 · QWEN
qwen3-vl-embedding-8b
Image + text embeddings
MODEL 02 · TENCENT
wemm-embedding-9b
Image + text embeddings
Everything you need to deploy and connect your own client.
Configure a Modal workspace, pinned checkpoints and private Secrets.
Deployment guide ↗Use a valid Bearer token for embedding and job endpoints.
Client integration ↗Prefer asynchronous jobs for longer GPU startup times.
Async API contract ↗