Explorer
Syncing—

Qwen3 Embedding 06B - OpenAI API compatibleService

qwen3-embedding-0-6b

OpenAI-API-compatible text embeddings, served by Qwen3-Embedding-0.6B. The expected endpoints are POST /v1/embeddings and GET /v1/models; suppliers MAY expose more of the OpenAI surface but consumers MUST NOT depend on it. Address the model as "pocket_network". Weights are specified: every supplier serves the same model, so vectors are semantically comparable across suppliers (but they are NOT bit-identical).

Active Suppliers
3
of 3 ever configured
Service Info
Service ID
qwen3-embedding-0-6b
Compute Units / Relay
10,000
Owner
pokt1m…pewk
Active Applications
1
Relay Mining EMA
2 relays
Service Metadata Cardsource: on-chain metadata (LCD)
{8 items
"schema":"pocket-service-card/v1"
"description":"OpenAI-API-compatible text embeddings, served by Qwen3-Embedding-0.6B. The expected endpoints are POST /v1/embeddings and GET /v1/models; suppliers MAY expose m..."
"rpc_types":[1 item
0:{4 items
"type":"REST"
"intent":"expected"
"backend_hint":"OpenAI-compatible embeddings server on :8080 (TEI) or :8000 (vLLM --task embed); mount at /"
"notes":"Only POST /v1/embeddings and GET /v1/models are expected."
}
]
"apis":[2 items
0:"openai-embeddings"
1:"openai-models"
]
"specs":[1 item
0:{3 items
"kind":"markdown"
"url":"https://raw.githubusercontent.com/pnyxai/pocket-network-services/678a9743dd5dafb810b6a8502f56f8d1b5639045/mainnet/docs_qwen3-embedding-0-6b.md"
"sha256":"03b4015d3dd1d6e8ef1b626c9605c7595b510a776fe636e1e0a86a86f8a25fdc"
}
]
"access":"public"
"results":"variable"
"serving":{3 items
"backend":"Any OpenAI-compatible server exposing POST /v1/embeddings and GET /v1/models, serving Qwen/Qwen3-Embedding-0.6B. The weights ARE specified for this service -- d..."
"healthcheck":[1 item
0:{3 items
"rpc_type":"REST"
"request":{3 items
"path":"/v1/embeddings"
"method":"POST"
"body":{2 items
"model":"pocket_network"
"input":"pocket network embedding healthcheck"
}
}
"expect":{2 items
"json_path":"$.data[0].object"
"matches":"^embedding$"
}
}
]
"notes":"Use a server with dynamic batching so one backend serves many concurrent requests, and expect callers to batch many inputs into a single relay. Serve the specif..."
}
}