Explorer
Syncing—

LLM InferenceService

llm-inference

Open-weight LLM inference for routing, classification, and summarization tasks. Deterministic at fixed model, precision, and seed. Served as a JSON object over POST /v1/llm (JSON in, JSON out).

Active Suppliers
0
of 0 ever configured
Service Info
Service ID
llm-inference
Compute Units / Relay
50,000
Owner
pokt10…87pn
Active Applications
1
Relay Mining EMA
1 relays
Service Metadata Cardsource: on-chain metadata (LCD)
{10 items
"schema":"pocket-service-card/v1"
"description":"Open-weight LLM inference for routing, classification, and summarization tasks. Deterministic at fixed model, precision, and seed. Served as a JSON object over ..."
"rpc_types":[1 item
0:{4 items
"type":"REST"
"intent":"expected"
"backend_hint":"llm-inference HTTP server on :8080; POST /v1/llm, GET /v1/health + /v1/version."
"notes":"Every response is a JSON object; errors are JSON 4xx/5xx with an error field."
}
]
"apis":[1 item
0:"llm-inference-api"
]
"specs":[1 item
0:{3 items
"kind":"openapi"
"api":"llm-inference-api"
"url":"https://services.supnodes.com/specs/llm-inference/openapi.json"
}
]
"access":"public"
"results":"deterministic"
"serving":{7 items
"backend":"llm-inference stdlib http.server container behind a HA RelayMiner (rest backend pointed at http://llm-inference-backend:8080). No auth toward the backend; calle..."
"implementations":[1 item
0:"llm-inference >= 1.0"
]
"docs":"https://services.supnodes.com/specs/llm-inference/README.md"
"min_disk_gb":1
"min_ram_gb":1
"healthcheck":[3 items
0:{4 items
"rpc_type":"REST"
"request":{2 items
"path":"/v1/version"
"method":"GET"
}
"expect":{2 items
"json_path":"$.service"
"matches":"^llm-inference$"
}
"notes":"Identity probe: pins backend to this service id."
}
1:{4 items
"rpc_type":"REST"
"request":{2 items
"path":"/v1/health"
"method":"GET"
}
"expect":{2 items
"json_path":"$.status"
"matches":"^ok$"
}
"notes":"Readiness probe."
}
2:{4 items
"rpc_type":"REST"
"request":{3 items
"path":"/v1/llm"
"method":"POST"
"body":{1 item
"query":"probe"
}
}
"expect":{2 items
"json_path":"$.service"
"matches":"^llm-inference$"
}
"notes":"Functional probe: deterministic echo of the service contract."
}
]
"notes":"No upstream rate limits for this container. Gateway operators: configure as type passthrough with rpc_types ["rest"]."
}
"docs":"https://services.supnodes.com/specs/llm-inference/README.md"
"updated":"2026-09-21"
}