SeedInfer — Private AI on Verified Hardware

Coming soon — proxy to docs.seedinfer.com

This console will proxy POST /v1/chat/completions to api.seedinfer.com (which proxies https://api.seedinfer.com). Currently shows curl playground with mock response. See docs.seedinfer.com for live auth & SDKs.

OpenAI compat

curl — SeedInfer (future)

curl https://api.seedinfer.com/v1/chat/completions \
  -H "Authorization: Bearer $SEEDINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedinfer/nemotron-lightning-1m",
    "messages": [
      {"role": "user", "content": "Explain private inference on Apple Silicon in one paragraph."}
    ],
    "stream": false,
    "max_tokens": 256
  }'

model: seedinfer/nemotron-lightning-1m$0.02 / $0.05 per 1Mstream: true|false

curl — SeedInfer (direct)

curl https://api.seedinfer.com/v1/chat/completions \
  -H "Authorization: Bearer $SEEDINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedinfer/nemotron-lightning-1m",
    "messages": [{"role": "user", "content": "Hello via SeedInfer"}]
  }'

Upstream base: https://api.seedinfer.com · placeholder until SeedInfer proxy cutover.

Playground — mock response

POST /v1/chat/completions

Request (editable mock — not sent upstream yet)

{
  "model": "seedinfer/nemotron-lightning-1m",
  "messages": [
    {
      "role": "user",
      "content": "Explain private inference"
    }
  ],
  "stream": false
}

Response (mock)

{
  "id": "chatcmpl-mock",
  "object": "chat.completion",
  "model": "seedinfer/nemotron-lightning-1m",
  "choices": [{"message": {"role": "assistant", "content": "This is a mock response — connect to docs.seedinfer.com for live proxy."}}]
}

Docs: docs.seedinfer.com · Auth: Authorization: Bearer $SEEDINFER_API_KEY · OpenAI SDK compatible (baseURL override).

SeedInfer.com · API console — Coming soon proxy to docs.seedinfer.com · POST /v1/chat/completions · OpenAI-compatible