Skip to main content
ParalleliX Docs

// Section 12.4 · Concepts

The Endpoints

1 min12.4Concepts
CODELINES 5
POST /v1/chat/completions   OpenAI-compatible single completion
POST /v1/batch              submit prompts[], fan out across the network
GET  /v1/batch/{id}         per-item status + result + PoE (owner-scoped)
GET  /v1/models             models the live network serves right now
GET  /v1/usage              this key's request count, credits spent, balance

A single completion:

CODELINES 4
curl https://api.parallelix.io/v1/chat/completions \
  -H "Authorization: Bearer pk_live_…" \
  -H "content-type: application/json" \
  -d '{"messages":[{"role":"user","content":"say hi"}]}'

A parallel batch:

CODELINES 5
curl https://api.parallelix.io/v1/batch \
  -H "Authorization: Bearer pk_live_…" \
  -H "content-type: application/json" \
  -d '{"prompts":["classify A","classify B","classify C"]}'
# → { "batchId": "batch_…", "total": 3, "poll": "/v1/batch/batch_…" }

Errors use the OpenAI envelope ({ "error": { "message", "type", "code" } }) so existing clients surface them correctly. The codes that matter: invalid_api_key (401), insufficient_credits (402, add credits), no_capacity (503, no node served in time, retry).