Documentation

Build on the OneAI commercial API.

OneAI is the model-routing and structured-intelligence layer. Use /v1/generate for task intelligence, /v1/chat/completions for standard model gateway calls, and /v1/models for catalog discovery.

Quickstart

Make the first /v1/generate call.

API Basics

Auth, request shape, response metadata.

Generate Reference

Task input, options, usage, trace.

Chat Completions

OpenAI-compatible model gateway calls.

Models

Catalog, health checks, pricing coverage.

Errors

Retryable failures and customer-safe errors.

Rate Limits

API key policy and production limits.

Schemas

Structured output contracts.

Production request

curl https://oneai-saas-api-production.up.railway.app/v1/generate \
  -H "content-type: application/json" \
  -H "x-api-key: $ONEAI_API_KEY" \
  -H "Idempotency-Key: launch-plan-001" \
  -d '{
    "type": "agent_plan",
    "input": { "goal": "Create a launch plan for OneAI API" },
    "options": { "llm": { "mode": "cheap", "maxCostUsd": 0.02 } }
  }'