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 OpenAI-compatible gateway calls, /v1/messages for Messages-style gateway calls, and /v1/models for catalog discovery.
Positioning, API surfaces, task list, cost controls, and commercial usage.
Security, SLA, DPA, privacy, execution boundary, and enterprise trust controls.
Customer-facing scenarios for strategy, content, support, market intelligence, and custom tasks.
Security, cost controls, idempotency, usage, and launch verification.
Copyable request and output examples for commercial tasks.
Capabilities, agent plans, handoff preview, and context preview without execution.
Protocol versions, compatibility rules, executor checklist, and OneClaw/OpenClaw expectations.
Make the first /v1/generate call.
Auth, request shape, response metadata.
Task input, options, usage, trace.
OpenAI-compatible model gateway calls.
Anthropic-style Messages API through OneAI model routing.
Catalog, health checks, pricing coverage.
Enterprise service-level expectations and support boundary.
Customer data processing, provider routing, and deletion/export path.
Stripe portal, manual invoices, billing evidence, and plan changes.
Order form, MSA, DPA, SLA, billing, and support contract pack.
Service boundary, acceptable use, API key responsibility, and plan limits.
Account data, request data, secrets, logs, and customer requests.
Retryable failures and customer-safe errors.
API key policy and production limits.
Structured output contracts.
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: business-strategy-001" \
-d '{
"type": "business_strategy",
"input": {
"goal": "Create a launch plan for OneAI API",
"audience": "SaaS builders",
"constraints": ["Keep it practical"]
},
"options": { "llm": { "mode": "cheap", "maxCostUsd": 0.03 } }
}'