🔑 Your API Key — paste once, used by every Try It button below
Stored in your browser localStorage. Works for both raw and intelligent endpoints — same key, different base URL.
openrout.ing serves 47,844 models across all 12 AI modalities through two API surfaces, both unlocked by a single API key:
raw.openrout.ing — Raw inference. Direct OpenAI-compatible model access with zero orchestration. Every request goes straight to the model and back — no containers, no memory, no tool loops. Maximum speed, minimum latency. All 47,844 models: 10,210 subscription open-weight LLMs + 25,691 PAYG models across chat, image, video, 3D, music, TTS, STT, digital-human, lipsync, faceswap, embedding and media modalities.
api.openrout.ing — Intelligent inference. The same OpenAI-compatible surface with platform-level enrichment: context enrichment, auto-summarization, model aliases with coalition fallback, structured output, streaming and observability. Every platform feature is included free with your plan.
Switch between them by changing only the base URL — your SDK, auth, and code stay identical.
Quickstart
# Set your key once
export OPENROUTING_API_KEY="or_..."
# 1. Raw inference — pure model access
curl https://raw.openrout.ing/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTING_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3-8B","messages":[{"role":"user","content":"Hello"}]}'
# 2. Intelligent inference — same call, agentic runtime
curl https://api.openrout.ing/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTING_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"general","messages":[{"role":"user","content":"Hello"}],"enrich":true}'
Model aliases on the intelligent surface: general → GLM-5.1 · chat → Qwen3-8B · fast → DeepSeek-V4-Flash · big → Qwen2.5-72B. Or pass any model by full ID.
Authentication
All requests require Authorization: Bearer or_.... Keys are created at openrout.ing/signup and work across both endpoints.
Per-model per-unit (per M tokens, per image, per video, per mesh…)
Cache
n/a
Cache reads at 65% off input price
Credits
Monthly token allowance per tier
Top up anytime — credits never expire
All Endpoints
The full endpoint reference (347 endpoints) is in the Postman Collection. Interactive Swagger docs: https://api.openrout.ing/docs. Admin key lifecycle (create/revoke keys with tier limits, rpm/tpd, concurrency, model whitelists, IP whitelists, scopes, expiry): POST /keys/create and friends — admin-tier key required.