OrcaRouter grades every prompt and routes it intelligently. Frontier-quality AI at up to 40% lower cost. Adaptive routing, load balancing, guardrails, agent firewall, observability, and governance — all through a single OpenAI-compatible endpoint.
No credit card · live in 60 secs
- client = OpenAI(api_key="sk-...")+ client = OpenAI(+ base_url="https://api.orcarouter.ai/v1",+ api_key="sk-orca-..."+ )# Everything else stays the same.response = client.chat.completions.create(model="orcarouter/auto", # router picks the best model per requestmessages=[{"role": "user", "content": "..."}])# → orcarouter/auto grades the prompt → frontier or open-source, zero token markup ✓
One line. We grade each prompt, route to frontier or OSS, and add $0.
Drop-in OpenAI-compatible, or connect agents over the OrcaRouter MCP server — keep your SDK, framework and editor.
Smart routing and automatic failover on every request.
Every prompt is embedded and routed by a model that keeps learning online from real traffic. On the public RouterArena leaderboard (Jun 2026) it leads on accuracy — ahead of GPT-5, Azure, Martian and NotDiamond — at 75.5%.
When a provider rate-limits or 5xxs, OrcaRouter retries the request against a healthy model across 200+ options before the response starts — so transient upstream outages don't surface to your users.
See and prove every call — cost, model, latency, and why.
See exactly what every request cost, which model served it, how long it took, and why it failed — full structured logs you can filter, replay, and copy as a runnable cURL. A route is never a black box.
You pay each provider their exact price — we add $0 per token, ever. Every request shows the grade, chosen model, provider, latency, and price, so cost is glass-box, not an opaque blended rate.
Versioned prompts and caching — without a redeploy.
Version prompts behind named labels with A/B splits and one-click rollback. Move a label and every request picks it up instantly — no redeploy, no code change, no client update.
Repeated and cached prompt tokens bill at the provider's cache rate — often a fraction of the input price — across 5-minute and 1-hour ephemeral windows. Same answers, less spend, with cached_tokens on every receipt.
Guardrails, budgets, and an agent firewall that enforces.
PII Shield and content policies run before the upstream call is billed. A blocked request returns a clean 400 and is never charged — guardrails enforced inline, not logged after the fact.
Budgets and roles for people; a risk-scored firewall for agents. Every tool and MCP call is graded ALLOW, REVIEW, or BLOCK before it runs, and anomaly detection flags rate and cost spikes against learned hour-of-week baselines.
One URL change. Your existing SDK, model names, and streaming all work exactly as before.
Set base_url to api.orcarouter.ai/v1 and swap your API key. No other code changes needed.
Every call is routed to the best model, checked against your guardrails, and metered — graded in under 1ms, with failover, caching and full logs built in.
Traffic goes direct to each provider's first-party API at their published rate — we add $0 per token. One OpenAI-compatible endpoint for routing, observability and governance.
200+ models with live, side-by-side pricing — what you'd pay the provider directly. We add $0 on top.
| Model | Routed to | Input /M | Output /M | Context | Quality |
|---|---|---|---|---|---|
| kimi/kimi-k2.7-codeNEW | Moonshot | $0.950 | $4.00 | 262K | 8.0 |
| anthropic/claude-fable-5NEW | Anthropic Direct | $10.00 | $50.00 | 1M | 10.0 |
| qwen/qwen3.7-plusNEW | Alibaba Cloud | $0.350 | $1.42 | 1M | 8.0 |
| minimax/minimax-m3NEW | — | $0.300 | $1.20 | 1M | 9.0 |
| anthropic/claude-opus-4.8NEW | Anthropic Direct | $5.00 | $25.00 | 1M | 10.0 |
| google/gemini-3.5-flashNEW | Google Direct | $1.50 | $9.00 | 1M | 9.0 |
| qwen/qwen3.7-maxNEW | Alibaba Cloud | $1.25 | $3.75 | 1M | 5.0 |
| qwen/qwen3.7-max-2026-05-20NEW | Alibaba Cloud | $1.25 | $3.75 | 1M | 5.0 |
| qwen/qwen3.6-flash | Alibaba Cloud | $0.250 | $1.50 | 1M | 7.0 |
| qwen/qwen3.6-35b-a3b | Alibaba Cloud | $0.248 | $1.48 | 262K | 8.0 |
| openai/gpt-5.5-pro | OpenAI Direct | $30.00 | $180.00 | — | 10.0 |
| openai/gpt-5.5 | OpenAI Direct | $5.00 | $30.00 | — | 10.0 |
| deepseek/deepseek-v4-pro | DeepSeek | $0.435 | $0.870 | 1M | 9.0 |
| deepseek/deepseek-v4-flash | DeepSeek | $0.140 | $0.280 | 1M | 8.0 |
| anthropic/claude-opus-4.7 | Anthropic Direct | $5.00 | $25.00 | 1M | 10.0 |
| + 194 more models · Prices update every 60 seconds | |||||
Streaming, tool calls, structured outputs, vision, embeddings and audio — routed unchanged across every model.
| Model | Streaming | Tools | Structured | Vision | Embeddings | Audio |
|---|---|---|---|---|---|---|
| anthropic/claude-opus-4.8 | supported | supported | supported | supported | not supported | not supported |
| google/gemini-3.1-pro-preview | supported | supported | supported | supported | not supported | supported |
| grok/grok-4.3 | supported | supported | supported | supported | not supported | not supported |
| anthropic/claude-fable-5 | supported | supported | supported | supported | not supported | not supported |
| anthropic/claude-opus-4.7 | supported | supported | supported | supported | not supported | not supported |
We never take a cut of your token spend. Our revenue comes from optional team features.
Audit reports available under NDA — request a copy below.
Swap one line. That's the migration.
Sign up with GitHub — $5 in tokens free. No credit card required. You're live in under a minute.
