Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...
Hosted API only
No self-host path — closed weights.
Auto Router's weights aren't published. Use it via the access providers below.
Where to use it
Cheapest hosted endpoints.
| Provider | Access | $/M in | $/M out | |
|---|---|---|---|---|
| OpenRouter | api aggregator | — | — | Launch ↗ |
Performance
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 46.1 | 2017 ms | 2539 ms |
FAQ
Frequently asked.
How do I run Auto Router?
Auto Router is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Auto Router?
Auto Router is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Auto Router?
Pricing varies per access provider — check each entry in the access table for current rates.
Is Auto Router open-source or proprietary?
Auto Router is a proprietary model from Openrouter. Access is API-only — there are no public weights to download.
Context window
How much it can remember.
2M tokens
≈ 1,500,000 English words
4K
32K
128K
1M
Capabilities
What it can do.
·
Vision input
·
Audio input
·
Video input
·
Function calling
·
Tool use
·
JSON mode
✓
Streaming
·
Fine-tuning