Vendor
OpenRouter models
6 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
6
0 routable here
Median list price
free
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every OpenRouter model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Auto Router (Beta)openrouter/auto-beta | Jul 17, 2026 | 2M | - | - | - | reasoning tools |
| Fusionopenrouter/fusion | Jun 13, 2026 | 1M | - | - | - | |
| Pareto Code Routeropenrouter/pareto-code | Apr 21, 2026 | 2M | - | - | - | |
| Free Models Routeropenrouter/free | Feb 1, 2026 | 200K | free | free | - | reasoning tools |
| Body Builder (beta)openrouter/bodybuilder | Dec 5, 2025 | 128K | - | - | - | |
| Auto Routeropenrouter/auto | Nov 8, 2023 | 2M | - | - | - | reasoning tools |
Frequently asked
- What is the cheapest OpenRouter model?
- Free Models Router at free per 1M input tokens and free per 1M output tokens (vendor list price).
- Which OpenRouter model has the largest context window?
- Auto Router (Beta) accepts 2M tokens of context.
- How do I route to OpenRouter models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example openrouter/auto-beta); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route OpenRouter with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a OpenRouter flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.