Vendor
Kwaipilot models
2 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
2
0 routable here
Median list price
$0.91
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Kwaipilot 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 |
|---|---|---|---|---|---|---|
| KAT-Coder-Pro V2.5kwaipilot/kat-coder-pro-v2.5 | Jul 10, 2026 | 262K | $0.74 | $2.96 | - | tools |
| KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2 | Mar 27, 2026 | 262K | $0.30 | $1.20 | - | tools |
Frequently asked
- What is the cheapest Kwaipilot model?
- KAT-Coder-Pro V2 at $0.30 per 1M input tokens and $1.20 per 1M output tokens (vendor list price).
- Which Kwaipilot model has the largest context window?
- KAT-Coder-Pro V2.5 accepts 262K tokens of context.
- How do I route to Kwaipilot models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example kwaipilot/kat-coder-pro-v2.5); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Kwaipilot with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Kwaipilot flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.