Kat Coder Pro
Coding model for repository understanding, refactors, and agentic engineering tasks
Cheapest input
$0.3
$/MTok · models.dev
Cheapest output
$1.20
$/MTok
Context
256K
tokens
Offers
4
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestkwaipilot/kat-coder-pro | Novita AI | $0.3 | $1.20 | $0.06 | 256K |
| LiteLLMnovita/kwaipilot/kat-coder-pro | — | $0.3 | $1.20 | $0.06 | — |
| LiteLLMkwaipilot/kat-coder-pro | — | $0.3 | $1.20 | $0.06 | — |
| LiteLLMkat-coder-pro | — | $0.3 | $1.20 | $0.06 | — |
Capabilities
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Released: 2026-01-05
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence33.7
- AA coding59.5
- AA agentic15.5
Sources: Arena AI, Artificial Analysis. See /benchmarks.