MoonshotAI: Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Everything else
| Max output | 262K |
|---|---|
| Input / 1M | $0.646 |
| Output / 1M | $2.72 |
| Cache read / 1M | $0.109 |
| Cache write / 1M | — |
| 1M in + 1M out | $3.37 |
| Takes | text, image |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-04-20 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | moonshotai/kimi-k2.6 |
Benchmarks
| source | epoch |
|---|---|
| eci | 151.03 |
| confidence | Confident |
| accessibility | Open weights (unrestricted) |
| gpqa | 0.908 |
| gpqaStderr | 0.0172 |
| sweBenchVerified | 0.767 |
| sweBenchVerifiedStderr | 0.0192 |
| frontierMath | 0.39 |
| frontierMathStderr | 0.0287 |
| aime | 0.961 |
| aimeStderr | 0.0238 |
| simpleQA | 0.387 |
| simpleQAStderr | 0.0154 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.