Kimi K2.6: price, context window and capabilities
Prices updated 8 Nov 2026
Kimi K2.6 is a model from Moonshot AI (moonshotai/kimi-k2.6). It supports reasoning. It supports tool use. It costs $0.650 per million input tokens and $3.41 per million output tokens, with a 262K-token context window.
What it costs in practice
Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0030, so 10,000 such turns cost about $30.05. Summarising a 100,000-token document into 2,000 tokens costs about $0.072. A long agent run that reads 1 million tokens and writes 50,000 costs about $0.821.
Kimi K2.6 compared with its closest rivals
| Model | Input / 1M | Output / 1M | Context | Chat turn |
|---|---|---|---|---|
| Kimi K2.6 Moonshot AI | $0.650 | $3.41 | 262K | $0.0030 |
| DeepSeek V4 Pro 0813 DeepSeek | $0.111 | $4.44 | 1.0M | $0.0024 |
| GPT-6.1 Terra Pro OpenAI | $1.00 | $5.00 | 1.1M | $0.0045 |
| GPT-6.1 Terra OpenAI | $1.00 | $5.00 | 1.1M | $0.0045 |
Rivals are the models from other providers with the same tool and reasoning support whose output price is closest to Kimi K2.6's.
How it compares
Among the 40 models we track, Kimi K2.6 ranks #19 by input price and #18 by output price (1 is cheapest), and #30 by context window (1 is largest). Models with the same tool and reasoning support that cost less per output token: GLM 5.3 Flash ($0.083), DeepSeek V4 Flash 0731 ($0.300), Qwen3.8 Omni Flash ($0.470), Qwen3.8 Flash ($0.470). Models with a larger context window at the same or lower output price: Llama 4 Scout (1.3M), DeepSeek V4.1 Flash 1017 (1.0M), DeepSeek V4.1 Flash (1.0M), DeepSeek V4 Flash 0731 (1.0M).
More from Moonshot AI
All Moonshot AI models on one page: Moonshot AI API pricing.
- Kimi K3.1 Pro: $2.00 in / $10.00 out, 1.0M context
- Kimi K3: $0.192 in / $16.00 out, 1.0M context
- Kimi K2.7 Code: $0.600 in / $3.50 out, 262K context
In the news
Prices and limits come from OpenRouter's public model catalogue, last synced 8 Nov 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.