Kimi K2 Instruct 0905
Latest Kimi K2 InstructSeptember 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
- Strongest at
- Writing Top 50% of the past year's models · one benchmark so far
- Price per 1M tokens
- $0.6 / $2.5 input / output · OpenRouter
- Context window
- 262.1K tokens in · 98.3K out
- Since the last one
- 56 days after Kimi K2 Instruct
Capability profile
Where it lands among 90 models released in the past year. 50 is the average model.
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow marker rests on a single benchmark.
- Writing EQ-Bench Longform Writing
- Science WeirdML v2
Price against capability
The shaded corner holds anything better and cheaper. Prices blend input and output 3 to 1.
5 models from the past year score higher on Writing for less: Kimi K2.5, Muse Glimmer 30B, GLM-4.7 and 2 more.
27 models from the past year score higher on Science for less: DeepSeek V4.1 Flash 1017, GPT-6 Luna, GLM-5.3-Flash and 24 more.
OpenRouter $0.6 / $2.5
Since Kimi K2 Instruct
2 releases in the Kimi K2 Instruct line.
Moonshot AI's past year
7 release days in the past year, about one every 52 days. The next is expected around Dec 7, 2026. Forecasts ↗
Specifications
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.