M
Kimi K2.7 CodeOPEN
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.
Prices update automatically — checked daily against provider list prices.
- $1.35 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 11% of the 191 open-weight models tracked here
- 5 of 7 Moonshot AI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Kimi K2.7 Code, measured by Artificial Analysis. Higher is better.
For the same budget, Kimi K2.7 Code delivers 4 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.76 per 1M tokens (median of 12) — this one costs $1.35.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 9 more
About this model
Kimi K2.7 Code is an open-weight AI model by Moonshot AI. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Kimi K2.7 Code?
Kimi K2.7 Code is an AI language model from Moonshot AI. It is open-weight: you can download it and run it on your own hardware, for free. It scores 43 on the Artificial Analysis intelligence index.
Is Kimi K2.7 Code free?
The weights are free and open — you can self-host Kimi K2.7 Code and pay nothing per token. If you prefer a hosted API, list prices are $0.66 per million input tokens and $3.4 per million output tokens.
What is Kimi K2.7 Code good at?
Independent benchmarks from Artificial Analysis give it GPQA 89.6%, Humanity's Last Exam 35%, Long Context Reasoning 75%, SciCode 47.5%, IFBench 63.1%, τ²-Bench 90.1%, τ-Bench Banking 20.2%, Terminal-Bench 67.4%, Terminal-Bench Hard 44.7%. It is particularly used for code generation.
How fast is Kimi K2.7 Code?
It generates about 39.5 tokens per second, with a median 1.28s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Kimi K2.7 Code?
Yes. Kimi K2.7 Code has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.