Kimi K2.7 Code vs Devstral 2 2512
Open-weight code specialists from Moonshot and Mistral.
What the numbers say
- Devstral 2 2512 is about 1.8x cheaper on output tokens (22.0 vs 38.5 credits per 1M).
- Both take the same 262K-token context window.
- Kimi K2.7 Code accepts images; Devstral 2 2512 is text-only.
- Kimi K2.7 Code is the newer release (June 2026 vs December 2025).
Derived from the live registry Zeplik routes and bills against. Credits: 1 credit = $0.10, raw provider rate with a 1.10x margin.
Side by side
Kimi K2.7 Code
MoonshotAI
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. It uses a native multimodal mixture-of-experts...
- Provider
- MoonshotAI
- Context window
- 262K tokens
- Input price
- 7.9 credits / 1M tokens ($0.72 raw)
- Output price
- 38.5 credits / 1M tokens ($3.50 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Best for
- Writing, reviewing and refactoring code; agentic coding workflows
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Devstral 2 2512
Mistral
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
- Provider
- Mistral
- Context window
- 262K tokens
- Input price
- 4.4 credits / 1M tokens ($0.40 raw)
- Output price
- 22.0 credits / 1M tokens ($2.00 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Best for
- Writing, reviewing and refactoring code; agentic coding workflows
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Try both on Zeplik
The honest answer to most model debates is to run your own prompt on both. Zeplik puts Kimi K2.7 Code and Devstral 2 2512 in the same chat, so you can switch mid-conversation and compare answers on the work you actually do.