Model comparison

Kimi K2.7 Code vs MiMo-V2.5-Pro

Pricing, context window and real answers (August 2026)

Kimi K2.7 Code (Moonshot) and MiMo-V2.5-Pro (Xiaomi), compared as you can actually call them on FastMetal. Both are served from the same OpenAI-compatible endpoint and API key; switching is a change to the model string.

Specs and pricing

moonshotai logoKimi K2.7 CodeMiMo-V2.5-Pro
ProviderMoonshotXiaomi
Input (per 1M tokens)¥55¥77.73
Output (per 1M tokens)¥530¥155.47
Typical cost (1,000 in + 500 out tokens × 1,000 calls)¥320¥155
Context window262,144 tokens1,050,000 tokens
Release date6/12/20264/22/2026
Input modalitiestext, imagetext
Arena · overallUnranked#40 · ELO 1,468
Arena · JapaneseUnranked#61 · ELO 1,418
Arena · codingUnranked#27 · ELO 1,520

Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.

Which should you pick?

  • On price, MiMo-V2.5-Pro: ¥155.47 per 1M output tokens, 71% less than Kimi K2.7 Code.
  • For long documents, MiMo-V2.5-Pro: a 1,050,000-token context window against 262,144 for Kimi K2.7 Code.
  • If in doubt, try both on the same key. Switching is a change to the model string, and each is billed at its own rate.

Frequently asked questions

Which is cheaper, Kimi K2.7 Code or MiMo-V2.5-Pro?
Per 1M output tokens, Kimi K2.7 Code is ¥530 and MiMo-V2.5-Pro is ¥155.47 on FastMetal (yen, before tax), so MiMo-V2.5-Pro is cheaper.
How do the context windows of Kimi K2.7 Code and MiMo-V2.5-Pro compare?
Kimi K2.7 Code takes 262,144 tokens; MiMo-V2.5-Pro takes 1,050,000.
Can I use Kimi K2.7 Code and MiMo-V2.5-Pro with the same API key?
Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "japan-kimi-k2.7-code" or "mimo-v2.5-pro" as the model. Each is billed at its own rate from the same prepaid balance.

Try both on one API key

Create an account and add credit to call Kimi K2.7 Code and MiMo-V2.5-Pro from the browser chat and the API. No monthly fee.

More comparisons with Kimi K2.7 Code

More comparisons with MiMo-V2.5-Pro