whichllmmodel
Back to Dashboard
💬 Text ModelOpen Source

kimi-k2.5

by Moonshot AI (Kimi)

✍️ Analysis by:the whichllmmodel Editorial Team|📅 Updated: June 2026
API Reference

Benchmark Evaluations

Codingswe-bench-pro

50.7%

Reasoninggpqa-diamond

87.6%

Pricing & Speed Details

Input Cost

$0.60

per 1M tokens
Output Cost

$3.00

per 1M tokens
Blended Cost

$1.20

based on 3:1 ratio
Speed

193 tps

Context Window

262.14k tokens

Want to test this model?

Compare kimi-k2.5 dynamically against other top AI models on our comparison dashboard to optimize your choice.

Go to Dashboard

Quick Info

  • ProviderMoonshot AI (Kimi)
  • CategoryText / Chat Generation
  • LicenseOpen Source

Frequently Asked Questions

kimi-k2.5 has a blended cost of $1.20 per 1 million tokens (calculated using a standard 3:1 input-to-output token ratio). Its specific pricing is $0.60 per 1M input tokens and $3.00 per 1M output tokens.

kimi-k2.5 supports a context window of 262.14k tokens. This allows it to process large documents, codebase segments, or long chat histories in a single query session.

kimi-k2.5 scores 50.7% on coding evaluations (SWE-bench-pro) and 87.6% on reasoning tasks (GPQA-diamond).

kimi-k2.5 is an open source model developed by Moonshot AI (Kimi).