MoonshotPaidOperational

Kimi K2.5

API model name: kimi-k2.5

Kimi K2.5 is Moonshot's chat model, served on the Api.Airforce unified API. It has a 262K-token context window. Capabilities include Tool calling, Prompt caching. It is priced at $0.58 per million input tokens and $2.95 per million output tokens. That is below the provider's $0.60 official input rate. Knowledge cutoff: 2025-08. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.

Pricing

Input / 1M tokens
$0.58
Output / 1M tokens
$2.95
Official input rate
$0.60
Official output rate
$3.00

Api.Airforce price vs. the provider's official rate.

Specifications

Provider
Moonshot
Type
chat model
Context window
262K tokens
Max output
16K tokens
Knowledge cutoff
2025-08
Input
text
Output
text
Prompt caching
Supported

Capabilities

Tool callingPrompt cachingStreaming

Benchmarks

Independent evaluations and measured speed from Artificial Analysis.

Intelligence Index
37.3/100
Coding Index
25.8/100
GPQA Diamond79%
Humanity's Last Exam12%
Output speed39.3 tok/s
Time to first token1.28 s

Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)

What is Kimi K2.5 used for?

  • Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
  • Agents & automation — function calling and tool use for multi-step workflows.
  • Long-context tasks — process entire documents or codebases in a single prompt.
  • Real-time experiences — stream tokens for responsive chat and apps.

Kimi K2.5 vs. similar models

ModelIntelligenceContextInput / 1MOutput / 1M
Kimi K2.537.3262K$0.58$2.95
Kimi K226.3131K$0.87$3.42
Kimi K2$0.87$3.42
Kimi K2 Turbo$3.42$13.65

Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.

Related models

Kimi K2.5 — frequently asked questions

How much does Kimi K2.5 cost?
Kimi K2.5 is billed pay-as-you-go at $0.58 per 1M input tokens and $2.95 per 1M output tokens. There is no subscription — you only pay for what you use.
What is the context window of Kimi K2.5?
Kimi K2.5 supports a context window of up to 262K tokens. It can return up to 16K tokens in a single response.
What can Kimi K2.5 do?
Kimi K2.5 supports Tool calling, Prompt caching.
Is Kimi K2.5 free to use?
Kimi K2.5 is a paid, pay-as-you-go model — no subscription, you are only charged for usage.
How do I use Kimi K2.5 via the API?
Kimi K2.5 is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID kimi-k2.5 with your Api.Airforce API key.
Who makes Kimi K2.5?
Kimi K2.5 is Moonshot's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.