Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for moonshotai

MoonshotAI: Kimi K2.5

moonshotai/kimi-k2.5

Model weights
Compare

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

Modalities

In / Out Price

$0.375 / $2.025per 1M

Context

262K

Released

Jan 27, 2026

Compare

About MoonshotAI: Kimi K2.5

OpenRouter makes MoonshotAI: Kimi K2.5 available through a unified, OpenAI-compatible API using the model ID moonshotai/kimi-k2.5. Requests can be routed across 10 providers, including DigitalOcean, DeepInfra, SiliconFlow, AtlasCloud, Venice, StreamLake, NovitaAI, Amazon Bedrock and 2 more, with automatic failover when an endpoint is unavailable.

MoonshotAI: Kimi K2.5 accepts text and images and returns text. It has a 262,144-token context window.

On OpenRouter, MoonshotAI: Kimi K2.5 costs $0.375/M input tokens and $2.025/M output tokens, with separate rates for Cache Read at $0.203/M tokens. Effective pricing can be lower when prompt caching applies. It was released on January 27, 2026.

More models from MoonshotAI

  • Kimi K3
  • Kimi K2.7 Code
  • Kimi K2.6

Frequently asked questions

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

Kimi K2.5 costs $0.375/M input tokens and $2.025/M output tokens, with separate rates for Cache Read at $0.203/M tokens.

Kimi K2.5 has a 262,144 token context window.

Yes. Kimi K2.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Kimi K2.5 accepts text and images as input and returns text.

Kimi K2.5 is served by 10 providers on OpenRouter: DigitalOcean, DeepInfra, SiliconFlow, AtlasCloud, Venice, StreamLake, NovitaAI, Amazon Bedrock and 2 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Kimi K2.5 was released on January 27, 2026.