MoonshotAI: Kimi K2.5

moonshotai/kimi-k2.5

Created Jan 27, 2026262,144 context

$0.60/M input tokens$3/M output tokens

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.

Providers for Kimi K2.5

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Performance for Kimi K2.5

Compare different providers across OpenRouter

Apps using Kimi K2.5

Top public apps this month

Recent activity on Kimi K2.5

Total usage per day on OpenRouter

Prompt

104M

Reasoning

10.7M

Completion

6.23M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Uptime stats for Kimi K2.5

Uptime stats for Kimi K2.5 across all providers

Sample code and API for Kimi K2.5

OpenRouter normalizes requests and responses across providers for you.

OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in your request to enable reasoning, and access the reasoning_details array in the response to see the model's internal reasoning before the final answer. When continuing a conversation, preserve the complete reasoning_details when passing messages back to the model so it can continue reasoning from where it left off. Learn more about reasoning tokens.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.