kimi-k2.5

kimi-k2.5 is a advanced-tier language model from Moonshot AI. kimi-k2.5 is a proprietary model available exclusively through Moonshot AI's API. The Kimi K2 family is Moonshot AI's model series for this capability tier.

kimi-k2.5 is priced at $0.6/1M input tokens and $3/1M output tokens. Output tokens are 5× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, kimi-k2.5 costs approximately $2.10 per 1,000 API calls. Moonshot AI does not publish a prompt caching rate for this model, so repeated long contexts are billed at the standard $0.6/1M input rate.

Its 262K-token context window is in the top tier for production models, enabling full-document analysis, long multi-turn conversations, and large codebase understanding without chunking. Median latency (P50 time-to-first-token) is approximately 700ms — suitable for interactive applications where sub-second response is acceptable. Throughput is approximately 110 tokens/second — adequate for streaming at comfortable reading speed. Maximum output length is 33K tokens — sufficient for long-form content generation, detailed code files, and extended reports.

kimi-k2.5 is best suited to chat, coding, vision. Supported capabilities include vision inputs (images alongside text), function calling / tool use for agentic workflows, streaming token output for real-time UIs. Vision support enables document analysis, screenshot understanding, diagram interpretation, and visual question answering — images are converted to tokens at the standard input rate based on resolution. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how kimi-k2.5 compares to similar models across these dimensions.

kimi-k2.5 sits in the advanced tier — strong general-purpose models balancing capability and cost, suitable for most production applications. Unlike open-weights alternatives, kimi-k2.5 is only available via Moonshot AI's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing kimi-k2.5 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (85/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.