kimi-k2.5 · Moonshot AI
Kimi K2.5 is the smartest model of Kimi to date, achieving open-source state-of-the-art (SoTA) performance in Agent, coding, visual understanding, and a series of general intelligent tasks. At the same time, Kimi K2.5 is also the most versatile model of Kimi so far, with a native multimodal architecture design that supports both visual and text input, thinking and non-thinking modes, as well as dialogue and Agent tasks.
Kimi K2.5 is the smartest model of Kimi to date, achieving open-source state-of-the-art (SoTA) performance in Agent, coding, visual understanding, and a series of general intelligent tasks. At the same time, Kimi K2.5 is also the most versatile model of Kimi so far, with a native multimodal architecture design that supports both visual and text input, thinking and non-thinking modes, as well as dialogue and Agent tasks.
Kimi K2.5 has a 256,000 token context window.
On AIHubMix, Kimi K2.5 costs $0.6 per million input tokens and $3 per million output tokens. Cached input reads are billed at $0.105 per million tokens.
Kimi K2.5 accepts text, image and video input.
Kimi K2.5 supports thinking, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.
Kimi K2.5 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to kimi-k2.5 — no other code changes needed.
Kimi K2.5 is developed by Moonshot AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work…
coding-kimi-k3-free is the open and free version of coding-kimi-k3. To maintain reliable…
Kimi K2.7 Code is Kimi’s most intelligent Coding model, capable of completing programming…
High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180…
Kimi K2.6 is Kimi's latest and most intelligent model, with stronger and more stable…
Use Kimi K2.5 via the AIHubMix unified API — one interface for every major LLM.