kimi-k2-turbo-preview · Moonshot AI
The kimi-k2-turbo-preview model is a high-speed version of kimi-k2, with the same model parameters as kimi-k2, but the output speed has been increased from 10 tokens per second to 40 tokens per second.
The kimi-k2-turbo-preview model is a high-speed version of kimi-k2, with the same model parameters as kimi-k2, but the output speed has been increased from 10 tokens per second to 40 tokens per second.
Kimi K2 Turbo Preview has a 262,144 token context window.
On AIHubMix, Kimi K2 Turbo Preview costs $1.2 per million input tokens and $4.8 per million output tokens. Cached input reads are billed at $0.3 per million tokens.
Kimi K2 Turbo Preview accepts text input.
Kimi K2 Turbo Preview supports tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.
Kimi K2 Turbo Preview 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-turbo-preview — no other code changes needed.
Kimi K2 Turbo Preview is developed by Moonshot AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Kimi K2 Turbo Preview was released on July 8, 2025 by Moonshot AI.
Kimi K3.1 Pro is based on Moonshot AI’s Kimi K3.1, offering code generation and…
Kimi K3.1 Pro Highspeed is an accelerated serving option for Kimi K3.1 Pro, focused on…
coding-kimi-k3.1-pro is a coding preview of Kimi K3.1 Pro, available for evaluation only…
coding-kimi-k3.1-pro-highspeed is a coding preview of Kimi K3.1 Pro highspeed, available…
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work…
Use Kimi K2 Turbo Preview via the AIHubMix unified API — one interface for every major LLM.