Kimi K2 Turbo Preview API

Kimi K2 Turbo Preview represents the forefront of AI language model engineering focused on sophisticated understanding and reasoning across very large inputs.
Output

How to use Kimi K2 Turbo Preview API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to .

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Kimi K2 Turbo Preview API Pricing

TypePrice
Input
Output

Kimi K2 Turbo Preview vs other models

ModelInputOutputContextBest for
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Yes, Kimi K2 Turbo Preview can stream responses as they are generated.

Yes, Kimi K2 Turbo Preview supports both function calling and structured outputs.

Kimi K2 Turbo Preview was built by Moonshot AI.

Kimi K2 Turbo Preview is accessed via the v1 endpoint.

Start building with Kimi K2 Turbo Preview

Get API Key
1000+ models, one API.