Kimi K2 Turbo Preview

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.

API Pricing

Input$1.2 / 1M tokens
Output$4.8 / 1M tokens
Cache read$0.3 / 1M tokens

Specifications

Context262K tokens
Modalitiestext
Featurestool calling, function calling, structured outputs

Frequently asked questions

What is Kimi K2 Turbo Preview?

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.

What is the context length of Kimi K2 Turbo Preview?

Kimi K2 Turbo Preview has a 262,144 token context window.

How much does Kimi K2 Turbo Preview cost?

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.

What modalities does Kimi K2 Turbo Preview support?

Kimi K2 Turbo Preview accepts text input.

What capabilities does Kimi K2 Turbo Preview support?

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.

How do I call Kimi K2 Turbo Preview via API?

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.

Who created Kimi K2 Turbo Preview?

Kimi K2 Turbo Preview is developed by Moonshot AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More models from Moonshot AI

See all Moonshot AI models →

Kimi K3

by Moonshot AI

Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work…

$3/1M in · $15/1M out
1,048,576 tokens context

Coding Kimi K3

by Moonshot AI
$0.44/1M in · $1.613/1M out
1,048,576 tokens context

Coding Kimi K3 (free)

by Moonshot AI

coding-kimi-k3-free is the open and free version of coding-kimi-k3. To maintain reliable…

1,048,576 tokens context

Kimi K2.7 Code

by Moonshot AI

Kimi K2.7 Code is Kimi’s most intelligent Coding model, capable of completing programming…

$0.95/1M in · $3.999/1M out
262,144 tokens context

Kimi K2.7 Code Highspeed

by Moonshot AI

High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180…

$1.9/1M in · $7.999/1M out
262,144 tokens context

Kimi K2.6

by Moonshot AI

Kimi K2.6 is Kimi's latest and most intelligent model, with stronger and more stable…

$0.95/1M in · $3.999/1M out
262,144 tokens context

Use Kimi K2 Turbo Preview via the AIHubMix unified API — one interface for every major LLM.