Skip to model information

Kimi K2.7 Code HighSpeed

Available

A Moonshot AI model with a 256K-token context window, image input and tool calling. Available on the Kimi Open Platform API.

Access details: Kimi Open Platform API

The model ID to use in API requests.

kimi-k2.7-code-highspeed
Updated Oct 1, 2026

Capabilities & limits

Context window
256K
Maximum output
Not published
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$1.90
Output
$8.00

Standard rates per million tokens. Discounts and long-context rates, where offered, are on Moonshot AI's pricing page.

Full rate card 3 rates

All prices in USD.

Input tokens (cache miss)

$1.90 per 1M tokens

Cached input tokens

$0.38 per 1M tokens
  • cache hit

Output tokens

$8.00 per 1M tokens

Prices exclude applicable taxes. The Batch pricing page lists no high-speed batch price.

Price history
Oct 1, 2026

Input $1.90 per million tokens

Oct 1, 2026

Output $8.00 per million tokens

Technical details

Parameters
1T
Active parameters
32B
Architecture
Mixture-of-Experts (MoE)
Training / knowledge cutoff
Not published
Input modalities
Text, image, video
Output modalities
Text

From Moonshot AI

How they describe it

High-Speed version of Kimi K2.7 Code model

Release & lifecycle

First available
—
available
As of Oct 1, 2026

Considering a switch?

Specs only go so far. Try both on your own tasks and compare quality, speed and cost.

Compare with GPT-6 Sol →

Prices and availability as of October 20, 2026. Moonshot AI's own pages have the latest.