Tokely
All models

Moonshot

kimi-k2

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

textUpstream unavailablefunction tools
kimi-k2

Tokely price / 1M tokens

$1.65input
$1.65cached input
$6.6output

USD · Price estimate · Updated 2026-10-06

OpenRouter reference$0.57 input · $2.3 output / 1M tokensStandard listed rates · 2026-10-06

Context window

131,072tokens · model specification

Model max output

98,304tokens

First request

Upstream unavailable. This entry is not currently enabled in the Tokely API.

Compare nearby prices

USD per million tokens. Compare price and context; these are not quality benchmarks.
ModelInputOutputContext
kimi-k2Moonshot · this model$1.65$6.6131,072
MiniMax-M3MiniMax$1.65$6.61,048,576
glm-4.5ChatGLM$1.65$6.6131,072
glm-4.6ChatGLM$1.65$6.6204,800
gpt-oss-120bOpenAI$1.65$6.6131,072

Capabilities & limits

Provider
Moonshot
API model ID
kimi-k2
Category
Text
Endpoints
POST /v1/chat/completions
Model modalities
text. Tokely currently accepts text input.

The context includes your instructions, conversation history, tool definitions and generated output. Keep the input and requested output within the model’s context window.

OpenRouter model reference

Frequently asked questions

How much does kimi-k2 cost?

$1.65 per million input tokens, $6.6 per million output tokens and $1.65 per million cached input tokens. This is an estimate; API access is currently unavailable.

Do I need a separate Moonshot account?

Use your Tokely API key and balance. A separate provider key is not required.

What is the context window?

131,072 tokens, including input and output. The Tokely request body and output limits listed above also apply.

Related versions

kimi-k2-0711-previewMoonshotkimi-k2.5Moonshotkimi-k2.62026-04-20kimi-k2.7-codeMoonshot