Long context

kimi-k3 API pricing

Moonshot's Kimi series — long context and agentic strength.

Model IDkimi-k3

Get API Key Try it Quick Start

Call summary

Input

$3.00/ 1M tokens

Cache write $3.00

Output

$15.00/ 1M tokens

Cache read $0.30

Context Window

1.05M

Max output

N/A

API Endpoints

Available Configurations

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Not enough production samples yet

This window needs at least 100 eligible requests across 5 independent principals. Metrics appear automatically after that threshold is met.

kimi-k3 API endpoints

One API key — call this model through any of the endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Docs

Call kimi-k3 from your code

The same API key works across every endpoint below.

Endpoint

/v1/chat/completions

Model ID

kimi-k3

Routing mode

chat_completions

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key