🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
M

Kimi K3

Moonshot AIModel IDkimi-k3
M

Kimi K3

Moonshot AIModel IDkimi-k3

Kimi‑K3 is Moonshot AI’s new flagship open‑weight MoE large model with 2.8 trillion total parameters. It features a 1‑million‑token ultra‑long context window and native vision multimodal input. Built on KDA hybrid linear attention architecture, it excels at large‑codebase processing, complex knowledge analysis and deep reasoning. Full weights are open‑sourced, supporting function‑call and structured output.

ModeText / Image / Video → Text
Input price$3 / 1M tokens
Output price$15 / 1M tokens
Context length1048576 tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Moonshot AI
Input modality
Text / Image / Video
Output modality
Text
Max output
1048576 tokens

Pricing

ProviderBilling typePrice summary
M
Moonshot-Custom
Per token
Input price$3per 1M tokens
Completion price$15per 1M tokens
Cache read price$0.3per 1M tokens
Cache write price$3per 1M tokens
M
Moonshot-Balanced
Per token
Input price$3per 1M tokens
Completion price$15per 1M tokens
Cache read price$0.3per 1M tokens
Cache write price$3per 1M tokens

Integration

Code Example

curl http://127.0.0.1:4179/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
openai

Supported Parameters

ParameterTypeDefaultDescription
stringmaxControls Kimi K3 reasoning effort. K3 always uses reasoning mode.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.