Kimi K31 Pro Think beyond text.

Try Kimi K31 Pro

K31 / API

Kimi K31 Pro API guide

Use your account API key to call Kimi K31 Pro from your own application. Browser playground and API calls share a credit balance.

  1. Sign in with Google, then create an API key in account settings.
  2. Send your model ID and messages to the endpoint below. Keep stream set to false.
  3. For images use image_url; for audio use input_audio with raw base64 data and a format. Audio is transcribed before Kimi inference and included in billing.
  4. Read usage and credits_used in the response. The service reserves credits before inference, settles actual usage and releases unused credits.
Manage API keys
curl https://k31.pro/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moonshotai/kimi-k3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Explain this idea clearly."
    }
  ],
  "max_completion_tokens": 64,
  "stream": false
}'

Request limits

Up to 40 messages, 256 KiB text, 8 embedded files, 4 MiB per file and 8 MiB total. Responses are capped at 8,192 tokens. A 64-token response limit is the playground default; increase it for longer answers.

Audio is transcribed before Kimi inference. Transcription costs are included in billing.

Explore model details