Moonshot AI logoMoonshot AIText

Kimi K3

Moonshot's Kimi model for long-horizon coding and end-to-end knowledge work with vision.

Pricing

Public Core prices are current quotes, not a locked rate.

Model details
SpecificationsPriceBenchmark priceDiscount
Input300 credits / 1M tokens300 credits / 1M tokens—
Output1,500 credits / 1M tokens1,500 credits / 1M tokens—
Context window
1,000,000 tokens
2,800B

Playground

Restoring conversation…

About this model

Capabilities & specifications

Input
Text · Image
Output
Text
Context window
1,000,000 tokens

Kimi K3 runs in thinking mode for long-horizon coding and knowledge workflows. Moonshot documents native visual understanding and a context window of up to one million tokens; the technical report describes its open-weight mixture-of-experts design.

  • Long context
  • Open weights
Text chatReasoningCoding
2,800B

Build with Kimi K3

Manage API keys
  • Bash, cURL and jq
  • Set ONEASTER_API_KEY to your OneAster API key.
bash
response=$(curl 'https://api.oneaster.ai/v1/chat/completions' \
  --fail-with-body --silent --show-error --max-time 60 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${ONEASTER_API_KEY:?Set ONEASTER_API_KEY}" \
  --data-binary @- <<< '{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024,
  "stream": false
}') && jq -r '.choices[0].message.content' <<< "$response"

Questions and answers

Where do Kimi K3 specifications come from?

The references below identify the sources for this model’s capabilities. Confirm current access, request limits and pricing with your service provider before integration.

Where do Kimi K3 specifications come from?

Things to consider

Review generated results before use. Available modes and request limits depend on the service you choose; check the linked documentation before integration.

Model information sources

  • Kimi K3 reference
  • Kimi K3 reference