Skip to main content
Moonshot AIMediumUltra

Kimi K3

Moonshot AI's Kimi K3 served through the OpenRouter aggregator - a 2.8T-parameter open-weight multimodal reasoning model with a 1M-token context and image/video input, built for complex coding, knowledge work, and long-horizon agentic workflows. Billed at OpenRouter's actual usage cost.

5,574/27,870credits
input / output ยท per 1M tokens
1M-token context window
Multimodal input (image + video) with text output
2.8T-parameter open-weight reasoning model (reasoning_effort supported)
OpenAI-compatible API (chat completions) via /llm/openrouter/v1
Billed at OpenRouter's actual usage.cost - listed rates are estimates

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
1.0M
tokens
Max Output
33K
tokens
Training Cutoff
Not published
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens5,574$3.72
Output Tokens27,870$18.58
Cached Tokens557.4$0.37

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openrouter/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "moonshotai/kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the attached report in 5 bullets."
    }
  ],
  "max_tokens": 1024
}'

Parameters

ParameterTypeRequiredDefaultDescription
modelstringYes-Model ID in vendor/model form, e.g. "moonshotai/kimi-k3".
messagesarrayYes-Chat messages in OpenAI format (system/user/assistant roles).
temperaturenumberNo0.7Sampling temperature (0-2).
max_tokensintegerNo2048Maximum completion tokens.
streambooleanNofalseStream the response as server-sent events.

Examples

Chat completion

OpenAI-compatible chat completion request via OpenRouter

curl -X POST "https://api.core.today/llm/openrouter/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "moonshotai/kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the attached report in 5 bullets."
    }
  ],
  "max_tokens": 1024
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openrouter/v1
2Charged at OpenRouter's usage.cost x 1,858 credits/USD - the listed rates are estimates and may lag OpenRouter price changes
3Output tokens cost ~5x input - keep max_tokens tight and use reasoning_effort to control how much the model thinks on simple tasks

Use Cases

Complex coding and repository-scale refactoring
Long-horizon agentic workflows with tool use
Knowledge work over long documents, images, and video