← All models
Online

Kimi K3

Moonshot AI · OpenAI-compatible API

moonshotai/kimi-k3

USD / 1M tokens

Input$2.39
Cached Input$0.24
Output$11.99
Context
1M
Tool Calling
✓
Reasoning
✓
Vision
✓
Streaming
✓
OpenAI-compatible API
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/kimi-k3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Overview

Text input, streaming and structured outputs; up to 999,999 output tokens.

Pricing

Prices in USD per 1M tokens.

Input$2.39
Cached Input$0.24
Output$11.99

API

Base URL
https://api.iteracompute.com/v1
Endpoint
POST /v1/chat/completions
Model ID
moonshotai/kimi-k3
Authentication
Authorization: Bearer ITERACOMPUTE_API_KEY

View Docs

Use Cases

Long-context coding, knowledge work and agentic reasoning.

FAQ

How do I use Kimi K3 with the OpenAI SDK?

Set base_url to https://api.iteracompute.com/v1 and model to moonshotai/kimi-k3. Authenticate with your IteraCompute API key.

What does Kimi K3 cost?

Input $2.39, cached input $0.24, output $11.99 per 1M tokens, in USD.

What context length is available?

1,048,576 tokens.