MoonshotAI: Kimi K3
Chatmoonshotai/kimi-k3Kimi K3 is Moonshot AI's flagship model, a 2.8T-parameter MoE released on 2026-07-16 with a 1M-token context window and built-in thinking exposed through reasoning_content. It supports vision input, tool use, prompt caching, and web search, making it suited to long-horizon agents that need to read documents and images, search the web, and reason across very large inputs. It runs directly on the OpenAI protocol, and over the Anthropic protocol no explicit thinking parameter is required. Context: 1M tokens, output: 1M. Input is $3/M tokens, with cache reads at $0.30/M. Available via OpenAI and Anthropic protocols through Ofox.
Context Window
1M
Max Output Tokens
1M
Released
2026-07-16
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb Search
Available Providers
Moonshot
Supported Protocols
openaianthropic
Providers
Moonshot
Input Tokens
$3/M
Output Tokens
$15/M
Cache Read
$0.3/M
Web Search
$0.0043/R
Protocols
openai
/v1/chat/completionsanthropic
Code Examples
from openai import OpenAIclient = OpenAI(base_url="https://api.ofox.run/v1",api_key="YOUR_OFOX_API_KEY",)response = client.chat.completions.create(model="moonshotai/kimi-k3",messages=[{"role": "user", "content": "Hello!"}],)print(response.choices[0].message.content)
Uptime & Status
Related Models
Frequently Asked Questions
MoonshotAI: Kimi K3 on Ofox.ai costs $3/M per million input tokens and $15/M per million output tokens. Pay-as-you-go, no monthly fees.
MoonshotAI: Kimi K3 supports a context window of 1M tokens with max output of 1M tokens, allowing you to process large documents and maintain long conversations.
Simply set your base URL to https://api.ofox.run/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.
MoonshotAI: Kimi K3 supports the following capabilities: Vision, Function Calling, Reasoning, Prompt Caching, Web Search. Access all features through the Ofox.ai unified API.