CrossModel
Kimi K3
moonshot/kimi-k3
Back to model catalog

Moonshot AI · Model guide

Kimi K3

Compare
moonshot/kimi-k3

Moonshot's latest open flagship is a native multimodal 2.8T-parameter MoE with 104B active, a 1M-token context window and always-on reasoning for coding, research, computer use and long-running agents.

Modalities
TextImageVideoText
Context
1M
Max output
1M
Price / 1M tokens
$ 3.00in$ 15.00out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA frontier-scale open model for real-world digital work and long-horizon multimodal agents.source

Best for

  • Long-horizon engineering · Targets repository-scale coding, terminal execution and autonomous engineering workflows.(vendor claim)source

  • Deep research · Strong official browsing and deep-search results support tool-assisted research.(vendor claim)source

  • Computer use · Evaluated on OSWorld and professional desktop task suites.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 3.00
Output$ 15.00
Cache read$ 0.30
Cache write$ 3.00
Estimate a request
$ 0.0600
Estimated cost per request
10.0K × $ 3.00
+ 2.0K × $ 15.00
≈ $ 60.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
1.0M tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Reasoning effort
low · high · max
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsgithub.comCapabilitiesgithub.com 1kimi.com 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.1
    pass_rate·Moonshot AI · 2026-07-16setup not fully disclosed
    88.3%
Agentic search
  • BrowseComp (with tools)
    accuracy·Moonshot AI · 2026-07-16setup not fully disclosed
    91.2%
  • DeepSearchQA
    f1·Moonshot AI · 2026-07-16setup not fully disclosed
    95%
Coding
  • DeepSWE
    resolved_rate·Moonshot AI · 2026-07-16setup not fully disclosed
    67.5%
  • ProgramBench
    score·Moonshot AI · 2026-07-16setup not fully disclosed
    77.8%
Computer use
  • OSWorld Verified
    success_rate·Moonshot AI · 2026-07-16setup not fully disclosed
    84.8%
Reasoning
  • Humanity's Last Exam Full (with tools)
    accuracy·Moonshot AI · 2026-07-16effort maxsetup not fully disclosed
    56%
Scientific reasoning
  • GPQA Diamond
    accuracy·Moonshot AI · 2026-07-16effort maxsetup not fully disclosed
    93.5%
Tool use
  • MCPMark Verified
    score·Moonshot AI · 2026-07-16setup not fully disclosed
    94.5%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Kimi K3?
Kimi K3 is available on CrossModel as moonshot/kimi-k3. It has a 1M-token context window and can return up to 1M tokens per request.
How much does Kimi K3 cost?
Currently $ 3.00 per 1M input tokens and $ 15.00 per 1M output tokens. Cached input is billed at $ 0.30 per 1M.
Does Kimi K3 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.