CrossModel
Kimi K2.6
moonshot/kimi-k2.6
Back to model catalog

Moonshot · Model guide

Kimi K2.6

Compare
moonshot/kimi-k2.6

Moonshot's open native multimodal agent model with 1T total parameters and 32B active, combining text, image and video understanding with long-horizon coding, research and tool use.

Modalities
TextImageVideoText
Context
262K
Max output
262K
Price / 1M tokens
$ 1.00in$ 4.16out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

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

VendorA native multimodal agentic model for coding, design, search and proactive tool-driven work.source

Best for

  • Agentic coding · Strong official results cover repository repair, terminal work and long-horizon software tasks.(vendor claim)source

  • Tool-assisted research · Built for browsing, deep search and multi-step information synthesis with tools.(vendor claim)source

  • Multimodal workflows · Accepts images and video for visual coding, design and agent tasks.(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$ 1.00
Output$ 4.16
Cache read$ 0.18
Cache write$ 1.00
Estimate a request
$ 0.0183
Estimated cost per request
10.0K × $ 1.00
+ 2.0K × $ 4.16
≈ $ 18.32 per 1,000 requests

Capabilities and limits

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

Context window
262.0K tokens
Max output
262.0K tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specshuggingface.coCapabilitieshuggingface.co 1kimi.com 2

Published benchmarks

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

Agentic coding
  • Terminal-Bench 2.0
    pass_rate·Moonshot AI · 2026-04-21Terminus 2setup not fully disclosed
    66.7%
Agentic search
  • BrowseComp (with tools)
    accuracy·Moonshot AI · 2026-04-21thinkingsetup not fully disclosed
    83.2%
  • DeepSearchQA
    f1·Moonshot AI · 2026-04-21setup not fully disclosed
    92.5%
Coding
  • SWE-Bench Pro
    resolved_rate·Moonshot AI · 2026-04-21setup not fully disclosed
    58.6%
  • SWE-Bench Verified
    resolved_rate·Moonshot AI · 2026-04-21setup not fully disclosed
    80.2%
Computer use
  • OSWorld Verified
    success_rate·Moonshot AI · 2026-04-21setup not fully disclosed
    73.1%
Multimodal reasoning
  • MMMU Pro
    accuracy·Moonshot AI · 2026-04-21setup not fully disclosed

    Direct-answer result; the model card also reports 80.1 with Python.

    79.4%
Reasoning
  • Humanity's Last Exam Full (with tools)
    accuracy·Moonshot AI · 2026-04-21thinkingtools: browser, code_interpreter, searchsetup not fully disclosed
    54%
Scientific reasoning
  • GPQA Diamond
    accuracy·Moonshot AI · 2026-04-21thinkingsetup not fully disclosed
    90.5%

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 K2.6?
Kimi K2.6 is available on CrossModel as moonshot/kimi-k2.6. It has a 262K-token context window and can return up to 262K tokens per request.
How much does Kimi K2.6 cost?
Currently $ 1.00 per 1M input tokens and $ 4.16 per 1M output tokens. Cached input is billed at $ 0.18 per 1M.
Does Kimi K2.6 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?
For text models, 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.