Kimi K2.6 API

Moonshot AI's Kimi K2.6 is the most capable open-source model available today. It scores 80.2% on SWE-Bench Verified, orchestrates up to 300 parallel sub-agents, and sustains autonomous execution across 4,000+ tool calls, matching closed frontier models at a fraction of the cost.

Modalities: TextText
In / Out price: $0.95/$4per 1M
Context window: 262K tokens
Released: Apr 20, 2026

Kimi K2.6 overview

Kimi K2.6 by Moonshot AI

With a 262,144-token context window, Kimi K2.6 handles massive projects in a single pass, reducing fragmentation and improving coherence across long workflows. It also supports agent swarms up to 300 agents, making it one of the most advanced open agentic systems available today.

Kimi K2.6 specs

Model ID: moonshot/kimi-k2-6
Developer: Moonshot AI
Context window: 262,000 tokens
Max output: 260,000 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Why Kimi K2.6 matters

Kimi K2.6 is the latest model in Moonshot AI's fast-moving K2 family, a line of open-source large language models that has consistently punched well above its weight since the original K2 debuted in July 2025. Where other releases make incremental gains, each Kimi K2 update has targeted a specific capability dimension and delivered genuine, measurable improvement.

K2.6 is no different. It picks up where K2.5 left off, already the top-ranked open model on the Artificial Analysis Intelligence Index, and doubles down on the three things developers and enterprises actually care about: long-horizon autonomous coding, scalable multi-agent orchestration, and production-ready deployment at low cost.

Technical overview

Specification	Kimi K2.6
Model family	Kimi K2 series
Provider	Moonshot AI
Architecture	Mixture-of-Experts
Context window	Long-context, with 256K-class handling in technical materials
Primary use case	Coding, agents, tool workflows
Strengths	Multi-step reasoning, large projects, orchestration, research synthesis
Output style	Structured text, code, agentic actions

What Makes Kimi K2.6 Different

Every K2 release has had a defining capability. K2.6 has several that work together to enable a new category of autonomous, long-running AI tasks.

300-Agent Swarm Orchestration

K2.6 scales to 300 parallel sub-agents per run, up from 100 in K2.5. The orchestrator decomposes tasks into independent subtasks, routes them to domain-specialized agents, and synthesizes outputs autonomously. This is not a single chatbot loop. It's a coordinated AI workforce.

Long-Horizon Execution: 4,000+ Tool Calls

K2.6 supports sustained autonomous execution for 12+ hours and 4,000+ sequential tool calls without losing coherence. Most models break down after a few hundred steps. K2.6 handles end-to-end software projects from a single prompt.

Native Multimodal

Built on the MoonViT-3D vision encoder, K2.6 understands images, UI screenshots, and video workflows natively, not as an afterthought. It can generate code directly from a design mockup, analyze diagrams, and orchestrate tools based on visual inputs.

Use cases

Kimi K2.6 is documented for long-horizon coding workflows, including frontend, backend, DevOps, and performance optimization. It is also documented for autonomous agent orchestration with proactive background task execution.

The model is documented for visual reasoning with image and video inputs. It is also documented for complex multi-step problem-solving that can require hundreds of sequential tool invocations.

Capabilities

Function calling
Streaming
Structured outputs
Web search

Kimi K2.6 benchmarks by Artificial Analysis

See how Kimi K2.6 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#198 / 21940.7Output tokens / second Latency#172 / 2162.83Seconds to first token Humanity's Last Exam#62 / 45837.5%Score GPQA Diamond#30 / 43991.1%Score

Speed

Output tokens / second

Benchmark results

Compare 8 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Kimi K2.6 API pricing

Kimi K2.6 pricing in US dollars
Usage	Price	Unit
Input	$0.95	1M tokens
Output	$4	1M tokens
Cached input	$0.16	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Kimi K2.6 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Kimi K2.6	$0.95	$4
Kimi K2.7 Code HighSpeed	$1.9	$8
Kimi K3.1 Pro	$2	$10
Kimi K3	$3	$15
Kimi K3.1 Pro Highspeed	$4	$20

How to use the Kimi K2.6 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "moonshot/kimi-k2-6",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "moonshot/kimi-k2-6",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moonshot/kimi-k2-6",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Kimi K2.6 FAQ

What is the context window of Kimi K2.6?

Kimi K2.6 has a 262,000 tokens context window and can return up to 260,000 tokens.

What inputs and outputs does Kimi K2.6 support?

Kimi K2.6 takes text as input and returns text.

What is the model ID for Kimi K2.6?

Use moonshot/kimi-k2-6 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does Kimi K2.6 cost?

Kimi K2.6 costs $0.95 input and $4 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Kimi K2.6 support streaming?

Yes, Kimi K2.6 can stream responses as they are generated.

Who created Kimi K2.6?

Kimi K2.6 was built by Moonshot AI.

Does Kimi K2.6 support tool use and web search?

Yes. It supports function calling, parallel tool calls, structured outputs, and web search.

Start building with Kimi K2.6

Get API key

Kimi K2.6 API

moonshot/kimi-k2-6

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "moonshot/kimi-k2-6",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "moonshot/kimi-k2-6",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moonshot/kimi-k2-6",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Kimi K2.6 API

Kimi K2.6 overview

Kimi K2.6 by Moonshot AI

Kimi K2.6 specs

Why Kimi K2.6 matters

Technical overview

What Makes Kimi K2.6 Different

300-Agent Swarm Orchestration

Long-Horizon Execution: 4,000+ Tool Calls

Native Multimodal

Use cases

Capabilities

Kimi K2.6 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Kimi K2.6 API pricing

Kimi K2.6 vs other models: token prices

How to use the Kimi K2.6 API

Build with your agent

1Get your API key

2Make your first request

Related articles

Kimi K2.6 FAQ

Start building with Kimi K2.6

Kimi K2.6 API

Build with your agent

1Get your API key

2Make your first request

Kimi K2.6 API

Kimi K2.6 overview

Kimi K2.6 by Moonshot AI

Kimi K2.6 specs

Why Kimi K2.6 matters

Technical overview

What Makes Kimi K2.6 Different

300-Agent Swarm Orchestration

Long-Horizon Execution: 4,000+ Tool Calls

Native Multimodal

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Kimi K2.6 API pricing

Kimi K2.6 vs other models: token prices

How to use the Kimi K2.6 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Kimi K2.6

Kimi K3.1 Pro

Kimi K3.1 Pro Highspeed

Kimi K3

V3 Large

DeepSeek V4 Pro

GLM-5

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Kimi K2.6 FAQ

Start building with Kimi K2.6