Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for moonshotai

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6

Model weights
Compare

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.

Modalities

In / Out Price

41% off

$0.5596 / $2.356per 1M

Context

262K

Released

Apr 20, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
41% off
$0.95$0.5596$4.00$2.356$0.16$0.094240.97s49 tps
99.96%
$0.56$3.39$0.170.43s114 tps
99.76%
$0.5684$3.332$0.09251.07s65 tps
98.63%
$0.58$3.40$0.0582.15s39 tps
99.13%
37% off
$0.95$0.5985$4.00$2.52$0.16$0.10081.57s31 tps
97.85%
$0.65$3.41$0.150.25s240 tps
99.97%
$0.70$3.50$0.350.26s23 tps
98.47%
$0.75$3.50$0.150.88s25 tps
99.71%
$0.75$3.50$0.161.11s26 tps
99.58%
$0.75$3.50$0.161.18s38 tps
99.87%
$0.77$3.40$0.141.08s40 tps
99.74%
$0.80$3.40$0.161.31s34 tps
99.49%
$0.95$4.00$0.192.75s38 tps
99.27%
$0.95$4.00$0.160.85s35 tps
99.92%
$0.95$4.00$0.162.34s27 tps
99.83%
$0.95$4.00$0.161.88s28 tps
91.71%
$1.09$4.60$0.371.60s18 tps
89.62%
$0.95$4.00$0.162.55s20 tps
93.43%
$0.95$4.00$0.160.53s68 tps
0.00%
$0.95$4.00$0.16----
--

Throughput

240tok/s

P50, best across providers

Latency

0.25s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
SiliconFlow
88.2%76.8%
Moonshot AI
86.4%78.1%
CoreWeave
85.3%76.9%
Decart
85.7%76.0%
StreamLake
83.8%77.8%
+14 more providers
Uptime (3d)

100.00%

Availability (3d)

98.43%

Availability over the last 3 days

Last 72 hours
Availability 98.43%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.93%
Without Routing
95.06%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
53.6Btokens
2.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
44Btokens
3.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
38.3Btokens
4.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
24Btokens
5.
Favicon for https://motor-de-busca/
motor-de-busca
new
7.76Btokens

Frequently asked questions

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces.

Kimi K2.6 costs $0.5596/M input tokens and $2.356/M output tokens, with separate rates for Cache Read at $0.09424/M tokens.

Kimi K2.6 has a 262,144 token context window. It supports up to 262,144 completion tokens.

Yes. Kimi K2.6 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Kimi K2.6 accepts text and images as input and returns text.

Kimi K2.6 is served by 20 providers on OpenRouter: Baidu Qianfan, Inceptron, Decart, Chutes, StreamLake, CoreWeave, Crusoe, DeepInfra and 12 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Kimi K2.6 was released on April 20, 2026.