Standard Compute
← All models

Kimi K2.6

Frontier

Moonshot's flagship open-weight generalist — broad capability with a long context.

Moonshot AI
Maker
87/100
Overall
72
Value score
$1.27
Blended /1M
262K
Context
Open
Weights
Pricing: $0.65 in · $2.72 out / 1M tokens · synced from OpenRouter · updated 2026-08-02

Scorecard

Output Quality8.6/10 · 75% community
Agentic Ability8.8/10 · 76% community
Speed7.6/10 · 70% community
Value for $9.2/10 · 78% community
Reliability9.0/10 · 77% community

Kimi K2.6 is Moonshot's flagship general open-weight model: a capable all-rounder for reasoning, writing, and agentic work with a 262K context. Open weights and competitive pricing make it a strong general choice for open agent stacks.

Strengths
  • Capable open-weight generalist
  • Long context
  • Good agentic behaviour
Trade-offs
  • A step behind the closed flagships
  • Pricier than the cheapest open models

Agents that run Kimi K2.6 well

A flagship-feel open-weight generalist.

Best model for ClineBest model for AiderBest model for OpenCodeBest model for OpenClawBest model for Hermes

Kimi K2.6 FAQ

Is Kimi K2.6 good for AI agents?
A flagship-feel open-weight generalist. On our editorial scoring it rates 8.8/10 for agentic ability and 8.6/10 for output quality. Capable open-weight generalist.
How much does Kimi K2.6 cost?
Via OpenRouter, Kimi K2.6 is priced at $0.65 in · $2.72 out / 1M tokens — a blended rate of about $1.27 per 1M tokens for typical input-heavy agent use.
What is Kimi K2.6's context window?
Kimi K2.6 has a 262K-token context window. Moonshot AI is the maker.
Is Kimi K2.6 open source?
Yes — Kimi K2.6 ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of Kimi K2.6?
The main trade-offs: a step behind the closed flagships; pricier than the cheapest open models. It's strongest for a flagship-feel open-weight generalist.

Kimi K2.6 compared

Kimi K2.6 vs Fable 5Kimi K2.6 vs SolKimi K2.6 vs Opus 4.8Kimi K2.6 vs GPT-5.5Kimi K2.6 vs Gemini 3.1 ProKimi K2.6 vs GLM 5.2Kimi K2.6 vs Qwen3.7 MaxKimi K2.6 vs DeepSeek V4 Pro

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Fable 5 · GPT-5.6 Sol

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. No usage limits. One flat bill.

Free trial · no card · plans from $39/mo

Free trial No credit card needed Billing by Stripe2,500+ agent users