KIMI K2.6

Kimi K2.6: Moonshot AI's agentic 1T-MoE model

Released April 2026. Multimodal. Agentic 1T-parameter MoE architecture. 256K-token context. Strong at long-horizon coding and multi-agent orchestration. $0.60/$2.80 per million tokens.

Try Kimi K2.6 on Council See it in a council

Kimi K2.6 is Moonshot AI's flagship as of April 2026 — a 1-trillion-parameter Mixture-of-Experts model engineered specifically for agentic workloads. It pairs a 256K-token context window with vision input and a training regime tuned for long-horizon code editing and multi-agent orchestration. Pricing lands at $0.60 per million input tokens and $2.80 per million output, putting it between budget Grok models and the OpenAI / Anthropic flagships. The case for Kimi K2.6: agentic coding pipelines that need to plan-act-observe over many steps without losing the plot, multi-agent setups where you want one model that's actually trained for tool use and self-coordination, and Chinese-language work where Moonshot is the natural strong choice. The case against: the tool-calling ecosystem outside of agent frameworks is less mature than OpenAI's, and for one-shot reasoning prompts GPT-5.5 or Claude Opus 4.7 still produce a cleaner answer. On Council AI, Kimi K2.6 is routed through OpenRouter rather than a dedicated Moonshot provider — set OPENROUTER_API_KEY in your environment.

Specs

ProviderMoonshot AI (via OpenRouter)
Architecture1T-parameter Mixture-of-Experts
Context window262,144 tokens (256K)
MultimodalText + image input
Web searchNo native search
Price (in / out per 1M)$0.60 / $2.80
SpecialtyAgentic coding & multi-agent orchestration

Best at

Where it loses

When to pick Kimi K2.6

Frequently asked questions

What does 'agentic' mean for Kimi K2.6?

Moonshot trained K2.6 on long sequences of plan-act-observe loops rather than just one-shot prompts. That makes it materially better at maintaining a goal across many tool calls — the failure mode where models 'forget the plan' shows up less often.

How much does Kimi K2.6 cost?

$0.60 per million input tokens and $2.80 per million output tokens. Council AI bundles it inside monthly plan budgets.

Why is Kimi routed through OpenRouter?

Council AI doesn't ship a dedicated Moonshot provider — Kimi requests go through OpenRouter, which adds a small latency hop but keeps integration simple. Set OPENROUTER_API_KEY in your environment if you self-host.

What does '1T-MoE' mean?

One trillion total parameters in a Mixture-of-Experts architecture, where only a fraction of those parameters activate on any given token. That's how Kimi gets flagship-tier quality at mid-tier prices.

Does Kimi K2.6 support vision?

Yes — text and image input. Useful for agent flows that need to read screenshots, diagrams, or UI mockups mid-loop.

Should I pick Kimi K2.6 or Claude Sonnet 4.6 for coding?

For single-prompt code edits or refactors, Sonnet 4.6 still wins on patch quality. For long-running agentic coding sessions where the model has to plan over many steps, Kimi K2.6 is the more interesting pick.

Does Kimi K2.6 have web search?

Not natively. If you need fresh information, pair it with a search tool in your agent loop, or use Grok 4.3 / Gemini 3 Pro instead.