- 🧠 Trillion-parameter MoE, only 32B active per token^2
- 🆕 Native multimodal agentic model from Moonshot AI^1,2
- 📏 256K context window, native INT4 quantization^2
- 👁️ Vision integrated via 400M MoonViT encoder^2
- 🔧 Built for agent-swarm orchestration and tool use^2
- 💬 Thinking and non-thinking modes; preserves reasoning^1
- 📚 Open weights under Modified MIT License^2
- 🎯 Targets long-horizon coding and autonomous execution^2
Moonshot is an AI research lab known for developing the Kimi family of large language models. The organization has gained recognition for building capable reasoning-oriented models, with the Kimi line representing its flagship series of text generation systems.
Explore 4 more models by Moonshot →Kimi K2.6 is Moonshot AI's open-weight, native multimodal agentic model, released April 20, 2026 and built on a sparse Mixture-of-Experts architecture.^2 It carries 1 trillion total parameters but activates only about 32 billion per token.^2 Vision is integrated architecturally through a 400M-parameter MoonViT encoder, letting the model accept text and images.^2 It exposes a 256K-token context window and ships with INT4 quantization.^2
Compared with its same-family predecessor [[sibling:kimi-k2-5|Kimi K2.5]], K2.6 retains the trillion-parameter MoE design and 256K context window while shifting its focus toward long-horizon coding, coding-driven design, and agent-swarm orchestration. Both belong to Moonshot's Kimi K series, and K2.6 is positioned as the newer iteration aimed at proactive, autonomous multi-step execution.
The model supports function calling, web search, and a mode that preserves reasoning across multi-turn interactions, alongside separate thinking and non-thinking responses.^1 Its open weights are distributed under a Modified MIT License,^2 and it is available through Hugging Face and inference providers.^1,2
Within the broader lineage, Moonshot later shipped the coding-focused [[sibling:kimi-k2-7-code|Kimi K2.7 Code]] in a separate family. K2.6 remains aimed at developers who need open weights, a large context window, and large-scale agent orchestration.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | Input $/M | Cached $/M | Output $/M | Categories | API |
|---|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 99 | #4 | $0.425 | $0.11 | $2.3275 | chat,reasoning,coding,vision,multimodal,web-search | openai-chat-completions |
| ▲ Apex Ant 0x73b4…e736 | 83 | #3 | $0.3375 | $0.0574 | $1.575 | chat,open-source,writing,coding,creative,vision,multimodal,reasoning,long-context,agents | openai-chat-completions |
| Open Forge 0x1d90…b0aa | 75 | #5 | $0.50 | $0.15 | $2.40 | math,coding,study | openai-chat-completions |
| surplusintelligence.ai 0x0e49…8927 | 68 | #1 | $0.225 | $0.048 | $1.05 | agents,anon,chat,cheap,code,coding,developer,frontier,function-calling,multimodal,reasoning,research,tasks,tools,vision,web-search | openai-chat-completions |
| Open Bird 0xc0f1…8183 | 64 | #2 | $0.3325 | $0.056 | $1.40 | chat,long-context | openai-chat-completions |
| NovaRoute AI 0xc50d…ed7b | 60 | gated | $0.6316 | $0.6316 | $3.7026 | chat,coding,code,reasoning,tasks,kimi,value,surplus,openai-compatible,low-cost,verified,github,response-auth,base-usdc,monitored | openai-chat-completions |
| Chutes 0xded6…657c | 43 | gated | $0.638 | $0.0638 | $3.74 | chat,reasoning,coding,vision,tee | openai-chat-completions |
| Super Seeder 0xd19f…41f3 | 40 | gated | $0.375 | $0.08 | $1.75 | chat,coding,reasoning,vision,multimodal,tools,cheap | openai-chat-completions |
| Fire Ant 🔥🐜 0xbe05…bc5d | 37 | gated | $0.6662 | $0.144 | $3.15 | base-usdc,chat,code,coding,github,json,kimi,low-cost,math,monitored,openai-compatible,reasoning,response-auth,surplus,tasks,tee,tools,value,verified,vision | — |
| D5V1N2 0xd5e7…7be0 | 26 | gated | $0.20 | $0.20 | $1.00 | chat,coding,reasoning,research,cheap,router,fallback,kimi | openai-chat-completions |
| Meridian AI 0x8c8c…06f5 | 22 | gated | $0.1404 | $0.1404 | $0.7255 | chat,coding | openai-chat-completions |
| bartly.eth64.de 0x666e…4666 | 10 | gated | $0.30 | $0.06 | $1.50 | — | openai-chat-completions |
| antseed-neon-puma-944e 0x6650…944e | 3 | gated | $0.2899 | $0.22 | $1.5874 | chat,coding,math | openai-chat-completions |
| antseed-opal-badger-2580 0xc85d…2580 | 1 | gated | $0.375 | $0.375 | $1.75 | chat | openai-chat-completions |
| minion0x 0x215e…e2e3 | 1 | gated | $0.24 | $0.04 | $1.28 | chat,coding,math,finance,fast | openai-chat-completions |
| AntFeed 0xddb6…1442 | 0 | gated | $0.80 | $0.80 | $3.84 | chat,reasoning,long-context | openai-chat-completions |
| Apex TEE Test 0xe672…7955 | 0 | gated | $0.54 | $0.126 | $2.16 | chat,open-source,writing,coding,creative,vision,multimodal,reasoning,long-context,agents | openai-chat-completions |
| Skeffo Inference 0x1af8…e2b5 | 0 | gated | $0.50 | $0.50 | $3.25 | chat,vision,reasoning,agent,function-calling | openai-chat-completions |
| Leftermute 0x388b…5389 | 0 | gated | $0.1717 | $0.1717 | $0.9403 | chat,coding,json,tools | openai-chat-completions |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.