Kimi K2.6
kimi-k2-6kimi-k2.6moonshotai/kimi-k2.6- π§ Trillion-parameter MoE, only 32B active per token^2
- π Native multimodal agentic model from Moonshot AI^1,2
- π 256K context window, native INT4 quantization^2
- ποΈ Vision integrated via 400M MoonViT encoder^2
- π§ Built for agent-swarm orchestration and tool use^2
- π¬ Thinking and non-thinking modes; preserves reasoning^1
- π Open weights under Modified MIT License^2
- π― 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 8 more models by Moonshot βKimi 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 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 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.
Daily usageΒ Β·Β Kimi K2.6Β Β·Β Organic providers
Top providersΒ Β·Β Kimi K2.6Β Β·Β Organic
- Phala48.8%
- Open Forge41.2%
- Chutes5.7%
- Venice.ai Proxy2.9%
- β² Apex Ant0.4%
- Katant0.2%
- Others0.7%
| Provider | Health | Repβ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save | 1st token | tok/s |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Phala 0x88c8β¦15d6 | healthy | 95.06 | $158.99 | 91.46M | #5 | $1.09 | $0.37 | $4.60 | β | β | β |
| Open Forge 0x1d90β¦b0aa | healthy | 91.02 | $134.05 | 190.48M | #3 | $0.50 | $0.15 | $2.40 | β23% | 1.8 s | 27 |
| Super Seeder 0xd19fβ¦41f3 | healthy | 90.57 | $0.27 | 954.80k | #4 | $0.707 | $0.1508 | $3.2994 | β | β | β |
| β² Apex Ant 0x73b4β¦e736 | healthy | 88.20 | $1.30 | 19.06M | #1 | $0.375 | $0.08 | $1.75 | β42% | β | β |
| Venice.ai Proxy 0x1f22β¦18c9 | healthy | 75.07 | $9.54 | 30.51M | #2 | $0.4125 | $0.088 | $1.925 | β37% | β | β |
| RedPill 0x7e99β¦dc4f | healthy | 65.36 | $0.00 | 2.16k | #6 | $1.09 | $0.37 | $4.60 | β | β | β |
| Relay Works 0x3040β¦7139 | β | 58.03 | $0.55 | 2.86M | gated | $0.2535 | $0.049 | $1.17 | β61% | β | β |
| HallPass 0xcac8β¦71b4 | β | 20.00 | β | β | gated | $0.055 | $0.012 | $0.24 | β92% | β | β |
| klinn 0x0ee1β¦6c41 | β | 12.34 | $0.04 | 535.43k | gated | $0.0202 | $0.0202 | $0.0945 | β97% | β | β |
| Chutes 0xded6β¦657c | β | 7.85 | $18.71 | 17.94M | gated | $0.638 | $0.0638 | $3.74 | β2% | β | β |
| bartly.eth64.de 0x666eβ¦4666 | healthy | 7.22 | $0.54 | 12.71M | gated | $0.0232 | $0.0049 | $0.1082 | β96% | β | β |
| dealer 0xc46eβ¦8ce6 | β | 2.11 | $0.01 | 2.76k | gated | $0.9025 | $0.152 | $3.80 | β | β | β |
| surplus-hive 0x6145β¦5c58 | β | 0.00 | β | β | gated | $0.9115 | $0.9115 | $4.1988 | β | β | β |
| Open Bird 0xc0f1β¦8183 | β | 0.00 | $0.08 | 192.30k | gated | $0.828 | $0.414 | $4.14 | β | β | β |
| AntFeed 0xddb6β¦1442 | β | 0.00 | β | β | gated | $0.80 | $0.80not advertised | $3.84 | β | β | β |
| Fire Ant π₯π 0xbe05β¦bc5d | β | 0.00 | $0.05 | 55.73k | gated | $0.675 | $0.14 | $3.15 | β | β | β |
| Apex TEE Test 0xe672β¦7955 | β | 0.00 | β | β | gated | $0.54 | $0.126 | $2.16 | β17% | β | β |
| antseed-neon-puma-944e 0x6650β¦944e | β | 0.00 | β | β | gated | $0.2899 | $0.22 | $1.5874 | β55% | β | β |
| minion0x 0x215eβ¦e2e3 | β | 0.00 | β | β | gated | $0.24 | $0.04 | $1.28 | β63% | β | β |
| Leftermute 0x388bβ¦5389 | β | 0.00 | β | β | gated | $0.1717 | $0.1717not advertised | $0.9403 | β74% | β | β |
| Meridian AI 0x8c8cβ¦06f5 | β | 0.00 | $0.01 | 9.30k | gated | $0.1404 | $0.1404not advertised | $0.7255 | β78% | β | β |
| Best 0x472fβ¦69fd | healthy | 0.00 | $0.15 | 995.69k | gated | $0.055 | $0.0467 | $0.24 | β92% | 0.2 s | 210 |
| NovaRoute AI 0xc50dβ¦ed7b | β | 0.00 | $0.16 | 232.55k | gated | $0.0207 | $0.6316 | $0.0964 | β97% | β | β |
"Best price" and the provider table are live Antseed catalog data (advertised $/1M tokens β or $ per generated image for unit-billed image models β not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what Antseed Desktop ships with): a trust β₯ 60 gate on the effective reputation, then cheapest-first among routable providers; 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.