Kimi K2.7 Code
kimi-k2-7-codekimi-k2.7-codemoonshot/kimi-k2.7-code- π§ Coding-focused agentic model built on Kimi K2.6.
- π’ Made by Moonshot AI, released June 2026.
- π 1T total parameters, 32B active, 256K context.
- π§ Mixture-of-Experts; always operates in thinking mode.
- ποΈ Accepts text and image input for coding workflows.
- π§ Supports function-calling and web-search for agentic loops.
- π― Targets long-horizon software engineering and tool use.
- π Open weights published on Hugging Face.
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 K2.7 Code is Moonshot AI's coding-specialized member of the Kimi K2 line, trained directly on top of the general-purpose Kimi K2.6 released two months earlier, which itself succeeded Kimi K2.5. Rather than a broad capability bump, it is a focused agentic-coding release that keeps the trillion-parameter Mixture-of-Experts architecture (1T total, 32B active per token) and adds long-horizon software-engineering training for tasks like codebase analysis, debugging, refactoring, and multi-step tool use.
Architecturally it stays close to its predecessors, so existing deployment setups can largely be reused, and it ships with a 256K-token context window and always-on thinking mode. The Venice catalog lists it as supporting text and image input with function-calling and web-search capabilities, distributed here at int4 quantization.
Compared with its predecessor, Moonshot reports gains on its own coding and agent evaluations, attributing the improvement to the model's tool-calling and long-horizon software-engineering focus; these figures are vendor self-reported on internal benchmarks, so treat them as the provider's claims rather than independent results, and third-party evaluation data was limited at release.
The weights are published on Hugging Face, and the model is paired with Moonshot's coding agent tooling for terminal and multi-turn workflows.
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 K2.7 CodeΒ Β·Β Organic providers
Top providersΒ Β·Β Kimi K2.7 CodeΒ Β·Β Organic
- Super Seeder30.0%
- β² Apex Ant13.4%
- Fire Ant π₯π11.8%
- Relay Works10.9%
- Best7.3%
- Open Bird5.2%
- Others21.3%
| Provider | Health | Repβ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save | 1st token | tok/s |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Super Seeder 0xd19fβ¦41f3 | healthy | 90.57 | $34.34 | 32.92M | #3 | $1.0712 | $0.2285 | $4.9991 | β | 0.7 s | 123 |
| β² Apex Ant 0x73b4β¦e736 | healthy | 88.20 | $15.38 | 110.88M | #1 | $0.375 | $0.08 | $1.75 | β38% | β | β |
| Venice.ai Proxy 0x1f22β¦18c9 | healthy | 75.07 | β | β | #2 | $0.4125 | $0.088 | $1.925 | β31% | β | β |
| Relay Works 0x3040β¦7139 | β | 58.03 | $12.50 | 14.27M | gated | $0.39 | $0.078 | $1.95 | β35% | β | β |
| Vikey Seller 0xe4c4β¦3c7b | healthy | 30.79 | $0.00 | 2.02k | gated | $0.38 | $0.076 | $1.60 | β37% | β | β |
| Prime Seed 0x71e2β¦fc07 | healthy | 27.20 | $0.00 | 2.52k | gated | $1.05 | $0.21 | $4.40 | β | β | β |
| HallPass 0xcac8β¦71b4 | β | 20.00 | $2.32 | 2.29M | gated | $0.07 | $0.015 | $0.32 | β88% | β | β |
| klinn 0x0ee1β¦6c41 | β | 12.34 | $3.84 | 11.56M | gated | $0.0672 | $0.0571 | $0.3073 | β89% | β | β |
| dealer 0xc46eβ¦8ce6 | β | 2.11 | $1.83 | 769.57k | gated | $0.9025 | $0.1805 | $3.80 | β | β | β |
| incharge-austin 0x5938β¦ac97 | β | 0.00 | $1.09 | 487.37k | gated | $0.9025 | $0.1805 | $3.80 | β | β | β |
| surplus-hive 0x6145β¦5c58 | β | 0.00 | $3.16 | 1.29M | gated | $0.8993 | $0.8993 | $4.2535 | β | β | β |
| Open Ant 0xe4f6β¦5bc4 | β | 0.00 | $0.01 | 6.41k | gated | $0.75 | $0.16 | $3.50 | β | β | β |
| Fire Ant π₯π 0xbe05β¦bc5d | β | 0.00 | $13.56 | 16.45M | gated | $0.675 | $0.144 | $3.15 | β | β | β |
| antseed-neon-puma-944e 0x6650β¦944e | β | 0.00 | $0.01 | 33.38k | gated | $0.3069 | $0.20 | $1.4663 | β49% | β | β |
| Apex TEE Test 0xe672β¦7955 | β | 0.00 | β | β | gated | $0.2025 | $0.0432 | $0.945 | β66% | β | β |
| surplus-hive 0xe177β¦e91c | β | 0.00 | $0.15 | 391.97k | gated | $0.114 | $0.114 | $0.6649 | β81% | β | β |
| NovaRoute AI 0xc50dβ¦ed7b | β | 0.00 | $4.25 | 13.28M | gated | $0.1002 | $0.2228 | $0.4675 | β83% | β | β |
| Best 0x472fβ¦69fd | healthy | 0.00 | $8.31 | 33.49M | gated | $0.0672 | $0.0571 | $0.3073 | β89% | 0.2 s | 210 |
"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.