Models / Kimi K2.7 Code

1T total params, 32B active per token (MoE) - 384 experts, 8 selected + 1 shared, 61 layers, 7168 attention hidden dimension, 64 heads, MLA, SwiGLU activation, 160K vocabulary. Built on Kimi K2.6 as a coding/agentic specialization, not a general chat replacement.

  • Context and I/O: native 256K context (262,144 tokens via API); native vision and multimodal tool use (PNG/JPEG/WebP/GIF images, MP4/MOV/AVI video).
  • Reasoning and tools: always-on thinking mode; Moonshot claims ~30% fewer thinking tokens than K2.6. Native function/tool calling with MCP support.

Open weights under a Modified MIT license on HuggingFace at moonshotai/Kimi-K2.7-Code. The license requires products with >100M monthly active users or >$20M monthly revenue to display “Kimi K2.7 Code” prominently.

Cloud-only for most users. A 1T-parameter MoE needs server-class hardware; there is no published Unsloth GGUF or consumer-grade quantization, so self-hosting is not practical on a workstation or DGX Spark. Run it via the Kimi API, OpenRouter, or vLLM/SGLang on a cluster.

Cloud API: $0.95/1M input, $4.00/1M output, $0.19/1M cache-hit input. A kimi-k2.7-code-highspeed variant runs at ~180 tok/s (up to 260 tok/s in short contexts) for 2x the price.

Benchmarks (Moonshot self-reported): Kimi Code Bench v2 62.0, Program Bench 53.6, MLS Bench Lite 35.1, Kimi Claw 24/7 Bench 46.9, MCP Atlas 76.0, MCP Mark Verified 81.1.

AI-generated content marks

This model embeds text watermarks in generated text and adds C2PA provenance metadata to supported files such as .png, .jpg, and .svg. Marks can be lost through editing, screenshots, or format conversion, so their absence does not prove a file is human-made.

Provider transparency docs →

coding reasoning agentic vision
Parameters
1000.0B
Context
256k
License
other
Developer
Moonshot AI
Origin
🇨🇳 China
Released
Jun 2026

Benchmark scores

Vendor-reported - from the developer's own model card / tech report

MCP-Atlas
76.0

Vendor-reported - from the developer's own model card / tech report

Ran this model on your own hardware? Join free and add your measured tok/s to the community numbers.

Score per dollar

131 pts per $/M input

general_score (86) divided by cheapest input price ($0.66/M). Higher is better value. See live pricing.

Related models

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Or run it in the cloud

Live per-provider pricing, throughput and uptime - refreshed about 23 hours ago via OpenRouter. Click a column to sort.

Provider Type Input $/M Output $/M Cache $/M Tok/s Latency Uptime Value
CoreWeave
API 0.71 3.50 0.150 - - 100.00% best uptime
StreamLake
API 0.71 3.00 0.142 - - 100.00%
Venice
API 0.75 3.50 0.160 - - 100.00%
ModelRun
API 0.85 3.75 0.160 - - 100.00%
Cloudflare
API 0.95 4.00 0.190 - - 100.00%
BaseTen
API 0.95 4.00 0.160 - - 99.92%
SiliconFlow
API 0.86 3.80 0.180 - - 99.91%
Moonshot AI
API 1.90 8.00 0.380 - - 99.79%
Novita
API 0.91 3.84 0.182 - - 99.76%
GMICloud
API 0.95 4.00 0.190 - - 99.67%
Nebius
API 0.95 4.00 0.180 - - 99.44%
Inceptron
API 0.66 3.30 0.180 - - 99.00% cheapest
DeepInfra
API 0.68 3.40 0.136 - - 98.46%
Alibaba
API 0.95 4.00 0.190 - - 97.26%
Fireworks avoid
API 0.95 4.00 0.190 - - 88.04%
Sub - - - - - - $10.00/mo Go ($5 first month)

Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.

Detailed API pricing page + JSON endpoint →

See who runs Moonshot AI in production →

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...