Moonshot AI model product
Kimi K2.7 Code
6.
Updated Aug 12, 2026. Default version: Kimi K2.7 Code
LLMBoard score66.8Kimi K2.7 Code
Coverage20%7 benchmark families
Context window262.1KTokens
Official input price$0.95Moonshot AI API
Kimi K2.7 Code Specifications
Technical details for the model's default version.
- Version
- Kimi K2.7 Code
- Released
- Jun 12, 2026
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- 1T
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Modified MIT License
Kimi K2.7 Code Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Kimi K2.7 Code Benchmark Results
Benchmark scores for Kimi K2.7 Code.
| Kimi Claw 24/7 Bench | 46.9% | 01 | 1 | 100.0% | C | |
| MCP-Mark | 81.1% | 01 | 8 | 100.0% | C | |
| Kimi Code Bench v2 | 62.0% | 02 | 2 | 0.0% | C | |
| MLS-Bench Lite | 35.1% | 03 | 3 | 0.0% | C | |
| Program Bench | 53.6% | 03 | 5 | 50.0% | C | |
| FrontierCode 1.1 | 30.1% | 11 | 15 | 28.6% | B | |
| MCP Atlas | 76.0% | 11 | 31 | 66.7% | C | |
| DeepSWE 1.1 | 31.0% | 18 | 20 | 10.5% | B | |
| LiveBench | 71.9% | 27 | 38 | 29.7% | B |
Kimi K2.7 Code Arena Results
Preference and agent-evaluation results for the default version.
| agent tool hallucination | overall | 05 | 0.0 | N/A | 364.3K | |
| agent task outcome explicit | overall | 18 | 0.0 | N/A | 5.4K | |
| agent praise complaint | overall | 22 | 0.0 | N/A | 1.6K | |
| agent | overall | 23 | 0.0 | N/A | 390.5K | |
| agent steerability | overall | 29 | -0.0 | N/A | 6.6K | |
| agent bash recovery steps | overall | 35 | -0.0 | N/A | 12.6K | |
| webdev | overall | 36 | 1473.6 | 4,675 | N/A |
Kimi K2.7 Code Runtime Performance
Provider-specific output speed and catalog latency for Kimi K2.7 Code. Runtime does not affect the capability score.
| Together | 694.444 tok/s | 0.238 s | 262.1K | 131.1K | |
| Moonshot AI | 125.62 tok/s | 1.108 s | 262.1K | 262.1K | |
| Novita | 114.832 tok/s | 2.124 s | 262.1K | 262.1K | |
| DeepInfra | 13.58 tok/s | 1.563 s | 262.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Kimi K2.7 Code Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.95 input, $4 output per 1M
- Official provider
- Moonshot AI
- Lowest third-party
- From $0.275 input, $1.1 output per 1M via routing.run
- Tracked offerings
- 59
| Kenari | kimi-k2-7-code | global | N/A | N/A | 262.1K | |
| Alibaba Token Plan | kimi-k2.7-code | global | N/A | N/A | 262.1K | |
| Umans AI Coding Plan | umans-kimi-k2.7 | global | N/A | N/A | 262.1K | |
| Kimi For Coding | kimi-for-coding | global | N/A | N/A | 262.1K | |
| Alibaba Token Plan (China) | kimi-k2.7-code | global | N/A | N/A | 262.1K | |
| routing.run | kimi-k2.7-code | global | $0.275 | $1.1 | 200K | |
| CrofAI | kimi-k2.7-code | global | $0.55 | $2.25 | 262.1K | |
| Deep Infra | moonshotai/Kimi-K2.7-Code | global | $0.68 | $3.4 | 262.1K | |
| Ambient | moonshotai/kimi-k2.7-code | global | $0.70 | $3.5 | 262.1K | |
| OpenRouter | moonshotai/kimi-k2.7-code | global | $0.70 | $3.5 | 262.1K | |
| Weights & Biases | moonshotai/Kimi-K2.7-Code | global | $0.71 | $3.5 | 262.1K | |
| ai& | moonshotai/kimi-k2.7-code | global | $0.75 | $3.5 | 262.1K | |
| Inceptron | moonshotai/Kimi-K2.7-Code | global | $0.75 | $3.5 | 262.1K | |
| Venice AI | kimi-k2-7-code | global | $0.75 | $3.5 | 256K | |
| Cortecs | kimi-k2.7-code | global | $0.75 | $3.5 | 262.1K | |
| AKI.IO | kimi-k2.7-code-1100b | global | $0.86 | $3 | 262.1K | |
| GreenPT | kimi-k2.7-code | global | $0.9006 | $4.39 | 262.1K | |
| Fireworks AI | accounts/fireworks/models/kimi-k2p7-code | global | $0.95 | $4 | 262K | |
| OpenCode Go | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Baseten | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262K | |
| Nebius Token Factory | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| NanoGPT | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| LLM Gateway | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| OpenCode Zen | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Cloudflare Workers AI | @cf/moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| GitHub Copilot | kimi-k2.7-code | global | $0.95 | $4 | 256K | |
| ClinePass | cline-pass/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Pioneer | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| ZenMux | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| EmpirioLabs AI | kimi-k2-7-code | global | $0.95 | $4 | 256K | |
| Together AI | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| Moonshot AI (China) | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Azure | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Neuralwatt | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| AIHubMix | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Umans AI | umans-kimi-k2.7 | global | $0.95 | $4 | 262.1K | |
| Synthetic | hf:moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| Kilo Gateway | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Merge Gateway | moonshot/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Charm Hyper | kimi-k2.7-code | global | $0.95 | $4 | 256K | |
| Vercel AI Gateway | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 256K | |
| NovitaAI | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Hugging Face | moonshotai/Kimi-K2.7-Code | global | $0.95 | $4 | 262.1K | |
| Perplexity Agent | moonshot-ai/kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| Moonshot AI | kimi-k2.7-code | global | $0.95 | $4 | 262.1K | |
| HPC-AI | moonshotai/kimi-k2.7-code | global | $0.95 | $4 | 256K | |
| Databricks | databricks-kimi-k2-7-code | global | $0.95 | $4 | 262.1K | |
| CrossModel | moonshot/kimi-k2.7-code | global | $1 | $4.16 | 262K | |
| TensorX | moonshotai/kimi-k2.7-code | global | $1.25 | $4.5 | 262.1K | |
| NanoGPT | moonshotai/kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| LLM Gateway | kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| EmpirioLabs AI | kimi-k2-7-code-highspeed | global | $1.9 | $8 | 256K | |
| Moonshot AI (China) | kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| AIHubMix | kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| Ofox | moonshotai/kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| GMI Cloud | moonshotai/kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| Merge Gateway | moonshot/kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K | |
| Moonshot AI | kimi-k2.7-code-highspeed | global | $1.9 | $8 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Kimi K2.7 Code Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Kimi K2.7 Code | 66.8 | 1T | 262.1K | 262.1K | Yes | Modified MIT License |
What is Kimi K2.7 Code?
Key information about Kimi K2.7 Code and its available data.
6. 6. The model uses a native multimodal Mixture-of-Experts architecture with 1T total parameters, 32B activated parameters, a 256K-token context window, image and video input support, and forced thinking with preserve_thinking enabled for multi-turn coding agent workflows.
Data as of 2026-08-11.
Kimi K2.7 Code vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Kimi K2.7 Code
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Kimi K2.5
Moonshot AI
MA
Kimi K2 Thinking
Moonshot AI
MA
Kimi K2.6
Moonshot AI
MA
Kimi K3
Moonshot AI
MA
Kimi K2
Moonshot AI
MA
Kimi k1.5
Moonshot AI
FAQ
Common questions about Kimi K2.7 Code.
When was Kimi K2.7 Code released?
Kimi K2.7 Code's default version was released on Jun 12, 2026.
How much does Kimi K2.7 Code cost?
Kimi K2.7 Code's official API price is $0.95 per million input tokens and $4 per million output tokens via Moonshot AI. The lowest tracked third-party offer starts at $0.275 input and $1.1 output via routing.run.
Who created Kimi K2.7 Code?
Kimi K2.7 Code was created by Moonshot AI.
What is the context window for Kimi K2.7 Code?
The default version has a 262.1K token context window.
Is Kimi K2.7 Code open weight?
Yes. The default version is marked as open weight under Modified MIT License.
How many API providers offer Kimi K2.7 Code?
59 provider offerings are linked to the default version.
What models should I compare Kimi K2.7 Code with?
Nearby ranked alternatives include Qwen3.6 Plus, Gemini 3 Pro, GLM 5.