Moonshot AI

Kimi K2.7 Code

Generally availableOpen weights262K contextReasoning

Summary

Kimi K2.7 Code is an open-weight language model from Moonshot AI, released on 12 Jun 2026. It accepts text, images and video and generates text, with a 262K-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.60 per million input tokens and $3.50 per million output tokens (OpenRouter), across 7 providers we track.

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMoonshot AI
Release date12 Jun 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemodified-mit [Hugging Face]
Parameters1T [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output262K tokens [models.dev]
Knowledge cutoffJan 2025 [models.dev]
InputText, images and video [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facemoonshotai/Kimi-K2.7-Code [Hugging Face]

Kimi K2.7 Code API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
moonshotai/kimi-k2.7-code
$0.60$3.50$0.16262KOpenRouter, 18 Nov 2026
SiliconFlow
moonshotai/Kimi-K2.7-Code
$0.86$3.80$0.18262Kmodels.dev, 18 Nov 2026
Moonshot AI API
kimi-k2.7-code
$0.95$4$0.19262Kmodels.dev, 18 Nov 2026
Azure AI Foundry
kimi-k2.7-code
$0.95$4$0.19262Kmodels.dev, 18 Nov 2026
Novita AI
moonshotai/kimi-k2.7-code
$0.95$4$0.19262Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
moonshotai/Kimi-K2.7-Code
$0.95$4–262Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
moonshotai/kimi-k2.7-code
$0.95$4$0.19256Kmodels.dev, 18 Nov 2026
Moonshot AI API
kimi-k2.7-code-highspeed
$1.90$8$0.38262Kmodels.dev, 18 Nov 2026

Running Kimi K2.7 Code locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)623 GB624 GB626 GB
Q8_0 (8-bit)1091 GB1092 GB1094 GB
FP16 / BF16 (16-bit)2054 GB2055 GB2057 GB

At 4-bit with an 8K conversation, Kimi K2.7 Code needs about 624 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Kimi K2.7 Code?

Kimi K2.7 Code has a context window of 262,144 tokens (262K) and can generate up to 262,144 tokens in a single response, according to models.dev.

How much does the Kimi K2.7 Code API cost?

Through Moonshot AI API, Kimi K2.7 Code costs $0.95 per million input tokens and $4 per million output tokens. The lowest listed price is $0.60 input / $3.50 output through OpenRouter. Prices last verified 18 Nov 2026.

Is Kimi K2.7 Code open source?

Kimi K2.7 Code is an open-weight model: its weights are published on Hugging Face as moonshotai/Kimi-K2.7-Code under the modified-mit license. Check the license terms before commercial use.

When was Kimi K2.7 Code released?

Moonshot AI released Kimi K2.7 Code on 12 Jun 2026, according to models.dev.

Which providers offer Kimi K2.7 Code?

We track Kimi K2.7 Code on 7 providers: OpenRouter, SiliconFlow, Moonshot AI API, Azure AI Foundry, Novita AI, Hugging Face Inference Providers, Vercel AI Gateway.

How much VRAM does Kimi K2.7 Code need?

About 624 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 1092 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
InklingThinkingmachines15 Jul 2026256K$1$4.05Open
Qwen3.6 27BAlibaba (Qwen)22 Apr 2026262K$0.30$3.19Open
GLM-5.1Zhipu AI (Z.ai)7 Apr 2026200K$1$3.20Open
Qwen3.5 397B-A17BAlibaba (Qwen)15 Feb 2026262K$0.45$3Open
GlimpseElorian17 Oct 2026262K$0.60$3–
Mistral Medium LatestMistral AI30 Apr 2026262K$1.50$7.50Open

Change history

  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • No longer listed on nebius
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • No longer listed on cloudflare-workers-ai
  • OpenRouter price changed: input $0.60 → $0.60, output $3.50 → $3.50 per 1M tokens
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • OpenRouter price changed: input $0.56 → $0.60, output $3.10 → $3.50 per 1M tokens
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • OpenRouter price changed: input $0.67 → $0.56, output $3.35 → $3.10 per 1M tokens
  • OpenRouter price changed: input $0.67 → $0.67, output $3.35 → $3.35 per 1M tokens
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • nebius price changed: input $0.95 → $0.95, output $4 → $4 per 1M tokens
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • nebius price changed: input $0.95 → $0.95, output $4 → $4 per 1M tokens
  • No longer listed on databricks
  • No longer listed on baseten
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code
  • Name changed from Kimi K2.7 Code to Kimi K2.7 Code HighSpeed
  • Name changed from Kimi K2.7 Code HighSpeed to Kimi K2.7 Code

Sources