Kimi K2.7 Code
Kimi K2.7 Code is a text generation model from Moonshot AI built for coding and agentic tasks with a 262,164-token context window.
Moonshot
DeepInfraCode-focused language model with long context
Kimi K2.7 Code is a large language model developed by Moonshot AI and made available through DeepInfra. It is designed specifically for coding and agentic use cases, as indicated by its tags, and supports a context window of 262,164 tokens, allowing it to process and reason over large codebases or extended conversations in a single pass.
The model accepts a range of sampling parameters including Top P, Min P, Top K, presence penalty, frequency penalty, repetition penalty, and stop sequences, giving developers fine-grained control over output behavior. Its long context capacity makes it well-suited for tasks like repository-level code generation, multi-step agentic workflows, and code review across large files.
What Kimi K2.7 Code supports
Code Generation
Generates code across programming languages as a primary use case. The model is tagged specifically for coding tasks, making it suited for writing, completing, and debugging code.
Agentic Workflows
Supports multi-step agentic task execution where the model takes sequential actions toward a goal. Designed to operate within tool-using or autonomous agent pipelines.
Long Context Processing
Handles up to 262,164 tokens in a single context window, enabling analysis of large codebases, long documents, or extended multi-turn conversations without truncation.
Sampling Controls
Exposes Top P, Min P, Top K, presence penalty, frequency penalty, and repetition penalty inputs so developers can tune output diversity and repetition behavior precisely.
Stop Sequence Support
Accepts custom stop sequences as a text input, allowing the model to halt generation at defined tokens or strings useful for structured output parsing.
Ready to build with Kimi K2.7 Code?
Get Started FreeCommon questions about Kimi K2.7 Code
What is the context window size for Kimi K2.7 Code?
Kimi K2.7 Code has a context window of 262,164 tokens, which allows it to process large codebases or extended conversations in a single request.
What is Kimi K2.7 Code designed for?
The model is tagged for coding and agentic tasks, making it suited for code generation, code review, and multi-step autonomous workflows.
Who publishes Kimi K2.7 Code and where is it hosted?
Kimi K2.7 Code is published by Moonshot AI under the model identifier moonshotai/Kimi-K2.7-Code and is served through the DeepInfra provider on MindStudio.
What sampling parameters does Kimi K2.7 Code support?
The model supports Top P, Min P, Top K, presence penalty, frequency penalty, repetition penalty, and custom stop sequences, giving developers control over generation behavior.
Is pricing information available for Kimi K2.7 Code?
No published pricing is listed in the current metadata for Kimi K2.7 Code. You can check MindStudio or DeepInfra directly for current pricing details.
Documentation & links
Parameters & options
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Float that represents the minimum probability for a token to be considered, relative to the probability of the most likely token. Set to 0 to disable this.
Sample from the best k (number of) tokens. 0 means off.
Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Positive values penalize new tokens based on how many times they appear in the text so far, increasing the model's likelihood to talk about new topics.
Alternative penalty for repetition, but multiplicative instead of additive (> 1 penalize, < 1 encourage).
A sequence where the API will stop generating further tokens.
Explore similar models
MoonshotKimi K3
Kimi K3 is a text generation model from Moonshot with a 1,048,576-token context window and up to 131,072-token responses.
MoonshotKimi K2.6
Kimi K2.6 is a text generation model from Moonshot AI with a 262,144-token context window, served via Deep Infra.
MoonshotKimi K2.5
Kimi K2.5 is a text generation model from Moonshot AI with a 262,144-token context window and up to 16,384-token responses.
GoogleGemini 3.8 Flash
OpenAIGPT-6 Astra
AnthropicClaude 5.1 Fable
Start building with Kimi K2.7 Code
No API keys required. Create AI-powered workflows with Kimi K2.7 Code in minutes — free.