LLMmoonshotai

MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Anyone in the Project can @-mention MoonshotAI: Kimi K2.7 Code with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Kimi K2.7 Code targets code generation and technical tasks with a 262K token context window — large enough for multi-file codebases or long documentation threads. At $0.73/$3.50 per Mtok, it undercuts many Western models on input cost while keeping output pricing competitive. The lack of public benchmarks means you're betting on MoonshotAI's internal claims, but the context size and pricing make it worth testing for cost-sensitive code workflows where you need to feed entire repositories. Best for teams willing to validate performance themselves in exchange for lower inference costs.

Best for

Multi-file codebase analysis and refactoring
Cost-sensitive code generation at scale
Long documentation summarization for developers
Repository-wide dependency mapping
Technical Q&A over large API references

Strengths

The 262K context window handles entire small-to-medium codebases in a single prompt, eliminating chunking overhead. Input pricing at $0.73/Mtok is 40-60% cheaper than GPT-4 class models, making it viable for high-volume code analysis pipelines. Vision support means it can parse screenshots of error messages or UI mockups alongside code. MoonshotAI's focus on code-specific tuning suggests stronger performance on syntax-heavy tasks than general-purpose models at this price point.

Trade-offs

No public benchmarks means you can't compare HumanEval or MBPP scores against Claude or GPT-4o before committing. MoonshotAI is less established in Western markets, so expect fewer integrations and community resources. Output pricing at $3.50/Mtok is higher than input, so verbose code generation runs can get expensive. The model's performance on non-code tasks (creative writing, general reasoning) is unproven. If you need battle-tested reliability for production code, Claude Sonnet or GPT-4o remain safer bets despite higher cost.

Specifications

Provider: moonshotai
Category: llm
Context length: 262,144 tokens
Max output: 235,929 tokens
Modalities: text, image
License: proprietary
Released: 2026-06-12

Pricing

Input: $0.66/Mtok
Output: $3.40/Mtok
Model ID: moonshotai/kimi-k2.7-code

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$26.08

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider	Context	Input	Output	P50 latency	Throughput	30d uptime
moonshotai	262k	$0.74/Mtok	$3.50/Mtok	—	—	—

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Refactor Legacy Module

Review this entire module (5 files included below) and identify code smells, tight coupling, and opportunities to apply SOLID principles. Propose a refactoring plan with before/after snippets for the three highest-impact changes.

Open in a Project →

Dependency Graph Extraction

Parse all import statements in the files below and generate a dependency graph in Mermaid format. Flag any circular dependencies and list modules imported but never used.

Open in a Project →

API Documentation Summary

Summarize this 50-page API reference into a 2-page quick-start guide covering authentication, core endpoints, rate limits, and error handling. Include code examples in Python.

Open in a Project →

Bug Reproduction from Screenshot

This screenshot shows a runtime error in our app. Analyze the stack trace, identify the root cause, and write a fix with inline comments explaining what went wrong.

Open in a Project →

Test Case Generation

Write pytest unit tests for the function below. Cover happy path, edge cases (empty input, null, overflow), and one failure scenario. Use fixtures where appropriate.

Open in a Project →

Compare with

Compare MoonshotAI: Kimi K2.7 Code with…

More language models

See all language models →