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 Space 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 Space, 100 credits/month, 1 MCP. No card.

Verdict

Kimi K2.7 Code targets code generation and debugging with a 262K token context window — enough for entire codebases or long debugging sessions. At $0.74/$3.50 per Mtok, it undercuts many Western alternatives while handling vision inputs for screenshot-based debugging. The trade-off: no public benchmarks yet, so performance claims remain unverified against Claude or GPT-4o. Best for teams needing affordable long-context code assistance who can tolerate uncertainty around competitive standing.

Best for

Long-context code refactoring across files
Cost-sensitive API integration projects
Screenshot-based UI debugging workflows
Large codebase comprehension tasks

Strengths

The 262K context window handles entire repositories or multi-file refactors without chunking. Vision support lets you paste error screenshots or UI mockups directly into debugging sessions. Pricing sits 40-60% below comparable Western models, making it viable for high-volume code generation. MoonshotAI's focus on code-specific tuning suggests stronger performance on syntax-heavy tasks than general-purpose models.

Trade-offs

Zero public benchmarks means you're flying blind on accuracy versus Claude Sonnet or GPT-4o Code. No information on supported languages beyond generic 'code' claims — Python and JavaScript likely strong, niche languages uncertain. Vision capabilities are listed but unspecified in scope; unclear if it matches GPT-4o's chart or diagram reasoning. Proprietary license limits transparency into training data or model architecture.

Specifications

Provider: moonshotai
Category: llm
Context length: 262,144 tokens
Max output: 16,384 tokens
Modalities: text, image
License: proprietary
Released: 2026-06-12

Pricing

Input: $0.74/Mtok
Output: $3.50/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

$27.60

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 Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Refactor Legacy Module

I'm pasting three related Python modules below (8,000 lines total). Refactor the authentication logic to use modern async patterns while preserving all existing API contracts. Show me the changes file-by-file with migration notes.

Open in a Space →

Debug From Screenshot

Here's a screenshot of a React component rendering incorrectly, plus the JSX and CSS files. Identify why the layout breaks on mobile and provide the corrected code with explanation.

Open in a Space →

API Integration Scaffold

Write a TypeScript client for the Stripe API covering payments, subscriptions, and webhooks. Include full type definitions, retry logic, and rate limiting. Structure it for a Next.js 14 app.

Open in a Space →

Codebase Comprehension Report

I'm attaching a 50K-line Django project. Generate an architecture overview covering: data models, API endpoints, authentication flow, third-party dependencies, and three highest-priority refactoring opportunities.

Open in a Space →

Multi-File Test Suite

Given these five interconnected service classes (12K lines), write a pytest suite covering happy paths, edge cases, and integration scenarios. Include fixtures and mocking strategies for external APIs.

Open in a Space →