MiniMax M2.7 is here
#5 on PinchBench. $0.30/M input. Available now in Kilo.
Why M2.7 matters
Near-Opus performance at a fraction of the cost
Near-Opus performance at a fraction of the cost
3.7-point jump from MiniMax M2.5 — moved MiniMax from mid-pack to top tier
Reads deeply before writing — catches things other models miss
Solves tasks no other model can (unique solve on SPARQL reasoning)
Self-evolving model: ran 100+ rounds of autonomous scaffold optimization
“These models aren't interchangeable. They're complementary.”
PinchBench — Top 5
50 models evaluated
Use it everywhere in Kilo
Pick the surface that fits your workflow
VS Code & JetBrains
Select M2.7 from 500+ models in your editor. Switch models per task.
Install Extension →KiloClaw (Hosted OpenClaw)
Fully managed cloud agent. 2 clicks, 60 seconds to start. No setup.
Launch KiloClaw →Trusted by developers at the world's most innovative companies
Why Kilo Code
Open source, no vendor lock-in, zero markup
Open Source
Apache 2.0. Inspect, modify, self-host. No black boxes.
500+ Models
Not locked into one provider. Switch models per task, per project.
BYOK (Bring Your Own Key)
Use your own API keys. Direct provider pricing. No middleman.
$0/month Base Price
Free to start. No subscription required. Ever.
Pay As You Go
Only pay for tokens you use. Zero markup on provider prices.
M2.7 at Provider Cost
$0.30/M input, $1.20/M output. Same as MiniMax direct.
When to use M2.7
With 500+ models in Kilo, pick the right model for the job
Use M2.7 when
- Complex refactors spanning multiple files
- Codebase-wide changes needing deep context
- Tasks where thoroughness > speed
- Budget-conscious work needing near-frontier quality
Consider lighter models when
- Quick iteration cycles
- Well-scoped, time-sensitive edits
- Simple file changes or boilerplate
Bottom line: With 500+ models in Kilo, you're never locked in.
Agentic Engineering
Glide through your workflow with a mode for every step
Ask mode
A knowledgeable technical assistant focused on answering questions without changing your codebase
Frequently Asked Questions
Compare Kilo Code with Other Tools
See how Kilo Code stacks up against other AI coding assistants
Kilo Code vs Cursor
Compare Kilo Code with Cursor across editors, models, BYOK, agents, cloud workflows, pricing, and enterprise controls.
GitHub Copilot vs Kilo Code
Compare GitHub Copilot and Kilo across IDEs, agents, CLI, models, local use, pricing, review, and governance.
Kilo Code vs Cline
Compare two open coding agents across models, local use, IDEs, CLI, orchestration, teams, and pricing.
Kilo Code vs Devin Desktop
Compare Kilo with Devin Desktop, formerly Windsurf, across IDEs, local and cloud agents, models, pricing, and teams.
Kilo Code vs Roo Code
Roo Code was discontinued May 15, 2026. Compare its preserved capabilities with maintained Kilo workflows and plan a safe migration.
Kilo Code vs Continue
Continue joined Cursor and is no longer actively maintained. Compare its preserved IDE, CLI, YAML, and local-model capabilities with Kilo.
Kilo Code vs Gemini Code Assist
Compare Kilo with paid Gemini Code Assist across IDEs, models, agents, quotas, Google Cloud integration, data controls, and pricing.
Kilo Code vs OpenAI Codex
Compare Kilo with the broad Codex platform across IDE, CLI, cloud, models, local providers, subagents, open source, pricing, and governance.
Kilo Code vs Claude Code
Open-source, multi-model CLI + IDE agent with inline autocomplete vs Anthropic's Claude-only terminal-first coding agent.
Kilo Code vs Roomote
Roomote is the new product from the team behind Roo Code after its May 2026 shutdown. Compare it with Kilo Code — the proven, actively maintained open-source AI coding agent.
Kilo Code vs Tabnine
Full agentic coding across 500+ models vs Tabnine's enterprise-only autocomplete.
Kilo Code vs Augment Code
Open-source, BYOK-everywhere agent platform vs Augment Code's closed proprietary stack.
Kilo Code vs Lovable
Kilo Code plugs into your real IDE and codebase — Lovable is a hosted AI app builder optimized for greenfield prototyping.
Kilo Code vs Replit
Use Kilo inside your existing editor and infrastructure vs Replit's hosted browser IDE.
The Open-Source Google Antigravity Alternative
Compare Google Antigravity with Kilo Code for open-source agentic coding in VS Code, JetBrains, and CLI with BYOK and local models.
Kilo Code vs Warp
Kilo Code works inside VS Code and JetBrains as an AI coding agent. Warp is a standalone terminal-first Agentic Development Environment. Same agent power, different home.
Kilo Code vs Amp Code
Amp Code is shutting down its VS Code extension — compare it with Kilo Code
Kilo Code for JetBrains IDEs
AI coding assistant for IntelliJ, PhpStorm, WebStorm, and Rider
Kilo CLI vs Claude Code
Compare Kilo CLI with Claude Code for terminal-first AI coding
Kilo CLI vs Aider
Compare model choice, workflows, and pricing for command-line agents
Kilo CLI vs Codex CLI
See how Kilo CLI compares with OpenAI Codex CLI
Kilo CLI vs Gemini CLI
Compare Google Gemini CLI with Kilo CLI and 500+ models
Kilo CLI vs OpenCode CLI
Compare Kilo CLI with the upstream OpenCode CLI and subscriptions
Kilo Code vs Google Antigravity
Compare models, pricing, agent workflows, and product surfaces
Kilo Autocomplete vs Cursor Tab
Feature-by-feature comparison for AI code completions
Kilo Autocomplete vs GitHub Copilot
Compare autocomplete quality, pricing, and IDE support
Kilo Autocomplete vs Codeium
Compare Kilo Code autocomplete with Codeium completions
Kilo Code Reviews vs Greptile
Compare AI code review workflows, model choice, and pricing
Graphite vs Kilo Code Reviews
Compare Graphite PR workflows with Kilo Code Reviews
Best AI Coding Assistant
Compare top AI coding assistants and when to choose each one
Start using M2.7 in under 60 seconds.
Join 3M+ developers using Kilo Code. Near-Opus performance at $0.30/M input.