Mercury Edit
Ultra-fast AI code editing model that generates code at 1,000+ tokens per second.
Editorial take
Mercury Edit's standout capability is fastest code generation at 1000+ tokens/second. It is best suited for dev teams building custom coding tools or ides. A free plan is available, with paid plans starting at $0.25/1M tokens.
What is Mercury Edit?
Mercury Edit is a diffusion-based language model from Inception Labs built specifically for code editing. Unlike autoregressive models, it generates entire code blocks in parallel, achieving speeds of 1,000+ tokens per second - approximately 5x faster than comparable GPT-class models. This speed makes it well-suited for IDE autocomplete, fill-in-the-middle completions, and next-edit prediction.
It is OpenAI API-compatible, meaning it works as a drop-in replacement in any IDE or toolchain that supports the OpenAI format. Mercury Edit is available on AWS Bedrock and Azure AI Foundry, with 10 million complimentary tokens for new accounts.
Best for
Dev teams building custom coding tools or IDEs
Key strength
Fastest code generation at 1000+ tokens/second
Score breakdown (out of 5)
Pros & Cons
π Pros
- β5x faster than comparable autoregressive models
- βOpenAI-compatible API - integrates directly with existing tools
- βAvailable on major cloud marketplaces (AWS, Azure)
π Cons
- βDeveloper API only - no consumer product
- β32K context window is smaller than many general-purpose LLMs
- βNo affiliate or reseller program
Key Features
- β Diffusion-based architecture (not autoregressive)
- β 1,000+ tokens/second generation speed
- β Fill-in-the-middle (FIM) autocomplete
- β Next-edit prediction using recent edit history
- β 32K context window
- β OpenAI API-compatible (drop-in replacement)
- β Available on AWS Bedrock and Azure AI Foundry
- β Structured output with schema constraints
Mercury Edit Pricing
β Mercury Edit has a free plan - no credit card required to start.
Pay-as-you-go
- β$0.75/1M output tokens
- β$0.025/1M cached input tokens
- β32K context window
- βPriority support
Mercury Edit vs Competitors
Developer resources
Related Tools
Claude is the best AI assistant for long-document work and research where accuracy matters. Its 200K context window and resistance to sycophancy make it the honest choice when you need a thinking partner rather than an agreeable assistant. Start on the free tier; the Pro plan at $20/month is worth it if you regularly hit daily limits.
ChatGPT is the most capable all-in-one AI assistant available. Its combination of image generation, voice mode, code execution, web browsing, and a large custom GPT ecosystem makes it the default choice for users who want one tool that handles everything. The tradeoff is that it is rarely the deepest tool on any single task.
Cursor is the most powerful AI code editor available. Its multi-file editing is genuinely ahead of plugin-based alternatives, making large-scale refactors practical in ways GitHub Copilot cannot match. At $20/month for Pro it is a meaningful upgrade for any developer doing more than small isolated changes.
GitHub Copilot is the right starting point for most developers adopting AI-assisted coding. It integrates into whatever editor you already use, requires no workflow change, and has a usable free tier. The Pro plan at $10/month is the lowest-cost path to unlimited AI completions, making it the practical default for individuals.
This page contains affiliate links. We may earn a commission at no extra cost to you. Learn more.