Open-source AI models for developers and enterprises | Freemium | - **Mistral Large 3**: 675 billion parameter multimodal model that processes text, images, audio, and video across 40+ languages with advanced reasoning capabilities.
- - **Ministral Edge Models**: Nine lightweight models (3B to 14B parameters) that run offline on devices like drones, phones, and laptops without internet connectivity.
|
Real-time AI copilot for software engineering interviews | Free tier | - **Screenshot and Prompt Parsing**: Capture a coding problem, table, or diagram and get a solution outline back. It works for LeetCode-style questions on platforms like HackerRank, CoderPad, CodeSignal, and Codility.
- - **Real-Time Voice Recognition**: GhostInterview transcribes spoken questions and surfaces hints as the conversation moves. You can trigger answers yourself in Manual mode or turn on Auto mode, which responds when the latest interviewer turn looks like a question.
|
AI coding agent that turns tickets into tested PRs | Free tier | - **Tickets to Pull Requests**: devlo reads your codebase and posts an implementation plan in the ticket, which you can edit or approve first. It then writes the code, adds tests, runs linters, and opens a PR you can steer through comments.
- - **AI Code Review**: Get reviews on every PR that check logic and style and flag security, performance, and reliability risks. You can set review instructions at the org and repo level so devlo enforces your own standards.
|
Run a fleet of cloud coding agents in parallel | Free tier | - **Parallel cloud agents**: Run many threads at once, each in its own isolated cloud machine. Subagents can split large jobs like migrations and refactors across separate or shared VMs.
- - **Captain, Build, and Review agents**: The Captain agent plans the work, Build agents write and test the code, and Review agents post findings on your pull requests.
|
Run coding agents in parallel, each in its own worktree | Freemium | - **Parallel Git Worktrees**: Every task runs in its own isolated git worktree. Send one prompt to several agents, compare what they produce, and merge the best version.
- - **Broad Agent Support**: Claude Code, Codex, Cursor CLI, Gemini, Copilot, OpenCode, and Pi come preconfigured. You can also run Grok, Amp, Goose, Cline, Kiro, Qwen Code, or any other CLI agent.
|
Agentic IDE to build, test, and monitor your code | Freemium | - **Bring-Your-Own-Agent Terminal**: Run any CLI agent, including Claude Code, Codex, Gemini CLI, and OpenCode, in a real terminal. You keep the agents and config you already use.
- - **Parallel Agents in Git Worktrees**: Each agent gets its own git worktree, so several can work at once without conflicts. Agents can also message each other in split panes.
|
Open source AI coding agent that works with any model | Freemium | - **75+ LLM Providers**: You can connect Claude, GPT, Gemini, local models, and many more through Models.dev. You aren't tied to one vendor.
- - **Use Your Existing Subscriptions**: Sign in with GitHub Copilot or ChatGPT Plus/Pro and use plans you already pay for.
|
AI assistant for research, coding, writing, reasoning, and complex tasks. | Freemium | - **AI chat**: Ask questions, write content, analyze information, and solve problems through DeepSeek Web.
- - **Advanced reasoning**: DeepSeek-V4.1-Flash supports both thinking and non-thinking modes for different tasks.
|
Ultra-fast AI inference for real-time apps | Paid | - **LPU inference hardware**: Groq's custom Language Processing Units are built specifically for AI inference, using deterministic execution and on-chip memory to deliver predictable, fast processing.
- - **High-speed inference**: Groq publishes model-specific inference speeds ranging from hundreds to around 1,000 tokens per second on some current models, including 1,000 t/s for GPT-OSS 20B.
|
