# Big-AGI

> Multi-model AI workspace that compares and merges answers

Big-AGI is a browser-based AI workspace that runs on your own API keys for more than 30 cloud and local model services. Its Beam feature sends one prompt to several models in parallel and can merge their replies into a single answer, and each request can be tuned and inspected in detail. The code is open source under the MIT License and can be self-hosted, while the hosted app is free and a Pro subscription adds cloud backup and sync.

- **Category:** AI Assistants
- **Made by:** Token Fabrics LLC (since 2023)
- **Website:** https://big-agi.com
- **Runs on:** Web
- **Facts last checked:** Oct 6, 2026

## Pricing

Big-AGI has a free plan. Paid plans start at $9 per month, billed yearly ($108), or $10.99 billed monthly (Pro).

- **Pricing model:** Free plan
- **Free plan:** Big-AGI Free is the full hosted workspace at no cost, with multi-model Beam and Personas, used with your own API keys. The MIT-licensed code can also be self-hosted.
- **Free trial:** None listed.

| Plan | Price | What you get |
| --- | --- | --- |
| Big-AGI Open | $0 | The open-source codebase under the MIT License, self-hosted with Docker or deployed to Vercel on your own infrastructure. |
| Free | $0 | The hosted app: everything in Open plus advanced multi-model, Personas and interface features. You bring your own API keys. |
| Pro | $9 per month, billed yearly ($108); $10.99 billed monthly | Everything in Free plus cloud backup of personas and chats, sync across devices with 1 GB of storage, email support and priority access to new features. |
| Business | Custom | Custom deployments, team management and SLA guarantees, arranged by contacting Big-AGI. |

Read from https://big-agi.com/ on Oct 6, 2026. Prices change, so confirm with Big-AGI before buying.

## Ways to pay less

- **Save 18% with yearly billing** (Annual discount): Pro is $9 a month when billed $108 a year, compared with $10.99 a month on monthly billing. Source: https://big-agi.com/

## Key features

- **Beam and Merge:** Beam sends one prompt to between 2 and 24 models in parallel, each answering without seeing the others. Merge then fuses the replies into one answer with built-in or custom merge prompts.
- **Your own keys for 30+ services:** Connects directly to OpenAI, Anthropic, Google Gemini, Mistral, DeepSeek, OpenRouter, Azure and AWS Bedrock, and to local servers such as Ollama and LM Studio, with no markup on usage.
- **Precise model controls:** Effort, temperature, verbosity, reasoning budget, search and tools can be set per request or per persona across more than 800 models.
- **Personas:** A persona carries its own instructions, attached documents and images, memory, a fixed model with parameters, and a voice, so a role can be reused across chats.
- **AI Inspector:** Shows the exact request leaving the browser, including the model, parameters, tokens and cost, both before and after it runs.
- **Local-first with optional sync:** Chats and settings stay in the browser by default. Pro adds cloud backup and sync of chats and personas across devices.

## Good for

- People with API keys for several providers who compare answers
- Checking an important answer across models before acting on it
- Self-hosters and IT teams that want an MIT-licensed chat interface

## Worth knowing

- No model access is included: every tier needs your own API keys, and each provider bills usage directly.
- Cloud backup and multi-device sync are Pro features. On Free and Open, chats stay in the browser on one device.
- It runs in the browser and installs as a web app; the site lists no native desktop or mobile apps.
- Team management and SLA guarantees are offered only through a custom Business plan with no public price.

## Works with

OpenAI, Anthropic, Google Gemini, Mistral, OpenRouter, AWS Bedrock, Ollama, LM Studio

**Tags:** Chat assistant, Open source, Self-hostable, Local-first, Keyboard-first, AI features

## Alternatives

- [TypingMind](https://toolgpa.com/tools/typingmind): Chat interface for AI models that runs on your own API keys. [Compare](https://toolgpa.com/compare/big-agi-vs-typingmind)
- [LibreChat](https://toolgpa.com/tools/librechat): Open-source, self-hosted chat interface for many AI providers. [Compare](https://toolgpa.com/compare/big-agi-vs-librechat)
- [Open WebUI](https://toolgpa.com/tools/open-webui): Self-hosted chat interface for local and cloud AI models. [Compare](https://toolgpa.com/compare/big-agi-vs-open-webui)
- [NextChat](https://toolgpa.com/tools/nextchat): Lightweight open-source AI chat client you can self-deploy. [Compare](https://toolgpa.com/compare/big-agi-vs-nextchat)
- [Chatbox](https://toolgpa.com/tools/chatbox): AI chat client for your own API keys or a hosted model plan. [Compare](https://toolgpa.com/compare/big-agi-vs-chatbox)

## Sources

The prices, plans, platforms and features above were read from these pages on Oct 6, 2026:

- https://big-agi.com/
- https://big-agi.com/terms
- https://github.com/enricoros/big-AGI
- https://api.github.com/repos/enricoros/big-AGI

Page: https://toolgpa.com/tools/big-agi
Listed by ToolGPA (toolgpa.com).