/pricing
Free and open source
GPT Researcher is published under the MIT License. There is no SaaS subscription, no API gateway, and no rate limit on this site. You self-host the agent and pay only your underlying LLM and search-API providers.
Machine-readable summary: /pricing.md. Structured offer data: /openapi.json.
Open Source - $0
- Full GPT Researcher Python package on PyPI.
- Official
gptr-mcpModel Context Protocol server. - Self-host on your own machine, server, or container.
- Use any supported LLM and any supported retriever.
- License: MIT.
Operating costs
You pay your chosen providers directly. Typical per-query cost depends on:
- LLM provider: OpenAI GPT-4o / Claude Sonnet / Gemini / DeepSeek / a local model.
- Retriever: Tavily, Bing, Google CSE, or free options (DuckDuckGo, SearXNG).
- Subtopics and iterations: configurable; defaults aim for 10 - 30 sources.
Indicative ballpark for a single deep-research run with default OpenAI + Tavily settings: a few cents to a few dollars of provider spend.
Enterprise / managed
No first-party hosted SaaS today. For managed deployments inside your VPC, custom retrievers connected to private corpora, or SLAs, reach out via Discord or email assaf.elovic@gmail.com.
FAQ
Is GPT Researcher free forever?
Yes. The OSS project is MIT-licensed. Future managed offerings would be separate from the open-source distribution.
Will my data leave my machine?
Only via the LLM and retriever providers you configure. Self-host with a local model and SearXNG to keep everything on-prem.
Are there usage limits?
None imposed by GPT Researcher. Limits come from your underlying provider rate limits.