ACS Research · Base model endpoint
Base models, served for research.
Direct, token-level access to large language base models, over an OpenAI compatible API. Free for researchers.
We aim to support research in AI safety and interpretability, understanding LLM psychology and personas, cyborgism-style human–AI collaboration, and more.
What you get
An endpoint built for research on the model itself, not just its outputs.
True base models
Raw /v1/completions — no chat template, no RLHF, no system prompt. The model as it came out of pretraining.
Token-level access
Top-k logprobs on generated tokens and prompt_logprobs on the input — for likelihood and interpretability work. Plus echo and SSE streaming.
OpenAI compatible
Point any OpenAI client at one base URL. Full sampling controls — temperature, top_p, top_k, min_p, penalties, and seed.
Browser workbench
Prompt the models straight from the browser to get a feel for them before you (ask your friendly LLMs to) write a line of code.
Models we're considering
We expect to figure out with our beta tester community what models — served on what schedules — would be most useful.
Getting access
Access is free for accepted researchers.
Apply
Tell us who you are and what you'd like to work on.
Get approved
We review your application and let you know via email.
Create a key
Generate an API key and start querying.
Need base models for your research?
Apply for access, or get in touch if you have questions about what's available.