Using the base-model API

Coding with an AI assistant? Point it at https://infra.acsresearch.org/llms.txt — the one-page version of the docs and API reference — and it can write your client for you.

This app provides access to base models — raw next-token prediction, no chat template, no instruction tuning — served over an OpenAI-compatible /v1/completions endpoint.

What you get

Three base models — a small one for quick tests plus two larger ones (see Models). Some are kept warm; others cold-start on first use.
Next-token access — arbitrary prefill/continuation, logprobs and prompt_logprobs for likelihood/surprisal and interpretability work, echo, and SSE streaming.
Sampling controls — temperature, top_p, top_k, min_p, penalties, and a seed for reproducibility.
API — OpenAI-compatible /v1/completions with strict input validation (a misspelled parameter returns an error instead of silently defaulting) and structured JSON errors.
Browser Workbench — try prompts and manage API keys without writing code.
Per-key budgets & usage — set token caps per key and track spend (see Account).
Feedback — a one-click Feedback button in the Workbench for feature requests and bug reports.

Two ways in

Workbench — prompt the models straight from your browser. Good for getting a feel before you write any code.
The API (below) — for anything programmatic. Create a key from your API keys page (your email → API keys).

Quick start

Create a key on your API keys page (your email → API keys), then point any OpenAI-compatible client at the API:

export ACS_API_KEY="acs-bm-..."          # your key
export ACS_API_BASE="https://infra.acsresearch.org/v1"

A first request with curl:

curl -s "$ACS_API_BASE/completions" \
  -H "Authorization: Bearer $ACS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llama-8b", "prompt": "The capital of France is", "max_tokens": 8}'

Or with the Python SDK (pip install openai):

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["ACS_API_BASE"],
    api_key=os.environ["ACS_API_KEY"],
)

resp = client.completions.create(   # completions — not chat.completions
    model="llama-8b",
    prompt="The capital of France is",
    max_tokens=16,
    logprobs=5,
)
print(resp.choices[0].text)

Worked examples

Examples has short, runnable snippets, one page per feature. The curl examples assume ACS_API_KEY + ACS_API_BASE are exported (see Quick start); the Python examples use the same openai SDK client as above.

The Colab workshop introduces base models in your browser, with no local setup. It covers completions, sampling, logprobs, reading a model's activations, and steering it to talk like a pirate.