000

The API opens in waves.Join the waitlist
Join waitlist

autter-large · vision · reasoning

Autter Large.Reads the whole thing.

Reads a whole repository or a day of logs in one context, reasons about it, and writes the report.

Join the waitlist Pricing

Context
131ktokens per call
Max output
33ktokens per call
Price
$3 / $5in / out, per 1M tokens
Cached input
$0.50per 1M tokens

Benchmark

Scores like a gated cyber model.Open to anyone.

On CyberGym, autter-large scores 88.1%, 2.5 points above OpenAI's dedicated GPT-5.5-Cyber. autter-flash scores 84.2% at a third of the price.

  1. autter-largeAutter, open to anyone88.1%
  2. GPT-5.5-CyberOpenAI's dedicated cyber model, gated85.6%
  3. autter-flashAutter, open to anyone84.2%
  4. GPT-5.6-SolOpenAI's latest general model83.6%
  5. DeepSeek-V4-ProDeepSeek's top open-weight model83.3%
  6. Claude Mythos PreviewAnthropic, preview access83.1%

CyberGym, pass rate. Higher is better.

Best for

When the whole thing has to be read.

about 600 ms to first token. Thinking on by default.

  1. 01/Code audits across a repository
  2. 02/Incident reconstruction from logs
  3. 03/Binary and config review with screenshots

A finding from a sample input

high · F-07

Token compared with bytes.Equal, not in constant time

auth/verify.go:142

The HMAC check uses bytes.Equal on a user-supplied value. Use hmac.Equal.

In detail

01/

131k context

A full pull request with its history, or 24 hours of edge logs, fits in one call. No chunking, no lost cross-references.

02/

Reasoning on

Thinking is switched on by default and spends output tokens. Ask for an effort level when you want it faster.

03/

Vision

Send screenshots of dashboards, diagrams and terminals. Images are priced as tokens, never per image.

04/

$3 in, $5 out

Per million tokens. Cached input is $0.50, so repeated context costs a sixth.

Quickstart

Call autter-large.

Point your SDK at inference.autter.dev. Keys are shown once.

Read the docs 
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.autter.dev/v1",
    api_key=os.environ["AUTTER_KEY"],
)

r = client.chat.completions.create(
    model="autter-large",
    messages=[{"role": "user", "content": f"Review this diff:\n{diff}"}],
    stream=True,
)
model autter-largebase URL inference.autter.dev