Agents-A1
Agents‑A1 is a 35B Mixture‑of‑Experts agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling.
text → text · made by Intern Science
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Agents-A1 — a text model from Intern Science.
It takes text and returns text, with a context window of 262,000 tokens. It was published in June 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Intern Science
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,000 tokens
- Longest answer
- 100,000 tokens
- Published
- June 2026
- Parameters
- 35 billion · read from its own weights
- Licence
- apache-2.0
Known as 1 name
InternScience/Agents-A1