AionLabs models

AionLabs has 6 models in the directory. The newest is Aion 3.5, released Sep 23, 2026.

The cheapest to run is Aion 3.5 Mini at $0.70 per million input tokens.

Aion 3.5 has the longest context window, 262K tokens.

Models
6
Newest
Sep 23, 2026
From
$0.70/M input
Longest context
262K

All AionLabs models

Filter in the directory
  • Reads text. Tool calling, reasoning. Served by 2 providers.

    by aion-labsSep 23, 2026$3/M input tokens$6/M output tokens2 providers

  • Reads text. Tool calling, reasoning. Served by 2 providers.

    by aion-labsSep 23, 2026$0.70/M input tokens$1.40/M output tokens2 providers

  • Reads text. Tool calling, structured output, reasoning. Served by 3 providers.

    by aion-labsJul 7, 2026$3/M input tokens$6/M output tokens3 providers

  • Reads text. Tool calling, structured output, reasoning. Served by 3 providers.

    by aion-labsJul 7, 2026$0.70/M input tokens$1.40/M output tokens3 providers

  • Reads text. Tool calling. Served by 2 providers.

    by aion-labsFeb 23, 2026$0.80/M input tokens$1.60/M output tokens2 providers

  • Reads text. Tool calling. Served by 3 providers.

    by aion-labsFeb 4, 2025$0.80/M input tokens$1.60/M output tokens3 providers

Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.

Not sure which AionLabs model fits?

I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.

Book Meeting