Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Aion-3.0

AionLabs· released 7 Jul 2026

aion-labs/aion-3.0
Input / 1M tokens
$3
Output / 1M tokens
$6
Context window131K tokens

Longest answer: 33K tokens

reads texttool callingreasoning
See it on openrouter.ai

About

Aion-3.0 is a text-output model from AionLabs for roleplaying and storytelling, built on the GLM family. Its summary describes a collaborative generation process in which multiple specialized models contribute, though no further details of that process are listed. The model accepts text input and has a context window of 131,072 tokens, with a maximum output of 32,768 tokens. Tools and reasoning are listed as supported. Input costs 3 USD per 1M tokens and output costs 6 USD per 1M tokens. Aion-3.0 was released on 2026-07-07. For builders assessing it for a text workflow, the stated use case, context size, output cap and per-token rates define the available fit signals; the listed output modality is text.

Who it is for

Aion-3.0 suits builders exploring text-based roleplaying or storytelling workflows who want a model with tools and reasoning support. Its token limits and separate input and output rates are relevant to teams estimating usage.

What is good

  • Designed for roleplaying and storytelling.
  • 131,072-token context window.
  • Supports tools and reasoning.
  • Text input and output.

What to know first

  • Maximum output is 32,768 tokens.
  • Input costs 3 USD per 1M tokens.
  • Output costs 6 USD per 1M tokens.

Verdict

Aion-3.0 is positioned for roleplaying and storytelling, with a large stated context window and tools and reasoning support. Its input and output rates differ, so estimate both sides of token usage when assessing cost.

Details

Lab
AionLabsopenrouter.ai · 3 Oct 2026
Context
131Kopenrouter.ai · 3 Oct 2026
Input price
$3 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$6 / 1Mopenrouter.ai · 3 Oct 2026
Max output
32,768 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources