Aion 3.0 Mini API

Aion Labs's Aion 3.0 Mini, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Facts

Model name
aion-3.0-mini
Maker
Aion Labs
Context window
131.1K tokens
Input price
$0.700 per million tokens
Output price
$1.400 per million tokens
Providers
1 independent provider
Regions
us

Providers

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aion-3.0-mini",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Aion 3.0 Mini?
Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Aion 3.0 Mini cost?
Offers now ask $0.700 per million input tokens and $1.400 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Aion 3.0 Mini?
The largest offer takes 131,072 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Aion 3.0 Mini do?
Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Aion 3.0 Mini support?
Text → Text.
Which providers serve Aion 3.0 Mini?
1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Aion 3.0 Mini?
Send "aion-3.0-mini" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Aion 3.0 Mini listed?
The exchange first listed it on 10/8/2026. This is not its release date.

Related pages