Aion-3.0
AionLabs · released Jul 7, 2026
- Type
- Proprietary
- Input
- $3.00
- Output
- $6.00
- Cached
- $0.75
List price · per 1M tokens · AionLabs at 131K context · source ↗
Our take
Written Aug 3, 2026Aion-3.0 is a proprietary text-only model from AionLabs with a 131,072-token request limit, released in July 2026. It is positioned as a mid-tier API choice for long-document work, though no benchmark scores or model size details have been published.
Pick this for long-document text tasks where you need a substantial request limit and do not require downloadable weights. Use it if you want identical pricing across both hosted endpoints for predictable billing. Skip it if you need measured quality data, fast generation speed, or transparency about model size and architecture.
The case for it
- 131,072-token request limit, among the larger ones in the mid-price tier for long-document work.
- Identical pricing across both tracked endpoints, giving predictable costs regardless of which host you choose.
The case against it
- No measured quality or capability scores in our data — no chat, reasoning, coding, or general benchmark results published.
- Slow generation at 57 tokens per second on the only measured endpoint; the alternative host is unverified.
- Proprietary with no transparency: parameter count is undisclosed and no licence is granted.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Aion-3.0 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes AionLabs's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $3.00 in / $6.00 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $3.00 / $6.00 | 131K | not measured | Unknown | Unknown | Unknown |
| AionLabs | $3.00 / $6.00 | 131K | 38 tok/s | No | Yes30 days | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✗ |
| AionLabs | ✓ | ✓ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
Models people weigh against Aion-3.0
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- aion-labs-aion-3-0