Vendor
Aion Labs models
4 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
4
0 routable here
Median list price
$1.00
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Aion Labs model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Aion-3.0-Miniaion-labs/aion-3.0-mini | Jul 7, 2026 | 131K | $0.70 | $1.40 | - | reasoning tools |
| Aion-3.0aion-labs/aion-3.0 | Jul 7, 2026 | 131K | $3.00 | $6.00 | - | reasoning tools |
| Aion-2.0aion-labs/aion-2.0 | Feb 23, 2026 | 131K | $0.80 | $1.60 | - | reasoning tools |
| Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b | Feb 4, 2025 | 33K | $0.80 | $1.60 | - |
Frequently asked
- What is the cheapest Aion Labs model?
- Aion-3.0-Mini at $0.70 per 1M input tokens and $1.40 per 1M output tokens (vendor list price).
- Which Aion Labs model has the largest context window?
- Aion-3.0-Mini accepts 131K tokens of context.
- How do I route to Aion Labs models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example aion-labs/aion-3.0-mini); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Aion Labs with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Aion Labs flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.