Aion Labs

Aion-2.0

Tool callingReasoning
Context
131K
Listed
7mo ago
Input / 1M tokens
$0.80
Output / 1M tokens
$1.60
Cached input / 1M tokens
$0.20

Sources:OpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer
Aion Labs
Model family
Aion
Type
Language model
Predecessor
—
Successor
—
Listed on OpenRouter
February 23, 2026
Model ID
aion-labs/aion-2.0
Openness
Closed
License
—
Input modalities
text
Output modalities
text
Modality
text->text
Tokenizer
Other
Max output tokens
33K
Hugging Face
—
Source freshness
Endpoints synced Oct 15, 2026, 1:18 PM UTC

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
AionLabsaion-labs131K$0.80$1.60$0.20—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter