Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...
Context
128K
128,000 tokens
Max output
33K
32,768 tokens
Input
$3.75
per 1M tokens
Output
$7.50
per 1M tokens
Providers
3
3 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Venice AI
| Token type | Standard |
|---|---|
| Input | $3.75 |
| Output | $7.50 |
| Cache read | $0.94 |
Lowest input price across providers: $3.00.
Capabilities
ReasoningYes
Effort: high
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsNo
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 3
3 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Kilo Gateway | aion-labs/aion-3.0 | 131K | — | 33K | $3.00 | $6.00 | — | $0.75 | — | — | — | Yes | Yes | No | Yes | May 5, 2026 |
 NanoGPT | aion-labs/aion-3.0 | 131K | 131K | 33K | $3.00 | $6.00 | — | $0.75 | — | — | — | Yes | Yes | No | Yes | May 5, 2026 |
 Venice AI | aion-labs-aion-3-0 | 128K | — | 33K | $3.75 | $7.50 | — | $0.94 | — | — | — | Yes | Yes | Yes | Yes | May 5, 2026 |