aionlabs · Frontier
AionLabs: Aion 3.0
Aion 3.0 is a GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.
- Reasoning
- Tools
- Input
- Text
- Output
- Text
- Discovery tier
- Frontier
Pricing
USD per 1M tokens- Input
- $3.00
- Output
- $6.00
- Cache read
- $0.75
Reference prices as published by the model provider. API example
Specifications
- Context window
- 131.1K
- Max output
- 32.8K
- Average output (7 days)
- 1.1K tokens
- Longer than 72% of 473 models
Side by side
AionLabs: Aion 3.0 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| AionLabs: Aion 3.0aionlabsThis model | AionLabs: Aion 3.5aionlabsRemove | |
|---|---|---|
| Provider | aionlabs | aionlabs |
| Discovery tier | Frontier | Frontier |
| Added | Jul 7, 2026 | Sep 23, 2026 |
| Limits | ||
| Context window | 131.07K | 262.14KBest |
| Max output | 32.77K | 32.77K |
| Average output | 1.1K tokens | 1.4K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $3.00 | $3.00 |
| Output | $6.00 | $6.00 |
| Cache read | $0.75 | $0.75 |
| Performance | ||
| Throughput | 58.9 tok/s | 65.2 tok/sBest |
| Time to first token | 2.1 sBest | 4.7 s |
| Request success (24h) | 100.0% | 100.0% |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- AionLabs: Aion 3.0
- AionLabs: Aion 3.5
| Leaderboard | AionLabs: Aion 3.0 | AionLabs: Aion 3.5 |
|---|---|---|
| Roleplay | Not in top 20 | #19 · 18.5% |
| Creative writing | Not in top 20 | #15 · 20.1% |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- AionLabs: Aion 3.0
- AionLabs: Aion 3.5
| Leaderboard | AionLabs: Aion 3.0 | AionLabs: Aion 3.5 |
|---|---|---|
| Creative Writing v3 | Not in top 20 | #13 · 1931 |
| Longform Writing | Not in top 20 | #9 · 82.1 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 58.9 tok/s
- Faster than 41% of 260 models
- Time to first token
- 2.1 s
- Quicker than 72% of 260 models
- Prompt cache hits
- 52.3%
- About $1.82 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aion-labs/aion-3.0",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="aion-labs/aion-3.0",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)aionlabs
Related models
Other aionlabs models, starting with the same family.