Aion 3.5 Mini with Jev
Aion 3.5 Mini is a model from AionLabs, released 2026-09-23. It costs $0.700 per million input tokens and $1.40 per million output tokens, reads up to 262K tokens of context, and writes up to 32,768 tokens in one reply. Through llm11, set model to aion-labs/aion-3.5-mini.
- Input price
- $0.700 / 1M
- Output price
- $1.40 / 1M
- Context window
- 262K tokens
- Max output
- 33K tokens
- Cached input
- $0.180 / 1M
- Released
- 2026-09-23
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 44% of the 332 priced models we can call cost more.
Using Aion 3.5 Mini with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Aion 3.5 Mini does the answering when Jev sends it work, or when you name it yourself. At list price Aion 3.5 Mini falls in the llm11-balanced band, but no pack routes to it because AionLabs is not one of the labs the packs draw from. You can still pin it: pass aion-labs/aion-3.5-mini as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Aion 3.5 Mini with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00063 | $0.630 |
| Question over retrieved documents | 4,000 / 500 | $0.00350 | $3.50 |
| Long document summary | 30,000 / 1,000 | $0.022 | $22.40 |
Cheaper models to try
The catalogue has no benchmark score for Aion 3.5 Mini, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Google Gemini 3.5 Flash Lite | $0.300 | $2.50 | 1.05M | |
| Google Gemini 2.5 FlashRetires 2026-10-20 | $0.300 | $2.50 | 1.05M | |
| Qwen Qwen2.5 VL 72B Instruct | $0.800 | $1.00 | 128K | |
| Mistral Devstral 2 2512 | $0.400 | $2.00 | 262K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="aion-labs/aion-3.5-mini",
messages=[{"role": "user", "content": "Hello"}],
)More from AionLabs
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Aion 3.5 | $3.00 | $6.00 | 262K | |
| Aion-3.0 | $3.00 | $6.00 | 131K | |
| Aion-3.0-Mini | $0.700 | $1.40 | 131K | |
| Aion-2.0 | $0.800 | $1.60 | 131K | |
| Aion-RP 1.0 (8B) | $0.800 | $1.60 | 33K |
Questions
- What is Aion 3.5 Mini with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Aion 3.5 Mini does the answering when Jev sends it work, or when you name it yourself. At list price Aion 3.5 Mini falls in the llm11-balanced band, but no pack routes to it because AionLabs is not one of the labs the packs draw from. You can still pin it: pass aion-labs/aion-3.5-mini as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Aion 3.5 Mini a System One model?
- No. Aion 3.5 Mini answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Aion 3.5 Mini cost?
- $0.700 per million input tokens and $1.40 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00350, so a thousand of them is about $3.50. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Aion 3.5 Mini context window?
- 262,144 tokens, with up to 32,768 tokens in a single reply.
- Does Aion 3.5 Mini support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Aion 3.5 Mini through llm11?
- Yes. Set model to aion-labs/aion-3.5-mini on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Aion 3.5 Mini?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Aion 3.5 Mini falls in the llm11-balanced band, but no pack routes to it because AionLabs is not one of the labs the packs draw from. You can still pin it: pass aion-labs/aion-3.5-mini as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Aion 3.5 Mini?
- Nearest in price and below it: Google Gemini 3.5 Flash Lite at $0.300 in and $2.50 out, Google Gemini 2.5 Flash at $0.300 in and $2.50 out and Qwen Qwen2.5 VL 72B Instruct at $0.800 in and $1.00 out. The catalogue has no benchmark score for Aion 3.5 Mini, so this is a price ordering. It does not claim these answer as well.