Aion-labs model
Aion-3.0 API cost calculator
Aion-3.0 costs $3 per 1M input tokens and $6 per 1M output tokens on the Aion-labs API, with a 131K-token context window. A typical request (2K input, 500 output tokens) costs $0.0090 — about $270/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Aion-3.0
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0033 | $3.30 |
| RAG query with context | 4,000 / 500 | $0.01 | $15.00 |
| Document summarization | 20,000 / 1,000 | $0.07 | $66.00 |
| Agent coding session | 100,000 / 5,000 | $0.33 | $330 |
Aion-3.0 vs other Aion-labs models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Aion-3.0 | $3 | $6 | 131K |
| Aion-3.0-Mini | $0.70 | $1.40 | 131K |
| Aion-2.0 | $0.80 | $1.60 | 131K |
| Aion-RP 1.0 (8B) | $0.80 | $1.60 | 33K |
Frequently asked questions
How much does Aion-3.0 cost per 1M tokens?
According to current pricing data, Aion-3.0 costs $3 per 1M input tokens and $6 per 1M output tokens. Processing 1M tokens each way costs $9.00.
What does a typical API request to Aion-3.0 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0090. At 1,000 requests per day that is $9.00 daily, or about $270 per month.
What is Aion-3.0's context window?
Aion-3.0 supports a 131K-token context window (131,072 tokens).
Does Aion-3.0 support prompt caching?
Yes. Cached input tokens cost $0.75 per 1M — a 75% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Aion-3.0?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $3 for Aion-3.0 — roughly 300x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Aion-3.0 vs Ling-2.6-flash pricing, or run Aion-3.0 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.