Aion-3.0 vs Aion-RP 1.0 (8B)
Aion-3.0 (AionLabs) and Aion-RP 1.0 (8B) (AionLabs) are listed at different prices. Aion-RP 1.0 (8B) costs less: $0.80 per 1M input tokens and $1.60 per 1M output tokens, against $3.00 and $6.00 for Aion-3.0. Aion-3.0 has the larger context window, 131,072 tokens against 32,768 for Aion-RP 1.0 (8B). Only Aion-3.0 supports tool calling. Both accept text and produce text.
AionLabs: Aion-3.0 and AionLabs: Aion-RP 1.0 (8B) both accept and produce text. Aion-3.0 has a 131,072-token context and supports tools, response formats, and reasoning; Aion-RP 1.0 has a 32,768-token context.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Aion-3.0 | Aion-RP 1.0 (8B) |
|---|---|---|
| Maker | AionLabs | AionLabs |
| Added to catalog | 7 Jul 2026 | 4 Feb 2025 |
| Input, per 1M tokens | $3.00 | $0.80 |
| Output, per 1M tokens | $6.00 | $1.60 |
| Cached input read, per 1M | $0.75 | n/a |
| Context windowTokens | 131,072 | 32,768 |
| Max outputTokens | 32,768 | 29,491 |
| Accepts | text | text |
| Produces | text | text |
| Tool calling | Yes | No |
| Structured outputs | No | No |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Aion-3.0 | Aion-RP 1.0 (8B) |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0033 | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.080 | $0.021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.102 | $0.027 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.459 | $0.122 |
Which to choose
Choose Aion-3.0 if
- Cached input costs less: $0.75 against n/a per 1M
- You need the larger context window: 131,072 tokens against 32,768
- You need longer answers in one response: 32,768 tokens against 29,491
- You need tool calling
Choose Aion-RP 1.0 (8B) if
- Input tokens cost less: $0.80 against $3.00 per 1M
- Output tokens cost less: $1.60 against $6.00 per 1M
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.