AI Rate CardAion-3.0 vs Hy-MT2-1.8B: API price and specs
Hy-MT2-1.8B is 99% cheaper than Aion-3.0 on input price.
Hy-MT2-1.8B is 97% cheaper than Aion-3.0 on output price.
Hy-MT2-1.8B is 98% cheaper than Aion-3.0 on a 1M-in / 200k-out workload.
Aion-3.0 has a 1500% larger context than Hy-MT2-1.8B.
| Field | Aion-3.0 | Hy-MT2-1.8B |
|---|---|---|
| Lowest input, per 1M | $3.00 +6718.2% | $0.044 |
| Median input, per 1M | $3.08 +6905.7% | $0.044 |
| Lowest output, per 1M | $6.00 +3289.8% | $0.18 |
| Median output, per 1M | $6.17 +3383.1% | $0.18 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $4.20 +5189.7% | $0.0794 |
| Context | 131K | 8K +93.8% |
| Max output | 33K | 4K +87.5% |
| Providers | 4 | 3 +25% |
| Regions | — | — |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | kilo | kilo |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
Frequently asked questions
Which is cheaper, Aion-3.0 or Hy-MT2-1.8B?
Hy-MT2-1.8B is 99% cheaper than Aion-3.0 on input price. Hy-MT2-1.8B is 97% cheaper than Aion-3.0 on output price. Hy-MT2-1.8B is 98% cheaper than Aion-3.0 on a 1M-in / 200k-out workload.
Which has the larger context, Aion-3.0 or Hy-MT2-1.8B?
Aion-3.0: 131K tokens; Hy-MT2-1.8B: 8K tokens.
Where can I use both Aion-3.0 and Hy-MT2-1.8B?
aiml, kilo, openrouter