AI Rate CardAion-2.0 vs Magnum v4 72B: API price and specs
Aion-2.0 is 68% cheaper than Magnum v4 72B on input price.
Aion-2.0 is 68% cheaper than Magnum v4 72B on output price.
Aion-2.0 is 68% cheaper than Magnum v4 72B on a 1M-in / 200k-out workload.
Aion-2.0 has a 300% larger context than Magnum v4 72B.
| Field | Aion-2.0 | Magnum v4 72B |
|---|---|---|
| Lowest input, per 1M | $0.80 | $2.50 +212.5% |
| Median input, per 1M | $0.82 | $2.50 +204.1% |
| Lowest output, per 1M | $1.60 | $5.00 +212.5% |
| Median output, per 1M | $1.64 | $5.00 +204.1% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.12 | $3.50 +212.5% |
| Context | 131K | 33K +75% |
| 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-2.0 or Magnum v4 72B?
Aion-2.0 is 68% cheaper than Magnum v4 72B on input price. Aion-2.0 is 68% cheaper than Magnum v4 72B on output price. Aion-2.0 is 68% cheaper than Magnum v4 72B on a 1M-in / 200k-out workload.
Which has the larger context, Aion-2.0 or Magnum v4 72B?
Aion-2.0: 131K tokens; Magnum v4 72B: 33K tokens.
Where can I use both Aion-2.0 and Magnum v4 72B?
aiml, kilo, openrouter