AI Rate CardGPT OSS 120B vs Apertus 70B: API price and specs
GPT OSS 120B is 94% cheaper than Apertus 70B on input price.
GPT OSS 120B is 96% cheaper than Apertus 70B on output price.
GPT OSS 120B is 95% cheaper than Apertus 70B on a 1M-in / 200k-out workload.
GPT OSS 120B has a 100% larger context than Apertus 70B.
| Field | GPT OSS 120B | Apertus 70B |
|---|---|---|
| Lowest input, per 1M | $0.027 | $0.45 +1556.1% |
| Median input, per 1M | $0.15 | $0.82 +446.7% |
| Lowest output, per 1M | $0.098 | $2.23 +2180% |
| Median output, per 1M | $0.60 | $2.35 +291.3% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.0466 | $0.89 +1818.5% |
| Context | 131K | 66K +50% |
| Max output | 131K | 30K +77.1% |
| Providers | 43 | 5 +88.4% |
| Regions | EU, GLOBAL, US | — |
| Accepts | file, text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | yes | no |
| Cheapest provider | kilo | regolo-ai |
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
aki-io, cortecs, huggingface, regolo-ai, trustedrouter
Frequently asked questions
Which is cheaper, GPT OSS 120B or Apertus 70B?
GPT OSS 120B is 94% cheaper than Apertus 70B on input price. GPT OSS 120B is 96% cheaper than Apertus 70B on output price. GPT OSS 120B is 95% cheaper than Apertus 70B on a 1M-in / 200k-out workload.
Which has the larger context, GPT OSS 120B or Apertus 70B?
GPT OSS 120B: 131K tokens; Apertus 70B: 66K tokens.
Where can I use both GPT OSS 120B and Apertus 70B?
aki-io, cortecs, huggingface, regolo-ai, trustedrouter