AI Rate CardDeepSeek-V3 vs GPT OSS 120B: API price and specs
GPT OSS 120B is 89% cheaper than DeepSeek-V3 on input price.
GPT OSS 120B is 86% cheaper than DeepSeek-V3 on output price.
GPT OSS 120B is 88% cheaper than DeepSeek-V3 on a 1M-in / 200k-out workload.
DeepSeek-V3 has a 25.1% larger context than GPT OSS 120B.
| Field | DeepSeek-V3 | GPT OSS 120B |
|---|---|---|
| Lowest input, per 1M | $0.25 +825.9% | $0.027 |
| Median input, per 1M | $0.32 +113.3% | $0.15 |
| Lowest output, per 1M | $0.71 +626.5% | $0.098 |
| Median output, per 1M | $0.94 +56.5% | $0.60 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.39 +742.1% | $0.0466 |
| Context | 164K | 131K +20.1% |
| Max output | 164K | 131K +20.1% |
| Providers | 14 +67.4% | 43 |
| Regions | EU, US | EU, GLOBAL, US |
| Accepts | text | file, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | yes |
| Cheapest provider | siliconflow | 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
aihubmix, aiml, deepinfra, edenai, fastrouter, helicone, huggingface, novita, poe, requesty, siliconflow, togetherai, trustedrouter
Frequently asked questions
Which is cheaper, DeepSeek-V3 or GPT OSS 120B?
GPT OSS 120B is 89% cheaper than DeepSeek-V3 on input price. GPT OSS 120B is 86% cheaper than DeepSeek-V3 on output price. GPT OSS 120B is 88% cheaper than DeepSeek-V3 on a 1M-in / 200k-out workload.
Which has the larger context, DeepSeek-V3 or GPT OSS 120B?
DeepSeek-V3: 164K tokens; GPT OSS 120B: 131K tokens.
Where can I use both DeepSeek-V3 and GPT OSS 120B?
aihubmix, aiml, deepinfra, edenai, fastrouter, helicone, huggingface, novita, poe, requesty, siliconflow, togetherai, trustedrouter