AI Rate CardQwen3 14B vs gpt-oss-120b-ultra: API price and specs
Qwen3 14B is 65% cheaper than gpt-oss-120b-ultra on input price.
Qwen3 14B is 76% cheaper than gpt-oss-120b-ultra on output price.
Qwen3 14B is 70% cheaper than gpt-oss-120b-ultra on a 1M-in / 200k-out workload.
gpt-oss-120b-ultra has a 0.1% larger context than Qwen3 14B.
| Field | Qwen3 14B | gpt-oss-120b-ultra |
|---|---|---|
| Lowest input, per 1M | $0.07 | $0.20 +185.7% |
| Median input, per 1M | $0.12 | $0.20 +66.7% |
| Lowest output, per 1M | $0.23 | $0.95 +316.7% |
| Median output, per 1M | $0.24 | $0.95 +295.8% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.12 | $0.39 +237.4% |
| Context | 131K +0.1% | 131K |
| Max output | 131K +0.1% | 131K |
| Providers | 12 | 4 +66.7% |
| Regions | EU, US | US |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | siliconflow | deepinfra |
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
deepinfra, edenai, fastrouter, trustedrouter
Frequently asked questions
Which is cheaper, Qwen3 14B or gpt-oss-120b-ultra?
Qwen3 14B is 65% cheaper than gpt-oss-120b-ultra on input price. Qwen3 14B is 76% cheaper than gpt-oss-120b-ultra on output price. Qwen3 14B is 70% cheaper than gpt-oss-120b-ultra on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 14B or gpt-oss-120b-ultra?
Qwen3 14B: 131K tokens; gpt-oss-120b-ultra: 131K tokens.
Where can I use both Qwen3 14B and gpt-oss-120b-ultra?
deepinfra, edenai, fastrouter, trustedrouter