gpt-oss-120b API price, and what each result really costs
OpenAI, listed 5 Aug 2025. Price checked 12 Nov 2026; unchanged since we started tracking it. Source: OpenRouter. openai/gpt-oss-120b
List price per million tokens
- Input
- $0.15
- Cached input
- $0.075
- Output
- $0.60
- Context window
- 131K tokens
Note: Open-weight; no first-party OpenAI API price. OpenRouter headline price; cheapest hosts start around $0.02 in / $0.07 out per 1M.
What it costs per task, and per task that works
Six common task shapes with typical token counts. The real cost counts the tries that get redone; the rates are examples, not measurements.
| Task | Per 1,000 tries | Per 1,000 that work, 8 in 10 | Per 1,000 that work, 6 in 10 | Per 1,000 that work, 4 in 10 |
|---|---|---|---|---|
| Support bot answer3,000 in / 300 out | $0.63 | $0.79 | $1.05 | $1.58 |
| Invoice field extraction2,500 in / 250 out | $0.53 | $0.66 | $0.88 | $1.31 |
| Lead scoring1,200 in / 100 out | $0.24 | $0.30 | $0.40 | $0.60 |
| Email reply draft1,500 in / 400 out | $0.47 | $0.58 | $0.78 | $1.16 |
| Translation900 in / 800 out | $0.61 | $0.77 | $1.03 | $1.54 |
| Search re-ranking4,000 in / 50 out | $0.63 | $0.79 | $1.05 | $1.58 |
Work out your own real cost per resultTest gpt-oss-120b on your own prompt
Compare gpt-oss-120b with
- GPT-4o mini$0.15 in / $0.60 outSwitch cost
- GPT-6 Luna$0.10 in / $0.50 outSwitch cost
- Mistral Small 4$0.15 in / $0.60 outSwitch cost
- MiniMax M3.1 Flash$0.15 in / $0.60 outSwitch cost
- GLM-5.3 Flash$0.15 in / $0.50 outSwitch cost
Questions
How much does the gpt-oss-120b API cost?
$0.15 per million input tokens and $0.60 per million output tokens, or $0.075 per million for cached input. Price checked 12 Nov 2026; unchanged since we started tracking it.
What does a result that works really cost with gpt-oss-120b?
A support bot answer (about 3,000 tokens in, 300 out) costs $0.00063 per try. If 6 in 10 work first time, each answer that works really costs $0.0011, because the redone ones were paid for too.