OpenAI: gpt-oss-120b API Pricing
by openai · 131K context window ·
Explore OpenAI's gpt-oss-120b API pricing for large language model applications. Understand the cost implications for your projects with a context window of 131,072 tokens. Input tokens are priced at $0.03900 per 1 million tokens, while output tokens cost $0.19000 per 1 million tokens, totaling $0.2290 per 1M tokens. If your application processes 100 million tokens per day (input and output combined), expect a monthly cost of approximately $687. Evaluate if OpenAI's gpt-oss-120b aligns with your budget and performance needs. Ideal for ML engineers comparing LLM API options and their associated expenses.
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | $0.01 |
| 1M tokens/month | $0.11 |
| 10M tokens/month | $1.15 |
| 100M tokens/month | $11.45 |
Compare with other models
OpenAI: gpt-oss-120b vs OpenAI: GPT-4o →OpenAI: gpt-oss-120b vs OpenAI: GPT-4o-mini →OpenAI: gpt-oss-120b vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use OpenAI: gpt-oss-120b when your quality requirements demand it.