AGENTKERNEL
- Home
- All models
- gpt-oss-120b
gpt-oss-120b: price, performance and context
Open gpt-oss-120b by OpenAI costs $0.037 per 1M input and $0.17 per 1M output tokens, handles up to 131.1K tokens in one request (≈ 390 pages of text) and scores 11.6 points on the AgentKernel performance index, rank 142 of 212.
Privacy: zero data retention with 20 providers, including in the EU. Availability over the last 24 h: 100%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $0.037
- Output / 1M tokens
- $0.17
- Context window
- 131.1K tokens
- Max. output
- 118K tokens
- Performance index
- 11.6 points · rank 142 of 212
- Coding index
- 30.4 points · rank 84 of 119
- Agentic index
- 3.7 points · rank 62 of 91
- Cost at your usage
- $0.08 / month
- Knowledge cutoff
- Jun 2024
- In the catalog since
- Aug 05, 2025
- Capabilities
- Reasoning, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.00 | 104,000 |
| Email draftsBullet points in, a finished email out | $0.00 | 129,000 |
| Document summariesRead 10 pages, write a one-page summary | $0.00 | 48,000 |
| Code reviewsReview and comment on 500 lines of code | $0.00 | 27,000 |
| Book analysesAnalyse a 300-page book in one go | $0.004 | 2,500 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| Ling 3.0 Flash VLinclusionAI | Open | 24.6 | $0.036 |
| Ling 3.0 FlashinclusionAI | Open | 20.1 | $0.037 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| MiniMax M1MiniMax | Proprietary | 11.7 | $1.10 |
| Sonar Reasoning ProPerplexity | Proprietary | 11.8 | $4.00 |
| Qwen3 Coder 480B A35BQwen | Open | 11.9 | $0.55 |