Extract vs gpt-oss-120b
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Extract is 8.7× cheaper than gpt-oss-120b on a typical 3:1 input/output mix. Extract has the larger context window (1M vs 131K).
| Extract | gpt-oss-120b | |
|---|---|---|
| Input price / 1M | $0.04 | $0.15 |
| Output price / 1M | Free | $0.60 |
| Blended price (3:1) | $0.03 | $0.26 |
| Cached input / 1M | — | $0.075 |
| Context window | 1M | 131K |
| Max output | 900K | 66K |
| Intelligence index | — | 3.8 |
| Coding index | — | 30.4 |
| Providers | — | — |
| Best provider uptime (30m) | — | — |
| Vision input | Yes | No |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Released | 2026-10-13 | 2025-08-05 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Extract or gpt-oss-120b?
Extract is 8.7× cheaper than gpt-oss-120b on a typical 3:1 input/output mix.
Extract vs gpt-oss-120b: which has a bigger context window?
Extract: 1,000,000 tokens. gpt-oss-120b: 131,072 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Extract ≈ $80.00, gpt-oss-120b ≈ $600.00.
More comparisons
Extract vs Gemini 4 CarbonExtract vs Claude Fable 5.2Extract vs Gemini Omni 1.2 FlashExtract vs Gemini Omni 1.1 FlashExtract vs Hy4Extract vs GLM 5.3 FlashX LegalExtract vs GPT-6.1 TerraExtract vs GPT-6.1 Terra ProExtract vs Kimi K3.1 ProExtract vs MiniMax M3.1 FlashExtract vs DeepSeek V4.1 Flash 1017Extract vs Nemotron 3.5 Super VLExtract vs Gemini 4 ArgonExtract vs Claude Haiku 5.5Extract vs Nano Banana 2.1Extract vs Mistral Large 4gpt-oss-120b vs Gemini 4 Carbongpt-oss-120b vs Claude Fable 5.2gpt-oss-120b vs Gemini Omni 1.2 Flashgpt-oss-120b vs Gemini Omni 1.1 Flashgpt-oss-120b vs Hy4gpt-oss-120b vs GLM 5.3 FlashX Legalgpt-oss-120b vs GPT-6.1 Terragpt-oss-120b vs GPT-6.1 Terra Pro