R1 vs gpt-oss-20b
Price, context window & benchmark comparison
VS
Compare different models
Verdict: gpt-oss-20b is 31.9× cheaper than R1 on a typical 3:1 input/output mix. R1 scores higher on the Artificial Analysis Intelligence Index (11.4 vs 9). gpt-oss-20b has the larger context window (131K vs 64K).
| R1 | gpt-oss-20b | |
|---|---|---|
| Input price / 1M | $0.70 | $0.018 |
| Output price / 1M | $2.50 | $0.09 |
| Blended price (3:1) | $1.15 | $0.036 |
| Cached input / 1M | — | — |
| Context window | 64K | 131K |
| Max output | 16K | 33K |
| Intelligence index | 11.4 | 9 |
| Coding index | 24.6 | 20.7 |
| Providers | — | — |
| Best provider uptime (30m) | — | — |
| Vision input | No | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2025-01-20 | 2025-08-05 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, R1 or gpt-oss-20b?
gpt-oss-20b is 31.9× cheaper than R1 on a typical 3:1 input/output mix.
R1 vs gpt-oss-20b: which has a bigger context window?
R1: 64,000 tokens. gpt-oss-20b: 131,072 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: R1 ≈ $2,650, gpt-oss-20b ≈ $81.00.
More comparisons
R1 vs GLM 5.3 PrimeR1 vs Qwen3.8 Max PrimeR1 vs Command A+R1 vs GPT-6 Luna ProR1 vs GPT-6 LunaR1 vs GPT-6 Sol ProR1 vs GPT-6 SolR1 vs Claude Opus 5.5R1 vs MiMo-V2.6-Pro-UltraSpeedR1 vs MiMo-V2.6-FlashR1 vs Grok 4.7R1 vs Qwen3.8 Omni FlashR1 vs GLM 5.3 FlashXR1 vs DeepSeek V4.1 FlashR1 vs GPT-6 AstraR1 vs GPT-6 Astra Progpt-oss-20b vs GLM 5.3 Primegpt-oss-20b vs Qwen3.8 Max Primegpt-oss-20b vs Command A+gpt-oss-20b vs GPT-6 Luna Progpt-oss-20b vs GPT-6 Lunagpt-oss-20b vs GPT-6 Sol Progpt-oss-20b vs GPT-6 Solgpt-oss-20b vs Claude Opus 5.5