openai/gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DekaLLMbf16 | $0.029 | $0.140 | 131K | 98.3% |
| WandBfp4 | $0.030 | $0.130 | 131K | 99.2% |
| DeepInfrabf16 | $0.030 | $0.140 | 131K | 99.7% |
| Phala | $0.040 | $0.150 | 131K | 65.2% |
| Novitafp4 | $0.040 | $0.150 | 131K | 99.8% |
| SiliconFlowfp8 | $0.040 | $0.180 | 131K | 100% |
| Parasailfp4 | $0.040 | $0.200 | 131K | 99.5% |
| Together | $0.050 | $0.200 | 131K | — |
| Amazon Bedrock | $0.070 | $0.150 | 131K | — |
| Amazon Bedrock | $0.070 | $0.150 | 131K | 98.8% |
| $0.070 | $0.250 | 131K | 99.7% | |
| Fireworks | $0.070 | $0.300 | 131K | 98.7% |
| Groq | $0.075 | $0.300 | 131K | 99.9% |
| NextBitfp8 | $0.100 | $0.450 | 131K | 100% |
gpt-oss-20b costs $0.029 per million input tokens and $0.140 per million output tokens via OpenRouter, making it 6th cheapest of 298 paid models.
gpt-oss-20b scores 24.5 on the Artificial Analysis Intelligence Index, ranking 103rd of 178 benchmarked models, with a GPQA Diamond score of 69%.
gpt-oss-20b generates around 391 tokens per second with 247ms time-to-first-token (p50), the 7th fastest tracked model.
gpt-oss-20b supports a 131K-token context window. It accepts text input.