Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | openaiOpenAI: gpt-oss-20b (batch)Remove × |
|---|---|
| What’s different | 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... |
| Date | Aug 5, 2025Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.024 in / $0.112 out/ 1M tokensDeepInfra · via OpenRouter · all routes ↗deepinfra/bf16 · quantization=bf16 |
| Provider endpoints | 2 endpoints → |
Specifications | |
| Context window | 131.1K |
| Max output | 118K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Reasoning | Supported |
| Open weights | Supported |