Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | openaigpt-oss-120bRemove × |
|---|---|
| What’s different | gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports… |
| Date | Aug 4, 2025Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.03 in / $0.15 out/ 1M tokensNear AI · via OpenRouter · all routes ↗near-ai/fp4 · quantization=fp4 |
| Provider endpoints | 40 endpoints → |
Specifications | |
| Context window | 131.1K |
| Max output | 65.5K |
| Parameters | 120B |
| Tool calling | Supported |
| Structured output | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |