AI Model DirectorySearch
Search models, providers, and docs
AI Model DirectorySearch models, providers, and docs
A side-by-side comparison of gpt-oss-120b and Qwen3.8 Flash, using the lowest price and highest limits found across every provider that offers each model.
| gpt-oss-120b | Qwen3.8 Flash | |
|---|---|---|
| Providers | 61 | 47 |
| Cheapest input ($/M) | $0 via FastRouter | $0.0192 via UnoRouter |
| Cheapest output ($/M) | $0 via FastRouter | $0.0602 via UnoRouter |
| Max context | 131.1K | 1.1M |
| Max output | 131.1K | 1M |
| Released | Jan 1, 2024 | Aug 25, 2026 |
| Open weights | Yes | Yes |
| Features | ReasoningToolsStructured outputTemperature | ReasoningToolsStructured outputFilesTemperature |
| Input modalities | Text | ImageTextVideo |
| Output modalities | Text | Text |