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. It activates 5.1B parameters per forward pass and is optimize…
Model details →OpenAI: gpt-oss-120b vs Qwen: Qwen-Turbo
Qwen: Qwen-Turbo wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.
Model details →Side-by-side comparison
| Capability | OpenAI: gpt-oss-120b | Qwen: Qwen-Turbo | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 131K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.04 | $0.03 | 🏆 Qwen: Qwen-Turbo |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.19 | $0.13 | 🏆 Qwen: Qwen-Turbo |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | — | 🏆 OpenAI: gpt-oss-120b |
Frequently asked questions
Is OpenAI: gpt-oss-120b better than Qwen: Qwen-Turbo?
Qwen: Qwen-Turbo wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between OpenAI: gpt-oss-120b and Qwen: Qwen-Turbo?
Input: $0.04 vs $0.03 per 1M tokens. Output: $0.19 vs $0.13 per 1M tokens.
What context windows do OpenAI: gpt-oss-120b and Qwen: Qwen-Turbo support?
OpenAI: gpt-oss-120b supports up to 131K tokens. Qwen: Qwen-Turbo supports up to 131K tokens.
Do both OpenAI: gpt-oss-120b and Qwen: Qwen-Turbo support tool calling?
OpenAI: gpt-oss-120b: yes. Qwen: Qwen-Turbo: yes.