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 lower-latency inference and deplo…
Model details →OpenAI: gpt-oss-20b vs Qwen: Qwen3 235B A22B
OpenAI: gpt-oss-20b wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "n…
Model details →Side-by-side comparison
| Capability | OpenAI: gpt-oss-20b | Qwen: Qwen3 235B A22B | 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. | $0.03 | $0.46 | 🏆 OpenAI: gpt-oss-20b |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.11 | $1.82 | 🏆 OpenAI: gpt-oss-20b |
| 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 | Yes | Tie |
Frequently asked questions
Is OpenAI: gpt-oss-20b better than Qwen: Qwen3 235B A22B?
OpenAI: gpt-oss-20b 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-20b and Qwen: Qwen3 235B A22B?
Input: $0.03 vs $0.46 per 1M tokens. Output: $0.11 vs $1.82 per 1M tokens.
What context windows do OpenAI: gpt-oss-20b and Qwen: Qwen3 235B A22B support?
OpenAI: gpt-oss-20b supports up to 131K tokens. Qwen: Qwen3 235B A22B supports up to 131K tokens.
Do both OpenAI: gpt-oss-20b and Qwen: Qwen3 235B A22B support tool calling?
OpenAI: gpt-oss-20b: yes. Qwen: Qwen3 235B A22B: yes.