Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used, visit [Activity](/activity), or read the `model` attribute of the respon…
Model details →Auto Router vs Qwen: Qwen Plus 0728 (thinking)
Auto Router wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Model details →Side-by-side comparison
| Capability | Auto Router | Qwen: Qwen Plus 0728 (thinking) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 2M | 1M | 🏆 Auto Router |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $-1000000.00 | $0.26 | 🏆 Auto Router |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $-1000000.00 | $0.78 | 🏆 Auto Router |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | — | 🏆 Auto Router |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Auto Router better than Qwen: Qwen Plus 0728 (thinking)?
Auto Router wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Auto Router and Qwen: Qwen Plus 0728 (thinking)?
Input: $-1000000.00 vs $0.26 per 1M tokens. Output: $-1000000.00 vs $0.78 per 1M tokens.
What context windows do Auto Router and Qwen: Qwen Plus 0728 (thinking) support?
Auto Router supports up to 2M tokens. Qwen: Qwen Plus 0728 (thinking) supports up to 1M tokens.
Do both Auto Router and Qwen: Qwen Plus 0728 (thinking) support tool calling?
Auto Router: yes. Qwen: Qwen Plus 0728 (thinking): yes.