Qwen3-Max vs Qwen3-235B-A22B-Instruct-2507: API Pricing Compared
Side-by-side API pricing and capabilities for Qwen3-Max and Qwen3-235B-A22B-Instruct-2507. Both are available through Riven behind one OpenAI-compatible endpoint — at vendor list price with transparent per-token pricing, or a flat $3 per million tokens on pay-as-you-go.
| Qwen3-Max | Qwen3-235B-A22B-Instruct-2507 | |
|---|---|---|
| Input price ($/1M tokens) | $2.11 | $0.07 |
| Output price ($/1M tokens) | $8.45 | $0.10 |
| Vendor | qwen | qwen |
| Capabilities | chat | chat |
Model pages: Qwen3-Max · Qwen3-235B-A22B-Instruct-2507
FAQ
Which is cheaper, Qwen3-Max or Qwen3-235B-A22B-Instruct-2507?
On Riven both are billed at vendor list price with transparent per-token pricing: Qwen3-Max is $2.11/1M input and $8.45/1M output; Qwen3-235B-A22B-Instruct-2507 is $0.07/1M input and $0.10/1M output. On the pay-as-you-go plan, every model is a flat $3 per million tokens.
Can I use Qwen3-Max and Qwen3-235B-A22B-Instruct-2507 with one API key?
Yes. One Riven key reaches both models through the same OpenAI-compatible endpoint, so you can A/B them by changing only the model id.
Is there a markup on these prices?
No. Riven lists these models at vendor list price with transparent per-token pricing. Pay-as-you-go users instead pay a flat $3 per million tokens across every model.