Devstral-2512 vs Qwen3-Coder-480B-A35B-Instruct: API Pricing Compared
Side-by-side API pricing and capabilities for Devstral-2512 and Qwen3-Coder-480B-A35B-Instruct. Both are available through Riven behind one OpenAI-compatible endpoint — at vendor list price with transparent per-token pricing, or a flat $3 per million tokens on pay-as-you-go.
| Devstral-2512 | Qwen3-Coder-480B-A35B-Instruct | |
|---|---|---|
| Input price ($/1M tokens) | $0.40 | $0.40 |
| Output price ($/1M tokens) | $2.00 | $1.60 |
| Vendor | provider | qwen |
| Capabilities | chat, code | chat, code |
Model pages: Devstral-2512 · Qwen3-Coder-480B-A35B-Instruct
FAQ
Which is cheaper, Devstral-2512 or Qwen3-Coder-480B-A35B-Instruct?
On Riven both are billed at vendor list price with transparent per-token pricing: Devstral-2512 is $0.40/1M input and $2.00/1M output; Qwen3-Coder-480B-A35B-Instruct is $0.40/1M input and $1.60/1M output. On the pay-as-you-go plan, every model is a flat $3 per million tokens.
Can I use Devstral-2512 and Qwen3-Coder-480B-A35B-Instruct 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.