Codestral-2508 vs GPT-5.6: API Pricing Compared
Side-by-side API pricing and capabilities for Codestral-2508 and GPT-5.6. Both are available through Riven behind one OpenAI-compatible endpoint — at vendor list price with transparent per-token pricing, or a flat $3 per million tokens on pay-as-you-go.
| Codestral-2508 | GPT-5.6 | |
|---|---|---|
| Input price ($/1M tokens) | $0.30 | $5.00 |
| Output price ($/1M tokens) | $0.90 | $30.00 |
| Vendor | provider | provider |
| Capabilities | chat, code | chat, reasoning |
Model pages: Codestral-2508 · GPT-5.6
FAQ
Which is cheaper, Codestral-2508 or GPT-5.6?
On Riven both are billed at vendor list price with transparent per-token pricing: Codestral-2508 is $0.30/1M input and $0.90/1M output; GPT-5.6 is $5.00/1M input and $30.00/1M output. On the pay-as-you-go plan, every model is a flat $3 per million tokens.
Can I use Codestral-2508 and GPT-5.6 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.