Mistral coding model for code completion, generation, and developer workflows
Codestral 2508 by mistral is offered by 6 providers on this page. Its reference price is $0.368 per 1M input tokens and $1.10 per 1M output tokens. The lowest paid channel is NanoGPT at $0.30 / $0.90 per 1M, about 1.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 256,000 tokens, with an output limit of 256,000 tokens. It supports structured output. Accepted input modalities are Text and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-03-31.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT | Gateway | $0.30 | $0.90 | $0.15 | — | 256,000 | 32,768 | |
| OpenRouter | Gateway | $0.30 | $0.90 | $0.03 | — | 256,000 | 204,800 | |
| DevPass (LLM Gateway) | Gateway | $0.30 | $0.90 | — | — | 256,000 | 16,384 | |
| LLM Gateway | Gateway | $0.30 | $0.90 | — | — | 256,000 | 256,000 | |
| Kilo Gateway | Gateway | $0.30 | $0.90 | $0.03 | — | 256,000 | 204,800 | |
| Cortecs | Gateway | $0.37 | $1.10 | $0.037 | — | 256,000 | 256,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.