Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰devstral-small-2507 is 100% cheaper than Mistral: Mixtral 8x7B Instruct
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | devstral-small-2507 | Mistral: Mixtral 8x7B Instruct |
|---|---|---|
| Provider | mistralai | mistralai |
| Input price / 1M tokens | Free | $0.54 |
| Output price / 1M tokens | — | $0.54 |
| Context window | 131k tokens | 33k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
Our small open-source code-agentic model.
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion...
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.