Compare
Devstral Medium 2507 vs Devstral Small 2505
This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.
Context window · side by side
Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.
Same context window size for both models.
Devstral Medium 2507 and Devstral Small 2505 have identical context windows (128K tokens). Devstral Small 2505 is 75% cheaper on input.
Quick verdicts
Short takeaways — validate with your own workloads.
RAG / high-volume retrieval
Use Devstral Small 2505. Input tokens are 75% cheaper — critical when sending large retrieved contexts.
Full specs
Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.
| Spec | Devstral Medium 2507 | Devstral Small 2505 |
|---|---|---|
| Context window | 128,000 tokens (128K) | 128,000 tokens (128K) |
| Max output tokens | 128,000 tokens (128K) | 128,000 tokens (128K) |
| Speed tier | Balanced | Balanced |
| Vision | No | No |
| Function calling | Yes | Yes |
| Extended thinking | No | No |
| Prompt caching | No | No |
| Batch API | No | No |
| Release date | N/A | N/A |
Pricing matrix
Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.
| Provider | Devstral Medium 2507 in | Devstral Medium 2507 out | Devstral Small 2505 in | Devstral Small 2505 out |
|---|---|---|---|---|
| Fireworks | — | — | $0.900/M | $0.900/M |
| Mistral | $0.400/M | $2.00/M | $0.100/M | $0.300/M |
Frequently asked questions
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model