Mistral's flagship that merges instruction following, reasoning and coding in one set of weights. Understands images, and reasoning effort is configurable per request.
| SWE-Bench Verified | 77.6 | |
|---|---|---|
| τ³-Telecom | 91.4 |
Which GPU does Mistral Medium 3.5 128B need?
The entry configuration is 1x H200, which delivers around 14 tokens per second. For more parallel requests and headroom on speed, go with 2x H200.
How much does Mistral Medium 3.5 128B cost?
An hour of Mistral Medium 3.5 128B runs from $3.86 to $8.28 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.
How do I call Mistral Medium 3.5 128B from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass mistral-medium-3.5:128b as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. Mistral Medium 3.5 128B runs on a dedicated GPU server inside a private environment: requests and responses never reach the model vendor and are not used for training.
What context window and license does Mistral Medium 3.5 128B have?
Mistral Medium 3.5 128B holds 32K tokens of context per request and ships under the Modified MIT license, so you can use it commercially on your own hosting terms.