Last refreshed 2026-10-18. Next refresh: weekly.
Why use Mistral Medium 3 on Microsoft Foundry?
Microsoft Foundry offers Mistral Medium 3. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.
Compare Mistral Medium 3 across 5 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: mistral-medium-2505Model ID
mistral-medium-2505Request example
Curated snippets for this provider are not sourced yet. Use Microsoft Foundry documentation with model ID
mistral-medium-2505.Gotchas
- Use provider model ID "mistral-medium-2505", not the LLMReference slug "mistral-medium-3".
Compare Mistral Medium 3 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Mistral AI Studio | $0.40 | $2.00 |
| Microsoft Foundry | — | — |
| OpenRouter | $0.40 | $2.00 |
| GCP Vertex AI | $0.40 | $2.00 |
Capabilities
VisionMultimodalJSON / Tool useStructured OutputsCode Execution
About Mistral Medium 3
Mistral Medium 3 is Mistral AI's enterprise-grade model delivering frontier-level capabilities including vision, function calling, and code generation at competitive cost for business applications.
Get Started
Model Specs
Released2025-05-01
Context128K
ArchitectureDecoder Only
Knowledge cutoff2025-03