Using Mistral Large 2 (2407) on Microsoft Foundry
Implementation guide · Mistral Large · MistralAI
ServerlessOpen Weights
Microsoft Foundry exposes Mistral Large 2 (2407) through model ID mistral-large-2-2407. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-16. Next refresh: weekly.
Quick Start
- 1
- 2Use the Microsoft Foundry SDK or REST API to call
mistral-large-2-2407— see the documentation for request format. - 3
Code Examples
Pricing on Microsoft Foundry
| Type | Price (per 1M) |
|---|---|
| Input tokens | $3.00 |
| Output tokens | $9.00 |
Capabilities
VisionStructured Outputs
About Mistral Large 2 (2407)
Flagship sparse MoE Mistral model (675B total, 41B active) with 256K context and multimodal capabilities. Leads benchmarks in complex reasoning and long-context processing.
Model Specs
Released2024-07-23
Parameters123B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-03