AIModelsTester
Mistral AItext->text

Mistral: Devstral Medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

Context Window

131K

Input Price

$0.4000/M tokens

Output Price

$2.00/M tokens

Modality

text->text

Pricing Breakdown
Cost per million tokens for input and output
Input$0.4000/M tokens
Output$2.00/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.006000

Context Window Size
Maximum tokens the model can process in a single request
Context Window131K tokens
13% of 1M max

~98K

Words Equivalent

~66

Pages of Text

~1311

Code Functions

Best Use Cases
What this model excels at
MathReasoningAnalysis

Related Categories:

Ready to Test Mistral: Devstral Medium?

Use our free AI Models Tester to compare Mistral: Devstral Medium with other models side-by-side using your own prompts. See real results instantly.