Mistral Medium 3.5 (batch)

Mistral Medium 3.5 is a 128B dense model that consolidates instruction-following, extended reasoning, and code generation capabilities into a single set of weights with optional per-request reasoning.

Strengths

Handles complex reasoning, coding tasks, and agentic workflows while supporting both text and image inputs across a 262K token context window.

Best for

Multi-step reasoning problems, code generation, and agent-based systems where you need capability across reasoning, coding, and instruction-following without switching models.

Limitations

Larger and more computationally demanding than Mistral's smaller tiers; batch-only availability means it is not suitable for real-time or latency-sensitive applications.