Mistral Medium 3.5

Mistral Medium 3.5 is a balanced Mistral model for enterprise assistants, multilingual work, and tools. It is part of the mistral-medium line. It has a context window of 262144 tokens and a max output of 262144 tokens. It accepts image and text inputs and returns text. It supports reasoning mode and tool calling. The weights are open. Pricing starts at $1.50 per million input tokens and $7.50 per million output tokens, with cached input at $0.15 per million tokens. It is served by 3 hosts.

Against Mistral Medium 3.1: input $0.40 to $1.50, output $2.00 to $7.50.

• ·262k token context and output windows
• ·Supports reasoning mode and tool calling
• ·Accepts image and text, returns text
• ·Open weights for self-hosting
• ·Balanced for enterprise and multilingual tasks

• Reach for it for enterprise assistant workflows
• Reach for it for multilingual text generation
• Reach for it for tool-calling and reasoning tasks
• Reach for it for image-plus-text input tasks

3 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and max output?

Both the context window and max output are 262144 tokens.

What is the pricing?

From $1.50 per million input tokens and $7.50 per million output tokens, with cached input at $0.15 per million tokens.

Does it support image input?

Yes, it accepts image and text inputs and returns text.