Mistral Medium 3 5: capabilities, context and price
Mistral Medium 3 5 is a Mistral route represented in Tavory for mistral medium 3.5 is a dense 128b instruction following model from mistral ai. it supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. it is particularly strong at reliable multi tool calling and long horizon tasks, with a 256k context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. self hostable on as few as four gpus and available under open weights..
Tavory's live catalog lists Mistral Medium 3 5 through Mistral. The route is described as mistral medium 3.5 is a dense 128b instruction following model from mistral ai. it supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. it is particularly strong at reliable multi tool calling and long horizon tasks, with a 256k context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. self hostable on as few as four gpus and available under open weights.. This page summarizes the current catalog facts so you can compare context, capabilities and provider price signals before opening a workspace request. Availability, plan access and final cost are checked again when you send.
Good fit for
text and chat
reasoning and analysis
document work
image understanding
Strengths and limitations
Catalog strengths
Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.
4/5 catalog quality signal
4/5 catalog speed signal
Keep in mind
Live availability and plan access can change.
Catalog signals do not guarantee a result for every prompt.
How to use Mistral Medium 3 5 in Tavory
01
Open the workspace
Sign in, start a conversation and keep the task or project context together.
02
Choose Mistral Medium 3 5
Select the model manually so Tavory preserves your choice for the request.
03
Review the result
Check the displayed model, answer, usage and settled cost before continuing.
Tavory's live catalog lists Mistral Medium 3 5 through Mistral. The route is described as mistral medium 3.5 is a dense 128b instruction following model from mistral ai. it supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. it is particularly strong at reliable multi tool calling and long horizon tasks, with a 256k context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. self hostable on as few as four gpus and available under open weights.. This page summarizes the current catalog facts so you can compare context, capabilities and provider price signals before opening a workspace request. Availability, plan access and final cost are checked again when you send.
What can Mistral Medium 3 5 be used for?
Mistral Medium 3 5 is represented in Tavory for text and chat, reasoning and analysis, document work, image understanding. Suitability still depends on the prompt and required capabilities.
Can I use Mistral Medium 3 5 in Tavory?
If Mistral Medium 3 5 is eligible for your plan and a healthy route is available when you send, you can choose it in Tavory. Tavory is an independent workspace and is not the manufacturer of Mistral Medium 3 5.
How much does Mistral Medium 3 5 cost in Tavory?
$1.65 input / $8.25 output per 1M tokens is the current public catalog signal. Tavory checks the selected route and shows the applicable request cost; provider data can change.
