Mistral Medium 3.5

Mistral Medium 3.5 is a Mistral AI model available in Quad Chat, with up to 256K tokens of context, image input, tool calling and step-by-step reasoning.

Mistral Medium 3.5 at a glance

LabMistral AI
Available onPro plan and up
Context window256K tokens
Max output256K tokens
Image inputYes
Tool callingYes
ReasoningYes
Privacy lanePrivate (Zero Data Retention)

How to use Mistral Medium 3.5 in Quad Chat

  1. Create a free account or sign in.
  2. Open the model picker and choose Mistral Medium 3.5.
  3. Ask, attach files, or compare the answer with another model.

Sign in or create a free account · Compare plans

Frequently asked questions

Can I use Mistral Medium 3.5 for free?

Mistral Medium 3.5 needs the Pro plan ($15/month) or higher. The Free plan needs no credit card and includes other chat models, so you can try Quad Chat first and upgrade when you need Mistral Medium 3.5. Yearly billing is 15% less than paying monthly.

What is the context window of Mistral Medium 3.5?

Mistral Medium 3.5 accepts up to 256K tokens of context and can write up to 256K tokens in one reply, according to the model catalog Quad Chat routes through. Files, pasted text and earlier messages all count toward that window.

Does Mistral Medium 3.5 support images, tools and reasoning?

Mistral Medium 3.5 accepts images as input, so you can attach screenshots, photos and scanned pages. It supports tool calling. It can reason step by step before it answers. You can switch to another model in the same conversation at any time.

Is Mistral Medium 3.5 private in Quad Chat?

Mistral Medium 3.5 runs on the Quad Chat Private Lane, routed to providers under Zero Data Retention terms. Quad Chat does not train models on your conversations, encrypts chats in transit and at rest, and lets you export or delete them at any time.

How much does Mistral Medium 3.5 cost in Quad Chat?

Quad Chat plans have a flat monthly price and draw usage from shared credits, not a per-token bill. The model picker shows an estimate before you send. For reference, the provider's API list price is $1.50 per million input tokens and $7.50 per million output tokens.

Can I compare Mistral Medium 3.5 with other models?

Yes. Send one prompt to Mistral Medium 3.5 and one or two other models, such as Mistral Large 3, GPT-6.1 Sol and Gemini 3.8 Flash, and compare the answers side by side in the same thread. You can also switch models mid-conversation without losing your files or context.

Related models

All AI models in Quad Chat