Tasks and inputs
Mistral Medium 3.5 is listed for Image-text-to-text, Text generation. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
Mistral Medium 3.5 is an open-weight multimodal model for coding and agent applications, released.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Mistral Medium 3.5 is an open-weight multimodal model for coding and agent applications, released.
The documented context allowance is 256,000 tokens. Function calling and structured responses support application workflows, but those features still need validation in the finished client. Test an actual repository issue, a document extraction job and an interaction that needs more than one tool result.
The weights use a Modified MIT licence. Read the modification rather than treating it as ordinary MIT solely because the name contains those letters. A hosted API route has separate service terms, limits and billing.
Base API rates shown in the documentation are $1.50 input and $7.50 output per million tokens. Include retries, caching and the processing tier in a budget. Record which model identifier the host resolves before comparing it with another route.
Keep a fixed set of tasks from your existing application. For code, run the acceptance tests and inspect unrelated changes. For documents, include a missing answer and conflicting passages. For agents, log incorrect arguments and repeated ineffective calls. Compare total accepted-task cost with Mistral Small 4, then assign a larger model only where the measured outcome justifies it.
Publisher source 1 Deployment limits and commercial terms belong to the selected checkpoint or API route.
Compare the model on the work you need to complete.
Mistral Medium 3.5 is listed for Image-text-to-text, Text generation. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 256K context and 262.14K maximum output. The listed route charges $1.50 input and $7.50 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under Modified MIT. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Anthropic
Claude’s small model for high-volume extraction, classification and routing, with adaptive thinking and a 1M-token context window.
Mistral AI
Mistral Large 4 is an open-weight multimodal model released in public preview on the publisher’s announced release, for general reasoning, coding and agent applications.
OpenAI
GPT-6.1 Sol is OpenAI's updated Sol model for coding and professional tasks. It accepts text and images and returns text.
inclusionAI
Ling 3.1 Flash is inclusionAI’s hybrid reasoning model for coding and tool agents, available through a hosted AI Gateway route.
Anthropic
Claude Sonnet 5.5 is an Anthropic language model that accepts text and images and returns text.
MiniMax
MiniMax M3.1 Flash Preview is a multimodal reasoning model for code and agent workflows, accessed through eligible MiniMax plans and tools.