Ollama Cloud adds Mistral Large 4 to its live model catalogue

Ollama lists Mistral Large 4 as a cloud model and provides the command ollama run mistral-large-4:cloud. The page describes a native multimodal model with text and image input, tool use, thinking, and a 1.05T-parameter headline figure.

AIMI first recorded the Ollama endpoint at 01:03:13 SAST on 7 October 2026. The route remains available in the latest endpoint check, so this is a confirmed provider addition rather than a stale catalogue record.

Mistral published its official Mistral Large 4 announcement on 6 October 2026. It called the API a public preview and said the model weights would arrive by the end of the month. That is the maker release date.

The Ollama route appeared later. AIMI first saw Mistral's official API route at 15:03:14 SAST on 6 October, then saw the Ollama route 9 hours, 59 minutes, and 59 seconds later. The interval describes catalogue timing, not a claim that Ollama responded to Mistral.

The verified AIMI record carries a 524,288-token context window and a 262,144-token maximum output, with text and image input and text output. OpenRouter lists the same context and output limits for its Mistral Large 4 route, priced at $0.68 per million input tokens and $2.09 per million output tokens, with cached input at $0.07.

Ollama's page currently displays a 1M-token context and 1.05T total parameter count, while Mistral's launch post describes 1 trillion parameters and 52 billion active parameters. Those differences may reflect provider presentation or route configuration. Treat the limits as route-specific until you verify them in the endpoint you plan to use.

Teams already using Ollama Cloud can try the public preview without changing their application to Mistral's API. The model is aimed at coding, agentic workflows, and multimodal understanding, so it is a sensible candidate for image-aware coding assistants and document workflows.

For production work, test the exact route for latency, tool behaviour, image handling, output limits, and cost. AZ Labs AI Gateway can keep those provider differences behind one integration when a workflow needs to compare routes.