Mistral Small 4

Mistral Small 4 is a production model from Mistral AI for chat, extraction, and cost-sensitive agents. It is part of the mistral-small line. It has a context window of 256000 tokens and a max output of 256000 tokens. Weights are open. It supports reasoning mode, tool calling, and accepts image and text inputs, returning text. Price starts at $0.15 per million input tokens and $0.60 per million output tokens, with cached input at $0.015 per million tokens. Knowledge cutoff is 2025-06. It is served by 10 hosts.

Against Mistral Small 3.2: window 128K to 256K, input $0.10 to $0.15, output $0.30 to $0.60.

Range across the hosts that serve it: up to $0.5811 per 1M input tokens.

• ·256k context and output window
• ·Reasoning mode and tool calling
• ·Accepts image and text inputs
• ·Open weights with low input price

• Reach for it for cost-sensitive agent workflows
• Reach for it for extracting structured data from text
• Reach for it for chat with long context
• Reach for it for multimodal tasks with image and text

10 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?

The context window is 256000 tokens, and max output is also 256000 tokens.

Does it support tool calling?

Yes, it supports tool calling and reasoning mode.

What is the price?

Input from $0.15 per million tokens, output from $0.60 per million tokens, cached input from $0.015 per million tokens.