Mistral AI • 24 Billion32,000 Token Context

Mistral Small 3 (24B) Token Pricing & VRAM Calculator

High-efficiency open-weights model fine-tuned for reasoning and multi-lingual tasks. Ideal for: Fast local responses, agent tool use, low-memory laptops.

API Cost (per 1M Tokens)

$0.20 / 1M Input

$0.60 / 1M Output

100k input tokens = ~$0.0200 | 100k output = ~$0.0600

Local VRAM & GPU Specs

16 GB

RTX 4080 (16GB) or Apple Silicon M2/M3

Local Ollama Run

ollama run mistral-small

Inspect port 11434: Port 11434 Guide

Compare Other AI Foundation Models

GPT-4o (Omni)$2.5/1M in Claude 3.5 Sonnet$3/1M in DeepSeek R1 (Reasoning)$0.55/1M in Llama 3.3 70B Instruct$0.7/1M in Qwen 2.5 Coder 32B$0.3/1M in

Frequently Asked Questions

How much does Mistral Small 3 (24B) cost per 1M tokens?

Mistral Small 3 (24B) costs $0.20 per million input tokens and $0.60 per million output tokens.

What GPU is needed to run Mistral Small 3 (24B) locally?

Mistral Small 3 (24B) requires at least 16GB VRAM for 4-bit quantization. Recommended hardware: RTX 4080 (16GB) or Apple Silicon M2/M3.

What is the context window size of Mistral Small 3 (24B)?

Mistral Small 3 (24B) supports a context window of 32,000 tokens.