mistral/ministral-3bOpen WeightsCompact Mistral model for edge, latency-sensitive, and cost-efficient workloads
TECHNICAL SPECIFICATIONS
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Ministral 3B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.
MCP Context Window Recommendations
With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
API CALL INVOCATION EXAMPLE
// Example: Calling Ministral 3B via OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.MISTRAL_API_KEY,
});
const response = await client.chat.completions.create({
model: "mistral/ministral-3b",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
This model supports prompt caching at $0.01 / 1M tokens, saving up to 90% on repetitive MCP tool definitions and system instructions.
MODEL RESOURCES
More Models by Mistral
Alternative and family models from the same lab
Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use