Back to models
Mistral·Mistral Large family
Mistral Large 3
Open WeightsMoEapache-2.0Released Dec 2025
Mistral AI's largest open-weight model with 41B active parameters (675B total MoE). State-of-the-art general-purpose multimodal model with 256K context window and powerful agentic capabilities. Released under Apache 2.0.
Capabilities
chatcompletionfunction-callingvisioncode-generationreasoning
Modalities
textimagecode
Context Window
256K tokens
Providers
4
available
Available from 4 providers
Cheapest
Together AI
$3.60/1M tokens
Amazon Bedrock, Azure AI, Mistral AI, Together AI
Providers (4)
Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.
| Provider | Pricing (per 1M) | Rate Limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| Together AI | In: $1.80Out: $1.80 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Healthy | 0ms |
| Amazon Bedrock | In: $2.00Out: $6.00 | 100 RPM / 300K TPM | us-east-1us-west-2eu-west-1 | Healthy | 0ms |
| Azure AI | In: $2.00Out: $6.00 | 200 RPM / 400K TPM | us-east-1us-west-2eu-west-1 | Healthy | 0ms |
| Mistral AI | In: $2.00Out: $6.00 | 300 RPM / 500K TPM | eu-west-1us-east-1global | Healthy | 0ms |
Quick Start
Use this model via Together AI with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.together.xyz/v1",
apiKey: process.env.TOGETHER_API_KEY,
});
const response = await client.chat.completions.create({
model: "mistralai/Mistral-Large-3",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using Together AI API • OpenAI-compatible SDK