Back to Models
mistralai logoMistral
mistral-large-4
Web only

Mistral Large 4

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...

10/6/2026
524,288 tokens
Input: $1.50/M
Output: $4.60/M

Specifications

Modalities

Input
text
image
Output
text

Supported Parameters

frequency_penalty
include_reasoning
logprobs
max_tokens
presence_penalty
reasoning
reasoning_effort
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_logprobs
top_p

Max Output Tokens

262,144

Reasoning Configuration

Default
Thinking on (effort: high)
Selectable effort levels
high
none
Turning thinking off
Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention
Not retained: every host this model runs on is configured not to retain prompts
Training
Not used for training

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.3s
Throughput (p50)127 tokens/s

    Measured through FastMetal's own gateway over the last 30 days (709 first-response samples).

    Throughput is sampled once a day: the median of 16 observations over the last 30 days.

    Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

    Available in the web app only

    Mistral Large 4 can be used in FastMetal's web app, billed from your prepaid balance like any other model. It is not available through the API or MCP: a request naming it is refused by the gateway (HTTP 403).

    Open in chat

    How Mistral Large 4 actually answers

    Real responses to our standard prompts, recorded on FastMetal.

    Count the number of 'r's in 'strawberry'

    Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

    I need to count the number of 'r's in 'strawberry'. Let me go through the word letter by letter: s-t-r-a-w-b-e-r-r-y Position 1: s - not an 'r' Position 2: t - not an 'r' Position 3: **r** - yes, that's an 'r' (1st 'r') Position 4: a - not an 'r' Position 5: w - not an 'r' Position 6: b - not an 'r' Position 7: e - not an 'r' Position 8: **r** - yes, that's an 'r' (2nd 'r') Position 9: **r** - yes, that's an 'r' (3rd 'r') Position 10: y - not an 'r' There are **3** 'r's in 'strawberry'.
    19.9s response195 output tokens

    Debug This Error

    I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

    The error occurs because `users` is `undefined` when the `UserList` component renders, so calling `.map()` on it throws the error. ## Common Causes & Fixes ### 1. **The prop isn't being passed** Make sure you're passing the `users` prop when using the component: ```jsx // ❌ Wrong - no users prop passed <UserList /> // ✅ Correct <UserList users={usersArray} /> ``` ### 2. **The data hasn't loaded yet (async data)** If `users` comes from an API call, it might be `undefined` initially: ```jsx function UserList({ users }) { // Add a guard clause if (!users) { return <p>Loading...</p>; // or return null } return ( <ul> {users.map(user => <li key={user.id}>{user.name}</…
    49.4s response523 output tokens

    Code Review

    Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

    Here's a reviewed version with improvements for readability, performance, and best practices: ```python import requests import time from typing import Any def get_data(url: str, retries: int = 3, timeout: int = 10) -> list[dict[str, Any]]: """ Fetch active items from a JSON API endpoint with retry logic. Args: url: The API endpoint URL retries: Maximum number of retry attempts (default: 3) timeout: Request timeout in seconds (default: 10) Returns: List of dictionaries containing 'name' and 'id' for active items, or empty list if all retries fail """ for attempt in range(retries): try: response = r…
    27.6s response831 output tokens

    Compare these answers side by side with other models →

    Frequently asked questions

    How much does the Mistral Large 4 API cost?
    On FastMetal, Mistral Large 4 is billed per token: $1.50 per 1M input tokens and $4.60 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
    What is the context window of Mistral Large 4?
    524,288 tokens, shared between the prompt and the response.
    What do I need to try Mistral Large 4?
    Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

    Try Mistral Large 4 right now

    Mistral Large 4 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.