Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key
Get API key

Mistral AI · Mistral · Balanced

Mistral Large 4

Discount −65%New

Mistral's open-weight multimodal model for reasoning, coding, tool use and structured output.

Model id

mistral-large-4
Get an API keyTry in Chat

Price per 1M tokens

Input
Regular rate $1.36now $0.476
Output
Regular rate $4.18now $1.428
Cached input
$0.1471% below input

65% below the market rate.

Added here 18 Oct 2026 — read the changelog for what changed and why.

Output is 3× the input rate. $1 covers about 840 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using Mistral Large 4

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-large-4",
    "stream": true,
    "messages": [{"role": "user", "content": "Write a TypeScript endpoint that returns paginated orders for the signed-in user."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="mistral-large-4",
    messages=[{"role": "user", "content": "Write a TypeScript endpoint that returns paginated orders for the signed-in user."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "mistral-large-4",
  messages: [{ role: "user", content: "Write a TypeScript endpoint that returns paginated orders for the signed-in user." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

More: quickstart · API reference · try it in Chat first

Benchmarks reported by the vendor

Scores for Mistral Large 4 as its maker published them, with the setting they state. We have not re-run them. Versions and settings differ between vendors, so compare only identical benchmark names; compare models side by side.

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

Nearest alternative

Mistral Large 4 or DeepSeek V4 Pro (free lane)?

Mistral Large 4 is the only Mistral model here. DeepSeek V4 Pro (free lane) from DeepSeek is the closest-priced balanced-tier model from another vendor. Each comparison lists the published rates and limits, then what favours each side.

Mistral Large 4vsDeepSeek V4 Pro (free lane)

Per 1M tokensMistral Large 4DeepSeek V4 Pro (free lane)
Input$0.4763% less$0.49
Output$1.4346% more$0.98
Context524.3k48% smaller1M
Max output262.1k32% less384k

Pick Mistral Large 4 when

  • cost per request decides it: Mistral Large 4 charges input 3% less than DeepSeek V4 Pro (free lane).
  • you rely on Vision, Structured output and Prompt caching, which DeepSeek V4 Pro (free lane) does not list.
  • requests include screenshots or other images.
  • the work is coding, tool use and structured output, which this catalogue lists for Mistral Large 4 and not for DeepSeek V4 Pro (free lane).

Pick DeepSeek V4 Pro (free lane) instead when

  • the job runs well enough on the lower rates: output at 31% less.
  • inputs outgrow the 524.3k-token window of Mistral Large 4; DeepSeek V4 Pro (free lane) accepts 1M.
  • the 262.1k output cap of Mistral Large 4 cuts answers short; DeepSeek V4 Pro (free lane) writes up to 384k.
  • Mistral Large 4 does not list JSON mode and your code depends on it.
  • your workload looks like coding agents, hard reasoning and math, labels the catalogue gives DeepSeek V4 Pro (free lane) only.

Use cases

What Mistral Large 4 is listed for, and what it costs

The catalogue lists Mistral Large 4 for coding, tool use and structured output. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.

Model your own traffic

  1. Coding

    Implementing a function or endpoint: 8,000 tokens of context in, 2,000 tokens of code out.

    Capable across languages for implementation, debugging and explaining code.

    “Write a TypeScript endpoint that returns paginated orders for the signed-in user.”

    Same request on DeepSeek V4 Pro (free lane) $0.00588.

    $0.006664

    per task, about 1,500 per $10

    $0.01924 at the market rate

    0.008 × $0.476 + 0.002 × $1.43

  2. Tool use

    A request carrying 15 tool definitions: 5,000 tokens in, a 300-token tool call out.

    “Find open invoices older than 30 days and draft a reminder to each customer.”

    Same request on DeepSeek V4 Pro (free lane) $0.002744.

    $0.002808

    per tool call, about 3,561 per $10

    $0.008054 at the market rate

    0.005 × $0.476 + 0.0003 × $1.43

  3. Structured output

    One document turned into structured JSON: 4,000 tokens in, 300 tokens out.

    “Extract invoice number, date, total and currency from this text as JSON.”

    Same request on DeepSeek V4 Pro (free lane) $0.002254.

    $0.002332

    per document, about 4,288 per $10

    $0.006694 at the market rate

    0.004 × $0.476 + 0.0003 × $1.43

Overview

When Mistral Large 4 fits

Mistral Large 4 is a balanced model from Mistral AI, available here under the exact model id “mistral-large-4”. It is currently the only Mistral model we serve. Mistral AI has not published a release date we can cite; it has been available here since 18 Oct 2026.

Mistral AI documents tools, vision, reasoning, structured output and prompt caching for it, and it reads images as well as text.

It costs $0.476 per million input tokens and $1.43 per million output tokens, so output is 3× the input rate. That is 65% below the market rate of $1.36 input and $4.18 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 43% of the bill for coding, 15% for tool use and 18% for structured output, so trimming the context you send saves more than capping the answer. With a 3:1 input-to-output mix it ranks 11th lowest-cost of the 27 models on this site.

Cached input bills at $0.14 per million tokens, 71% below the standard input rate, which pays off when the same system prompt or documents go out on every request.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Similar models

Same tier, other vendors

Same key, same balance. Switching is a change to the model field.

Compare side by sideAll models

Use Mistral Large 4 with any balance.

Mistral Large 4 is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Create an accountSee pricing

Mistral Large 4 is developed by Mistral AI. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by Mistral AI.