Mistral Large 4 API
Mistral's 1.05T-parameter mixture-of-experts flagship (49B active), text and image in, served from the EU. Public preview at half the list price.
Model spec
- Input
- $0.68per 1M tokens
- Output
- $2.09per 1M tokens
- Cached input
- $0.07per 1M tokens
- Context
- 524K
Model ID
OpenAI-compatible · api.companyfabric.com/v1
Overview
About Mistral Large 4
Mistral Large 4 is Mistral's new flagship, released as a public API preview on 6 October 2026: a granular mixture-of-experts model with 1.05 trillion parameters, 49 billion active per token, and a 1.6B vision encoder, so it reads images as well as text. Mistral trained it in Europe and serves it from the EU. It is announced as open weights, but the weights are not out yet; Mistral says end of October, after a red-teaming window. Until then it is API-only. Mistral positions it for coding and agents, cybersecurity, finance and legal work, and visual grounding. During the preview it costs $0.68 input and $2.09 output per million tokens, half its $1.36 / $4.18 list price, on the same CompanyFabric key and balance as every other model. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope, one integration covers the entire library.
Facts
At a glance
Availability
Preview
Added 6 Oct 2026
Pricing
$0.68 in · $2.09 out
Per 1M tokens, metered exactly per call
Context window
524K tokens
Commercial use
See license
Announced as open weights; the weights and their licence are not published yet (Mistral says end of October 2026), so it is API-only for now. Commercial output use per Mistral's terms.
Variants
All endpoints
Quickstart
How to use the Mistral Large 4 API
- 1
Create a free CompanyFabric account, starter credits are included, no card required.
- 2
Copy your API key from the dashboard. One key covers every model in the library.
- 3
Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "mistral/mistral-large-4".
- 4
Read the exact metered cost of the call from the response, the same number shown in the playground.
Use cases
What teams build with it
Agents & copilots
Drive agent loops, tool calls, and user-facing assistants over the OpenAI-compatible endpoint.
agentstool useassistants
Content pipelines
Summarization, rewriting, and structured generation at metered per-token cost.
contentsummarization
Extraction & classification
Turn unstructured input into typed JSON with schema-constrained output.
extractionjson mode
Get better output
Prompting tips
- State the output format before the task, models follow contracts declared early.
- Few-shot beats description: two worked examples outperform a paragraph of rules.
- Cap output length explicitly when cost matters; output tokens dominate most bills.
Exact, metered, prepaid
Mistral Large 4 pricing
Mistral Large 4 pricing is per token: $0.68 / M input · $2.09 / M output · $0.07 / M cached input. Output tokens cost 3.1× input tokens, so long generations, not long prompts, are what actually drive most bills. A typical call with a 2k-token prompt and a 1k-token answer costs about $0.0035.
Every call is metered exactly and attributed to your key, the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap, and bring your own provider key (BYOK) at 0% platform fee if you already have a direct contract.
| Endpoint | Type | Price |
|---|---|---|
| Mistral Large 4 | Chat | $0.68 / M input · $2.09 / M output · $0.07 / M cached input |
Starter credits
Use Mistral Large 4 free
Your CompanyFabric starter credits cover your first Mistral Large 4 calls at no cost, create a free account, no card required, and the credits apply to Mistral Large 4 and every other model on the key. When they run out, prepaid credits or BYOK (0% fee) take over with no plan to pick.
Production-grade
Code samples
import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://api.companyfabric.com/v1",
apiKey: process.env.COMPANYFABRIC_API_KEY,
})
const res = await client.chat.completions.create({
model: "mistral/mistral-large-4",
max_tokens: 1024,
temperature: 0.7,
messages: [{ role: "user", content: "Say hello from the fabric." }],
})
console.log(res.choices[0].message.content)Playground
Try it in the browser
Comparisons
Mistral Large 4 vs the alternatives
Mistral Large 4 vs Mistral Medium 3.5
Mistral Large 4 and Mistral Medium 3.5 compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: Mistral Large 4 vs Mistral Medium 3.5 →Mistral Large 4 vs GPT-6 Sol
Mistral Large 4 and GPT-6 Sol compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: Mistral Large 4 vs GPT-6 Sol →Mistral Large 4 vs DeepSeek V4 Pro
Mistral Large 4 and DeepSeek V4 Pro compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: Mistral Large 4 vs DeepSeek V4 Pro →Compare
Mistral Large 4 head to head
FAQ
Frequently asked questions
How do I get a Mistral Large 4 API key?
Create a CompanyFabric account, and one key unlocks Mistral Large 4 and every other model in the library. Free starter credits are included, no subscription, no card required to try it.
Why use Mistral Large 4 on CompanyFabric instead of going direct?
One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.
Is the API OpenAI-compatible?
Yes, point any OpenAI SDK at api.companyfabric.com/v1 and set model to "mistral/mistral-large-4".
Can I use the output commercially?
Announced as open weights; the weights and their licence are not published yet (Mistral says end of October 2026), so it is API-only for now. Commercial output use per Mistral's terms.
How does billing work?
Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.
How much does the Mistral Large 4 API cost?
During the public preview, $0.68 per million input tokens, $0.07 per million cached input tokens and $2.09 per million output tokens. That is half Mistral's list price of $1.36 / $0.14 / $4.18, and Mistral has not said when the discount ends. CompanyFabric bills the rate Mistral charges at the time and updates it the day it changes.
Can I download the Mistral Large 4 weights?
Not yet. Mistral says the weights land at the end of October 2026, and the licence is not published. Today it is available only through the API.
What is Mistral Large 4's context window?
Mistral's documentation says 1M tokens. The serving limit reported by OpenRouter and Artificial Analysis is 524,288 tokens, so CompanyFabric lists 524,288 until a live request confirms more.
Is Mistral Large 4 used by companyfabric/auto?
Not today. companyfabric/auto and companyfabric/cheap pick the cheapest model that can serve the request, and companyfabric/best the highest-priced one; Mistral Large 4 is neither. Call it by name: mistral/mistral-large-4.
Provider
About Mistral
Mistral publishes the mistral-large family. License: Announced as open weights; the weights and their licence are not published yet (Mistral says end of October 2026), so it is API-only for now. Commercial output use per Mistral's terms.
One key. Every model. Exact prices.
Run Mistral Large 4 with free starter credits. Free starter credits included, no subscription required.