Mistral: Mistral Large 3 2512: AI model
Mistral Large 3 is Mistral's Apache-2.0 flagship. A sparse mixture-of-experts model (41B active of 675B) with a 256K-token context and vision input, reachable from inside Iran through Hormouz.
- Context window:
- 262,144 tokens
- Input:
- $0.5/1M tokens
- Output:
- $1.5/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Mistral Large 3 is Mistral's most capable flagship in this lineup. It uses a sparse mixture-of-experts (MoE) architecture with 41B active parameters out of 675B total, and is released under the Apache 2.0 license. The MoE design lets it reach high capability while activating only a fraction of its weights per token.
It accepts text and image input, offers a 256K-token context window, and supports tool calling. A strong fit for demanding reasoning, multimodal tasks and agentic workflows. It is served through Hormouz behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.
Pricing is usage-based: $0.5 per million input tokens and $1.5 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-large-2512",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Mistral AI |
|---|---|
| Type | Text, Image |
| Context window | 262,144 tokens |
| Pricing | $0.50/M in · $1.50/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-large-2512",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="mistralai/mistral-large-2512",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "mistralai/mistral-large-2512",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Mistral: Mistral Large 3 2512 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Mistral: Mistral Large 3 2512 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Mistral Large 3 cost?
- Billing is usage-based: $0.5 per million input tokens and $1.5 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Mistral Large 3 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Mistral Large 3 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- What is the mixture-of-experts design in Mistral Large 3?
- It activates only a subset of its experts per token. 41B active parameters out of 675B total. So it can reach flagship capability while keeping the per-token compute lower than a dense model of the same total size.
- Does Mistral Large 3 support images and long context?
- Yes. It accepts text and image input and offers a 256K-token context window, so it handles multimodal prompts and long documents, and it supports tool calling for agentic use.
Updated 2026-10-13