Mistral: Mistral Medium 3: AI model
Mistral Medium 3 targets frontier-class reasoning and multimodal ability at lower operating cost, with vision input and a 128K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 131,072 tokens
- Input:
- $0.4/1M tokens
- Output:
- $2/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Mistral Medium 3 is an enterprise-oriented mid-tier model that aims to deliver near-frontier reasoning and multimodal performance while keeping operating cost well below flagship models. It accepts text and image input and offers a 128K-token context window.
That balance makes it a practical default for production assistants and multimodal workloads where you want strong quality without top-tier pricing. It supports tool calling for agentic and structured-output use. 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: $0.4 per million input tokens and $2 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
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-medium-3",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Mistral AI |
|---|---|
| Type | Text, Image |
| Context window | 131,072 tokens |
| Pricing | $0.40/M in · $2.00/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-medium-3",
"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-medium-3",
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-medium-3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Mistral: Mistral Medium 3 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Mistral: Mistral Medium 3 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 Medium 3 cost?
- Billing is usage-based: $0.4 per million input tokens and $2 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Mistral Medium 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 Medium 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.
- Why choose Mistral Medium 3 over a flagship?
- It targets near-frontier reasoning and multimodal quality at a lower operating cost, so it is a good production default when you want strong results without paying flagship prices.
- Does Mistral Medium 3 handle images?
- Yes. It accepts text and image input and offers a 128K-token context window, so it works for multimodal prompts as well as long text, with tool calling for agentic workflows.
Updated 2026-10-13