Mistral: Mistral Small 3.2 24B: AI model
Mistral Small 3.2 24B updates Small 3.1 with better instruction following, fewer repetitions and improved function calling, with vision input and a 128K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 256,000 tokens
- Input:
- $0.09/1M tokens
- Output:
- $0.25/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Mistral Small 3.2 24B is an update to Mistral Small 3.1, focused on three practical improvements: following instructions more reliably, repeating itself less, and calling functions more accurately. It keeps the 24B size and multimodal (text + image) input.
Better function calling in particular makes it a stronger choice for tool-using assistants and agents, and the reduced repetition helps in longer generations. It offers a 128K-token context window. 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: $0.1 per million input tokens and $0.3 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...
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-small-3.2-24b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Mistral AI |
|---|---|
| Type | Text, Image |
| Context window | 256,000 tokens |
| Pricing | $0.09/M in · $0.25/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
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-small-3.2-24b-instruct",
"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-small-3.2-24b-instruct",
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-small-3.2-24b-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Mistral: Mistral Small 3.2 24B API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Mistral: Mistral Small 3.2 24B 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 Small 3.2 24B cost?
- Billing is usage-based: $0.1 per million input tokens and $0.3 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Mistral Small 3.2 24B 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 Small 3.2 24B 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 does Mistral Small 3.2 improve over 3.1?
- It follows instructions more reliably, repeats itself less, and calls functions more accurately, while keeping the 24B size and text-plus-image input. The better function calling helps tool-using assistants and agents.
- Does Mistral Small 3.2 24B support function/tool calling?
- Yes, and improved function calling is one of its headline changes over 3.1, so it works well for agents and tool-driven workflows. It also accepts image input alongside text.
Updated 2026-10-13