azureavailablesupports_assistant_prefillsupports_function_callingsupports_prompt_cachingsupports_reasoningsupports_tool_choice

Back to Model Explorer

AzureAvailable on AvalAI

deepseek-v3.2-speciale API on AvalAI

deepseek-v3.2-speciale

deepseek-v3.2-speciale is an AI model from DeepSeek that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$0.28 / 1M tokens

Output price$0.42 / 1M tokens

Context window163,840 tokens

Maximum output163,840 tokens

Use deepseek-v3.2-speciale with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "deepseek-v3.2-speciale", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="deepseek-v3.2-speciale",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v3.2-speciale",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• Assistant prefill
• Function calling
• Prompt caching
• Reasoning
• Tool choice

deepseek-v3.2-speciale rate limits

Tier	RPM	TPM
Basic	3	40,000
Tier 1	250	500,000
Tier 2	500	1,000,000
Tier 3	1,500	2,000,000
Tier 4	2,500	3,000,000
Tier 5	3,500	5,000,000

Related models

• DeepSeek V3.2
• deepseek-v3.1
• DeepSeek V4 Pro 0423
• DeepSeek V4 Flash 0423

Frequently asked questions

What is the deepseek-v3.2-speciale API on AvalAI?

Create an AvalAI API key and send the model ID deepseek-v3.2-speciale to one of the supported endpoints shown on this page.

How much does the deepseek-v3.2-speciale API cost on AvalAI?

The deepseek-v3.2-speciale API on AvalAI costs $0.28 per 1M input tokens and $0.42 per 1M output tokens.

What is the token cost for deepseek-v3.2-speciale?

Current AvalAI pricing for deepseek-v3.2-speciale is $0.28 / 1M tokens for input and $0.42 / 1M tokens for output.

What is the deepseek-v3.2-speciale context window?

The recorded maximum input context for deepseek-v3.2-speciale is 163,840 tokens.

What are the rate limits for deepseek-v3.2-speciale on AvalAI?

On tier 5, deepseek-v3.2-speciale on AvalAI supports up to 3,500 requests per minute and 5,000,000 tokens per minute.

What features does deepseek-v3.2-speciale support on AvalAI?

deepseek-v3.2-speciale on AvalAI supports Assistant prefill, Function calling, Prompt caching, Reasoning, Tool choice.

What account tier is required to use deepseek-v3.2-speciale on AvalAI?

Calling deepseek-v3.2-speciale on AvalAI requires the Basic tier (tier 0) or higher.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)