Skip to main content

DeepSeek model on ScaleMax

DeepSeek V3.2 API

Call DeepSeek V3.2 with the model ID deepseek-v3.2 through ScaleMax's OpenAI-compatible API. It costs $0.20 per million input tokens and $0.60 per million output tokens, prepaid, with no subscription.

Lowest price · Text only · 200K context

Get an API keySee the code
Model ID
deepseek-v3.2
Maker
DeepSeek
Input / 1M tokens
$0.20
Output / 1M tokens
$0.60
Context window
200,000 tokens
Max output
131,072 tokens

DeepSeek V3.2 pricing

ScaleMax publishes one customer rate per model and deducts each completed request from your prepaid balance at that rate: $0.20 per 1M input tokens and $0.60 per 1M output tokens for DeepSeek V3.2.

What typical requests cost at the standard rate (token counts are illustrative sizes):

RequestSizeCost per requestPer $25 of credit
Chat reply2,000 tokens in, 600 out$0.00076about 32,894 requests
Coding-agent step40,000 tokens in (files + history), 2,000 out$0.0092about 2,717 requests

The Starter credit pack costs $2.50 and adds $25 of usage credit (larger packs add more per dollar — see how pricing works). Prompt-cache reads, where the model supports caching, can bill below the input rate.

Pay by UPI, PayU or Cashfree (UPI, cards, net banking), Cryptomus (crypto) or PayPal. Prices on this page are in US dollars; India checkout shows rupees. See what ₹1,000 buys for token packs.

How to call DeepSeek V3.2

Create a key in the dashboard, export it as SCALEMAX_API_KEY, and send deepseek-v3.2 as the model. OpenAI-compatible clients use the base URL https://api.scalemax.pro/v1. Token pack keys use /token/v1 instead of /v1.

curl · Chat Completions
curl https://api.scalemax.pro/v1/chat/completions \
  -H "Authorization: Bearer $SCALEMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "Explain this error in one line."}],
    "max_tokens": 300
  }'
Python · OpenAI SDK
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalemax.pro/v1",
    api_key=os.environ["SCALEMAX_API_KEY"],
)

reply = client.chat.completions.create(
    model="deepseek-v3.2",
    messages=[{"role": "user", "content": "Explain this error in one line."}],
    max_tokens=300,
)
print(reply.choices[0].message.content)

Keep the key server-side. Call GET /v1/models with your key to see every model it can use; the quick start covers errors and streaming.

Capabilities and limits

  • Context window: 200,000 tokens (200K-token).
  • Maximum output: 131,072 tokens per response.
  • Supports: Tool / function calling.
  • Streaming: server-sent events on every route.

Works in

Any OpenAI-compatible client: Cursor, Cline, Roo Code, Kilo Code, OpenCode, Continue, Aider, Zed and Hermes Agent, with the model ID above. Setup steps for each are on the integrations page.

Other DeepSeek models

ModelModel IDInput / 1MOutput / 1MContext
DeepSeek V3.2deepseek-v3.2$0.20$0.60200,000
DeepSeek V4 Flashdeepseek-v4-flash$0.19$0.511,000,000
DeepSeek V4.1 Flashdeepseek-v4.1-flash$0.30$1.201,000,000
DeepSeek V4 Prodeepseek-v4-pro$1$41,000,000

Lower-cost alternatives

Models from other makers with a lower output rate. Quality differs by task — test on your own prompts before switching.

ModelModel IDInput / 1MOutput / 1MContext
GPT-6 Lunagpt-6-luna$0.10$0.501,050,000
MiMo V2.5 Promimo-v2.5-pro$0.14$0.281,048,576

All models, with their IDs and rates, are on the model list.

DeepSeek V3.2 API questions

What is the API model ID for DeepSeek V3.2?

Use deepseek-v3.2. Send it as the "model" field to https://api.scalemax.pro/v1/chat/completions.

How much does the DeepSeek V3.2 API cost?

$0.20 per 1M input tokens and $0.60 per 1M output tokens at the published ScaleMax rate. A Pay as you go key is prepaid: each completed request is deducted from your credit.

What is the context window of DeepSeek V3.2?

200,000 tokens, with up to 131,072 output tokens per response.

Can I use DeepSeek V3.2 in Cursor, Cline or Roo Code?

Yes. Add ScaleMax as an OpenAI-compatible provider with the base URL https://api.scalemax.pro/v1 and the model ID deepseek-v3.2. Your key must include this model.

Can I pay for DeepSeek V3.2 from India in rupees?

Yes. ScaleMax is prepaid and checkout accepts UPI, cards and net banking in INR, as well as crypto. There is no subscription.

Use DeepSeek V3.2 in your tools

Start calling DeepSeek V3.2

Get a prepaid key, copy the model ID, and send your first request in a couple of minutes.

Get an API keyStart the free trial