Seedance 2.0 | Special Offer ✦ 10% OFF NOW
deepseek
deepseek/deepseek-v3.2

deepseek/deepseek-v3.2

163,840 context · $0.26/M input tokens · $0.38/M output tokens

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Prezzi

Pay-per-use

Nessun costo iniziale, paga solo per ciò che usi

Input$0.26 / M Tokens
Output$0.38 / M Tokens

Utilizzo API

Usa i seguenti esempi di codice per integrare la nostra API:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v3.2",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Introduzione al modello

Deepseek deepseek-v3.2

deepseek deepseek-v3.2


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 163840 context window for long document handling
  • Competitive pricing at $0.3/$0.4 per million tokens

Key Features

  • Context Window: 163840 tokens
  • Max Output: 65536 tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderDeepseek
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window163840 tokens
Max Output65536 tokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$0.3
Output$0.4

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: deepseek/deepseek-v3.2


API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v3.2",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek/deepseek-v3.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: deepseek/deepseek-v3.2
  • Provider: Deepseek

Info

Providerdeepseek
Tipollm

Funzionalità supportate

Input
Testo
Output
Testo
Contesto163,840
Output massimo65,536
Vision-
Function Calling✓ Supportato

Guida all'accesso API

Base URLhttps://llm.wavespeed.ai/v1
API Endpointchat/completions
ID modellodeepseek/deepseek-v3.2

DeepSeek V3.2 API

deepseek/deepseek-v3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Input

$0.26 /M

Output

$0.38 /M

Contesto

164K

Output max

66K

Uso strumenti

Supportato

Prova DeepSeek V3.2 su WaveSpeedAI

Accedi a DeepSeek V3.2 tramite la nostra API unificata — compatibile con OpenAI, senza cold start, prezzi trasparenti.

Apri Playground

Domande frequenti su DeepSeek V3.2

Quanto costa DeepSeek V3.2 via API?+

Prezzi su WaveSpeedAI: $0.26 per milione di token in input e $0.38 per milione di token in output. Prompt caching e batch processing sono fatturati separatamente e riducono il costo effettivo su carichi lunghi e ripetitivi.

Qual è la context window di DeepSeek V3.2?+

DeepSeek V3.2 supporta fino a 164K token di contesto e fino a 66K token di output per richiesta.

DeepSeek V3.2 è compatibile con OpenAI?+

Sì. WaveSpeedAI espone DeepSeek V3.2 tramite un endpoint compatibile con OpenAI all'indirizzo https://llm.wavespeed.ai/v1. Punta l'SDK ufficiale di OpenAI a questa base URL con la tua API key WaveSpeedAI — senza altre modifiche al codice.

Come si inizia con DeepSeek V3.2?+

Accedi a WaveSpeedAI, crea una API key in Access Keys, poi invia una richiesta a https://llm.wavespeed.ai/v1/chat/completions con il model id mostrato sopra. I nuovi account ricevono crediti gratuiti per testare DeepSeek V3.2.

API LLM correlate