DeepSeek V4 Flash | Cost-Efficient 284B MoE LLM API

Name: DeepSeek V4 Flash API
Brand: deepseek
Price: 0.17 USD
Availability: InStock

Uso da API

Use os exemplos de código abaixo para integrar com nossa 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-v4-flash",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Introdução do modelo

Deepseek deepseek-v4-flash

DeepSeek-V4-Flash is DeepSeek's cost-efficient open-source model, released on April 24, 2026. It is a 284B parameter Mixture-of-Experts (MoE) language model with only 13B active parameters, pre-trained on 32T tokens, supporting a context length of one million tokens. V4-Flash delivers reasoning performance approaching V4-Pro while being significantly faster and cheaper — making it ideal for high-volume, latency-sensitive workloads.

Why It Looks Great

Mixture-of-Experts architecture with 284B total parameters and only 13B active — the smallest activation among Tier-1 models
1000000 context window powered by Compressed Sparse Attention (CSA) and DeepSeek Sparse Attention (DSA)
Near V4-Pro reasoning performance at a fraction of the cost

Key Features

Context Window: 1000000 tokens
Max Output: 384000 tokens
Vision: Not Supported
Function Calling: Supported
Thinking Mode: Supported (non-thinking / high / max)
JSON Output: Supported
FIM Completion: Supported (non-thinking mode only)

Benchmarks

Benchmark	V4-Flash	V4-Pro	Claude Opus 4.6	GPT-5.4
SWE-bench Verified	79.0	80.6	80.8	—
LiveCodeBench	91.6	93.5	88.8	91.7
Codeforces Rating	3052	3206	—	3168
MMLU-Pro	86.2	87.5	89.1	87.5
Terminal Bench 2.0	56.9	67.9	65.4	75.1

Specifications

Specification	Value
Provider	Deepseek
Model Type	Large Language Model (LLM)
Architecture	Mixture-of-Experts (MoE)
Total Parameters	284B (13B active)
Context Window	1000000 tokens
Max Output	384000 tokens
Input	Text
Output	Text
Vision	Not Supported
Function Calling	Supported
Thinking Mode	Supported (high / max)
Release Date	April 24, 2026

How to Use

Write your prompt — describe the task, provide context, and specify desired output format.
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-v4-flash

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-v4-flash",
    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-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: deepseek/deepseek-v4-flash
Provider: Deepseek
Open-source weights available on HuggingFace and ModelScope
Supports both OpenAI and Anthropic API formats
For simple Agent tasks, V4-Flash performs on par with V4-Pro; for complex agentic workflows, consider V4-Pro

DeepSeek V4 Flash API

deepseek/deepseek-v4-flash

DeepSeek V4 Flash is DeepSeek's efficiency-first open-source model released in April 2026, built on a 284B-parameter Mixture-of-Experts architecture with just 13B parameters active per token — the smallest activation footprint among current Tier-1 models. It shares the same 1M-token context window and hybrid attention design as V4 Pro, delivering near-equivalent reasoning capability (LiveCodeBench 91.6, Codeforces 3052, SWE-bench Verified 79.0) while running significantly faster and at dramatically lower cost. Pre-trained on 32T tokens, V4 Flash is purpose-built for high-throughput, latency-sensitive scenarios such as coding assistants, conversational agents, and batch processing pipelines. It supports thinking and non-thinking modes, function calling, JSON output, and FIM completion.

Perguntas frequentes sobre DeepSeek V4 Flash

Quanto custa DeepSeek V4 Flash via API?+

Preços no WaveSpeedAI: $0.17 por milhão de tokens de entrada e $0.34 por milhão de tokens de saída. Prompt caching e batch processing são cobrados separadamente e reduzem o custo efetivo em cargas longas e repetitivas.

Qual é a janela de contexto do DeepSeek V4 Flash?+

DeepSeek V4 Flash suporta até 1049K tokens de contexto e até 384K tokens de saída por requisição.

DeepSeek V4 Flash é compatível com OpenAI?+

Sim. O WaveSpeedAI expõe o DeepSeek V4 Flash através de um endpoint compatível com OpenAI em https://llm.wavespeed.ai/v1. Aponte o SDK oficial da OpenAI para esta base URL com sua chave API do WaveSpeedAI — sem outras alterações no código.

Como começo a usar o DeepSeek V4 Flash?+

Entre no WaveSpeedAI, crie uma chave API em Access Keys, então envie uma requisição para https://llm.wavespeed.ai/v1/chat/completions com o model id mostrado acima. Contas novas recebem créditos grátis para avaliar o DeepSeek V4 Flash.

Preços