deepseek/deepseek-v4-flash
Yayın tarihi: 2026-04-24
1,048,576 context · $0.17/M input tokens · $0.34/M output tokens
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.
Kullandıkça öde
Ön ödeme yok, yalnızca kullandığınız kadar ödeyin
API'mizle entegre etmek için aşağıdaki kod örneklerini kullanın:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'deepseek/deepseek-v4-flash',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'deepseek/deepseek-v4-flash',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}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.
| 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 |
| 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 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: deepseek/deepseek-v4-flash
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 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!"}]
}'
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.
Giriş
$0.17 /M
Çıkış
$0.34 /M
Bağlam
1049K
Maks. Çıkış
384K
Araç Kullanımı
Destekleniyor
Birleşik API'miz aracılığıyla DeepSeek V4 Flash'e erişin — OpenAI uyumlu, soğuk başlatma yok, şeffaf fiyatlandırma.
WaveSpeedAI fiyatlandırması: milyon giriş tokenı başına $0.17 ve milyon çıkış tokenı başına $0.34. Prompt caching ve toplu işleme ayrı faturalanır ve uzun, tekrar eden yüklerde etkin maliyeti düşürür.
DeepSeek V4 Flash istek başına 1049K bağlam tokenını ve 384K çıkış tokenını destekler.
WaveSpeedAI, DeepSeek V4 Flash modelini https://llm.wavespeed.ai/v1 adresindeki OpenAI uyumlu Chat Completions arayüzü üzerinden sunar. Çoğu OpenAI SDK istemcisinde base URL ve API anahtarını değiştirmek yeterlidir; isteğe bağlı alanlar modele bağlıdır.
WaveSpeedAI’a giriş yapın, Access Keys bölümünde bir API anahtarı oluşturun ve yukarıdaki model id ile https://llm.wavespeed.ai/v1/chat/completions adresine istek gönderin. Güncel kullanılabilirlik, özellikler ve fiyatlar için model kataloğunu kontrol edin.