deepseek/deepseek-v4-flash
प्रकाशन तिथि: 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.
Pricing
Pay-per-use
No upfront costs, pay only for what you use
Try the model
API Usage
Use the following code examples to integrate with our API:
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["WAVESPEED_API_KEY"],
base_url="https://llm.wavespeed.ai/v1",
timeout=120.0,
max_retries=2,
)
try:
response = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content or "")
except Exception as exc:
raise SystemExit(f"LLM request failed: {exc}") from excModel Introduction
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
Info
Supported Functionality
API Access Guide
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.
Input
$0.17 /M
Output
$0.34 /M
Context
1049K
Max Output
384K
Tool Use
Supported
Try DeepSeek V4 Flash on WaveSpeedAI
Access DeepSeek V4 Flash through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Frequently Asked Questions about DeepSeek V4 Flash
How much does DeepSeek V4 Flash cost via the API?+
Pricing on WaveSpeedAI: $0.17 per million input tokens and $0.34 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
What is the context window of DeepSeek V4 Flash?+
DeepSeek V4 Flash supports up to 1049K tokens of context with up to 384K tokens of output per request.
Is DeepSeek V4 Flash OpenAI-compatible?+
WaveSpeedAI exposes DeepSeek V4 Flash at https://llm.wavespeed.ai/v1 through the OpenAI-compatible Chat Completions interface. Most OpenAI SDK clients work by changing the base URL and API key; optional fields depend on the selected model.
How do I get started with DeepSeek V4 Flash?+
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with the model id shown above. Check the current model catalog for availability, capabilities, and pricing.