DeepSeek 4 Flash API

Q: What is the DeepSeek 4 Flash model ID?

Use deepseek/deepseek-v4-flash as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

A 284B-parameter Mixture-of-Experts model engineered for fast, affordable inference without sacrificing reasoning depth. Thirteen billion parameters active per forward pass. One million tokens of context.

Modalities: TextText
In / Out price: $0.2645/$0.4221per 1M
Context window: 1M tokens
Released: Apr 24, 2026

DeepSeek 4 Flash overview

DeepSeek 4 Flash by DeepSeek

In the 1M-token context setting, V4 Flash achieves only 10% of the single-token FLOPs and 7% of the KV cache size compared with DeepSeek-V3.2, a dramatic efficiency jump that makes serving very long contexts actually economical.

DeepSeek 4 Flash specs

Model ID: deepseek/deepseek-v4-flash
Developer: DeepSeek
Context window: 1,000,000 tokens
Max output: 384,000 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What is DeepSeek V4 Flash?

DeepSeek V4 Flash is the efficiency-first member of DeepSeek's fourth-generation model family, released in preview on April 24, 2026. It sits alongside V4 Pro as a complementary option, where Pro optimizes for maximum intelligence, Flash optimizes for throughput, latency, and cost per token without falling dramatically short on quality.

The model uses a sparse Mixture-of-Experts design: while it carries 284 billion parameters in total, only 13 billion are active during any single inference call. That translates directly into lower compute and lower cost while keeping outputs sharper than a dense 13B model would achieve on its own.

Architecture & key innovations

Several architectural decisions separate V4 Flash from earlier DeepSeek releases and from the broader open-source field.

`Compressed Sparse Attention (CSA)`

Compresses KV caches along the sequence dimension (compression rate 4 in Flash), then applies DeepSeek Sparse Attention. A lightning indexer picks the top 512 most relevant compressed KV entries per query, plus a 128-token sliding window so local context is never missed.

`Heavily Compressed Attention (HCA)`

Applies a much more aggressive compression rate of 128, then performs dense attention over that compressed representation, giving the model a cheap global view of distant tokens in every layer. CSA and HCA layers are interleaved throughout the network.

`Manifold-Constrained Hyper-Connections (mHC)`

Strengthens conventional residual connections to enhance stability of signal propagation across layers while preserving model expressivity, a key factor in maintaining quality at high compression ratios.

`Muon optimizer`

Used during training for faster convergence and greater stability. Alongside FP4/FP8 mixed precision (expert weights in FP4, most other weights in FP8), this keeps training costs low while preserving model quality.

Use cases

Everyday dialogue, content creation, basic RAG applications, and batch text processing are documented as suitable uses for this model.

For everyday dialogue, the documentation says it is designed for high-concurrency, lightweight workloads and is suited to common, essential conversational use cases.

For content creation, the same source explicitly lists content creation among the model’s intended uses.

For basic RAG applications, the documentation names basic retrieval-augmented generation as a suitable use case.

Capabilities

Function calling
Streaming
Structured outputs

DeepSeek 4 Flash benchmarks by Artificial Analysis

See how DeepSeek 4 Flash compares in generation speed and latency. Data retrieved Nov 4, 2026.

Speed#77 / 219130Output tokens / second Latency#117 / 2161.60Seconds to first token Humanity's Last Exam#57 / 45838.6%Score GPQA Diamond#34 / 43990.8%Score

Speed

Output tokens / second

Benchmark results

Compare 7 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

DeepSeek 4 Flash API pricing

DeepSeek 4 Flash pricing in US dollars
Usage	Price	Unit
Input	$0.2645	1M tokens
Output	$0.4221	1M tokens
Cached input	$0.006	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

DeepSeek 4 Flash vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
DeepSeek 4 Flash	$0.2645	$0.4221
DeepSeek Chat (V4.1 Flash)	$0.3	$1.2
DeepSeek V4.1 Flash	$0.3	$1.2
DeepSeek V4 Flash Vision Exp	$0.44	$1.32
DeepSeek V4.1 Flash 1017	$0.39	$1.56

How to use the DeepSeek 4 Flash API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

DeepSeek 4 Flash FAQ

How much does DeepSeek 4 Flash cost?

DeepSeek 4 Flash costs $0.2645 input and $0.4221 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does DeepSeek 4 Flash support streaming?

Yes, DeepSeek 4 Flash can stream responses as they are generated.

Does DeepSeek 4 Flash support tool calling and structured outputs?

Yes, DeepSeek 4 Flash supports both function calling and structured outputs.

Who created DeepSeek 4 Flash?

DeepSeek 4 Flash was built by DeepSeek.

What is the DeepSeek 4 Flash model ID?

Use deepseek/deepseek-v4-flash as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of DeepSeek 4 Flash?

DeepSeek 4 Flash accepts up to 1,000,000 tokens of context and returns up to 384,000 output tokens.

Start building with DeepSeek 4 Flash

Get API key

DeepSeek 4 Flash API

deepseek/deepseek-v4-flash

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

DeepSeek 4 Flash API

DeepSeek 4 Flash overview

DeepSeek 4 Flash by DeepSeek

DeepSeek 4 Flash specs

What is DeepSeek V4 Flash?

Architecture & key innovations

`Compressed Sparse Attention (CSA)`

`Heavily Compressed Attention (HCA)`

`Manifold-Constrained Hyper-Connections (mHC)`

`Muon optimizer`

Use cases

Capabilities

DeepSeek 4 Flash benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

DeepSeek 4 Flash API pricing

DeepSeek 4 Flash vs other models: token prices

How to use the DeepSeek 4 Flash API

Build with your agent

1Get your API key

2Make your first request

DeepSeek 4 Flash FAQ

Start building with DeepSeek 4 Flash

DeepSeek 4 Flash API

Build with your agent

1Get your API key

2Make your first request

DeepSeek 4 Flash API

DeepSeek 4 Flash overview

DeepSeek 4 Flash by DeepSeek

DeepSeek 4 Flash specs

What is DeepSeek V4 Flash?

Architecture & key innovations

Compressed Sparse Attention (CSA)

Heavily Compressed Attention (HCA)

Manifold-Constrained Hyper-Connections (mHC)

Muon optimizer

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

DeepSeek 4 Flash API pricing

DeepSeek 4 Flash vs other models: token prices

How to use the DeepSeek 4 Flash API

Build with your agent

1Get your API key

2Make your first request

Models similar to DeepSeek 4 Flash

DeepSeek Chat (V4.1 Flash)

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash 1017

Seed-2.0-Lite

Gemini 3.1 Flash Lite Preview

Mercury 2

DeepSeek 4 Flash FAQ

Start building with DeepSeek 4 Flash

`Compressed Sparse Attention (CSA)`

`Heavily Compressed Attention (HCA)`

`Manifold-Constrained Hyper-Connections (mHC)`

`Muon optimizer`