~deepseek V4 Flash Latest

~deepseek-v4-flash-latest by DeepSeek Released July 31, 2026
Reasoning · Function calling · Structured output · Prompt caching · EU hosting · Up to 35% off
Input from
$0.06 / 1M
Output from
$0.18 / 1M
Cached input from
$0.014 / 1M
Context window
1.05M
Endpoints
10
from 9 providers
Regions
Global, Europe, United States

About ~deepseek V4 Flash Latest

A highly efficient, lightweight MoE model with 284 billion parameters in total and 13 billion activated parameters, natively supporting context windows of up to one million tokens. It offers fast inference speed, low latency, and cost-effective invocation, delivering well-balanced overall performance. Designed for high-concurrency, lightweight workloads, it is ideally suited for common, essential use cases such as everyday dialogue, content creation, basic RAG applications, and batch text processing.

~deepseek V4 Flash Latest is a chat model by DeepSeek, available on Eden AI through 10 endpoints from 9 providers, from $0.06 per million input tokens and $0.18 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

10 endpoints from 9 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
DeepInfra (United States)deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731
United States
1.05M
$0.06
$0.18
$0.015
Reasoning · Tools · JSON · Cache
FlexAIflexai/DeepSeek-V4-Flash-0731
Global
1.05M
$0.13
$0.26
$0.0195
Reasoning · Tools · JSON · Cache
FlexAI (Europe)flexai/DeepSeek-V4-Flash-0731@eu
Europe
1.05M
$0.13
$0.26
$0.0195
Reasoning · Tools · JSON · Cache
Qwenqwen/deepseek-v4-flash-0731
Global
1M
$0.22$0.143
$0.429
$0.0143
−35% · Reasoning · Tools · JSON · Cache
GreenPT (Europe)greenpt/deepseek-v4-flash-0731
Europe
1M
$0.1538
$0.3846
$0.044
Reasoning · Tools · JSON · Cache
Arkane Cloudarkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731
Global
1.05M
$0.2
$0.4
$0.05
Tools · Cache
TensorX (Europe)tensorx/deepseek/deepseek-v4-flash-0731
Europe
1.05M
$0.25
$0.3
$0.0625
Reasoning · Tools · Cache
sference (Europe)sference/deepseek-ai/DeepSeek-V4-Flash-0731
Europe
1.05M
$0.28
$0.56
$0.07
Reasoning · Tools · JSON · Cache
Scaleway (Europe)scaleway/deepseek-v4-flash-0731
Europe
256K
$0.4396
$0.8791
$0.0879
Reasoning · Tools · Cache
Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-FLASH-0731)cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731
CF/DEEPSEEK-AI/DEEPSEEK-V4-FLASH-0731
1.05M
$0.44
$1.32
$0.014
Reasoning · Tools · JSON · Cache

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.74 s
sference (Europe)
Lowest latency
2.5 s
FlexAI (Europe)
Highest throughput
184.23 tok/s
sference (Europe)
Best availability
99.99%
Qwen
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
DeepInfra (United States)
1.59 s
4 s
18.12 s
54.11 tok/s
99.97%
79.55%
4.59%
0.51%
FlexAI
1.51 s
2.82 s
15.29 s
112.76 tok/s
99.73%
96.13%
1.21%
0.3%
FlexAI (Europe)
1.39 s
2.5 s
24.58 s
110.53 tok/s
99.55%
97.04%
0.19%
0%
Qwen
3.78 s
11.28 s
78.77 s
59.79 tok/s
99.99%
90.29%
17.46%
0%
GreenPT (Europe)
0.93 s
5.57 s
77.34 s
85.08 tok/s
99.68%
90.93%
0.17%
0%
Arkane Cloud
1.11 s
7.63 s
45.08 s
61.22 tok/s
99.45%
72.97%
1.21%
0%
TensorX (Europe)
1.5 s
8.21 s
89.76 s
76.26 tok/s
99.77%
72.29%
0.97%
0.62%
sference (Europe)
0.74 s
4.14 s
17.75 s
184.23 tok/s
99.98%
90.26%
0.37%
0%
Scaleway (Europe)
2.15 s
6 s
51.9 s
87.08 tok/s
99.92%
19.44%
35.28%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~deepseek V4 Flash Latest with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "~deepseek-v4-flash-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~deepseek V4 Flash Latest

On Eden AI, prices for this model start at $0.06 per million input tokens and $0.18 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

10 endpoints from 9 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~deepseek V4 Flash Latest in the EU? Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU. ‖ How fast is ~deepseek V4 Flash Latest? Over the last 30 days, the fastest first token was 0.74 s (sference (Europe)) and the highest throughput was 184.23 tokens per second (sference (Europe)).