DeepSeek V4.1 Flash

deepseek-v4.1-flash by DeepSeek Released September 13, 2026
Reasoning · Function calling · Structured output · Prompt caching · Image input · EU hosting · Up to 35% off
Input from
$0.0975 / 1M
Output from
$0.39 / 1M
Cached input from
$0.002 / 1M
Context window
1.05M
Endpoints
16
from 12 providers
Regions
Global, Asia, Europe, United States

About DeepSeek V4.1 Flash

This model always redirects to the latest model in the DeepSeek Flash family.

DeepSeek V4.1 Flash is a chat model by DeepSeek, available on Eden AI through 16 endpoints from 12 providers, from $0.098 per million input tokens and $0.39 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

16 endpoints from 12 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
Qwenqwen/deepseek-v4.1-flash
Global
1M
$0.15$0.0975
$0.39
$0.002
−35% · Reasoning · Tools · JSON · Cache · Vision
DeepSeek (Asia)deepseek/deepseek-flash
Asia
1M
$0.15
$0.6
$0.003
Official · Reasoning · Tools · JSON · Cache · Vision
DeepSeek (Asia)deepseek/deepseek-v4-flash
Asia
1M
$0.15
$0.6
$0.003
Official · Reasoning · Tools · JSON · Cache · Vision
DeepSeek (Asia)deepseek/deepseek-v4-flash-vision-exp
Asia
1M
$0.15
$0.6
$0.003
Official · Reasoning · Tools · JSON · Cache · Vision
Tencent Cloud (Asia)tencent/deepseek-v4.1-flash
Asia
1M
$0.15
$0.6
$0.003
Reasoning · Tools · JSON · Cache · Vision
DeepInfra (United States)deepinfra/deepseek-ai/DeepSeek-V4.1-Flash
United States
1.05M
$0.2
$0.6
$0.006
Reasoning · Tools · JSON · Cache · Vision
GreenPT (Europe)greenpt/deepseek-v4.1-flash
Europe
1M
$0.2438
$1.2189
$0.0122
Reasoning · Tools · Cache · Vision
Databricksdatabricks/databricks-deepseek-v4-1-flash
Global
1M
$0.3
$1.2
$0.03
Reasoning · Tools · Cache · Vision
Fireworks AI (United States)fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash
United States
1.05M
$0.3
$1.2
$0.006
Reasoning · Tools · JSON · Cache · Vision
Together AItogether_ai/deepseek-ai/DeepSeek-V4.1-Flash
Global
1.05M
$0.3
$1.2
$0.006
Reasoning · Tools · JSON · Cache · Vision
Google Cloudvertex/deepseek-ai/deepseek-v4.1-flash-maas
Global
$0.3
$1.2
$0.03
Arkane Cloudarkanecloud/deepseek-ai/DeepSeek-V4.1-Flash
Global
1.05M
$0.3
$1.2
$0.075
Reasoning · Tools · Cache · Vision
Google Cloud (Europe)vertex/deepseek-ai/deepseek-v4.1-flash-maas@eu
Europe
$0.33
$1.32
$0.033
Google Cloud (United States)vertex/deepseek-ai/deepseek-v4.1-flash-maas@us
United States
$0.33
$1.32
$0.033
TensorX (Europe)tensorx/deepseek/deepseek-v4.1-flash
Europe
1.05M
$0.5
$1.5
$0.125
Reasoning · Tools · Cache · Vision
Scaleway (Europe)scaleway/deepseek-v4.1-flash
Europe
256K
$0.669
$2.007
$0.1338
Reasoning · Tools · Cache · Vision

Performance

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

Fastest first token
0.52 s
Together AI
Lowest latency
1.54 s
TensorX (Europe)
Highest throughput
239.36 tok/s
Together AI
Best availability
100%
Tencent Cloud (Asia)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
2.71 s
5.81 s
29.74 s
82.41 tok/s
99.97%
94.42%
0.11%
27.38%
DeepSeek (Asia)
1.77 s
4.93 s
31.57 s
85.79 tok/s
99.7%
98.69%
0.9%
18.12%
DeepSeek (Asia)
0.75 s
2.51 s
13.81 s
86.76 tok/s
99.85%
97.47%
0.24%
2.39%
DeepSeek (Asia)
0.71 s
3.09 s
35.54 s
97.13 tok/s
99.92%
97.05%
0.49%
51.22%
Tencent Cloud (Asia)
2.78 s
7.44 s
72.16 s
75.47 tok/s
100%
98.55%
0.4%
0%
DeepInfra (United States)
1.96 s
4.58 s
27.77 s
78.8 tok/s
99.81%
96.89%
0.44%
0%
GreenPT (Europe)
0.76 s
3.25 s
30.98 s
128.87 tok/s
99.39%
94.11%
0.67%
12.21%
Databricks
1.95 s
4.53 s
13.91 s
153.36 tok/s
99.92%
45.73%
1.8%
0.07%
Fireworks AI (United States)
1.28 s
3.51 s
22.53 s
107.24 tok/s
99.92%
97.36%
0.12%
0%
Together AI
0.52 s
2.34 s
16.58 s
239.36 tok/s
99.78%
85.45%
5.34%
0.71%
Google Cloud
2.18 s
4.77 s
46.99 s
66.92 tok/s
99.28%
51.26%
4.32%
0.32%
Arkane Cloud
1.33 s
3.06 s
14.4 s
141.28 tok/s
99.98%
96.2%
1.24%
0%
Google Cloud (Europe)
2.19 s
4.74 s
45.75 s
69.57 tok/s
99.29%
49.62%
4.52%
0.32%
TensorX (Europe)
1.51 s
1.54 s
11.02 s
55.6 tok/s
99.8%
81.63%
0.64%
0%
Scaleway (Europe)
1.32 s
6.12 s
32.76 s
120.11 tok/s
99.64%
55.99%
20.95%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call DeepSeek V4.1 Flash 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-v4.1-flash",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about DeepSeek V4.1 Flash

On Eden AI, prices for this model start at $0.0975 per million input tokens and $0.39 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

16 endpoints from 12 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run DeepSeek V4.1 Flash 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 V4.1 Flash? Over the last 30 days, the fastest first token was 0.52 s (Together AI) and the highest throughput was 239.36 tokens per second (Together AI).