DeepSeek V4 Flash 0731

deepseek-v4-flash-0731 by DeepSeek Released July 31, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off

Input from

$0.06 / 1M

Output from

$0.18 / 1M

Cached input from

$0.014 / 1M

Context window

1.05M

Endpoints

from 10 providers

Regions

Monde, Europe, États-Unis

About DeepSeek V4 Flash 0731

Un modèle MoE léger et hautement efficace, comptant au total 284 milliards de paramètres et 13 milliards de paramètres activés, prenant en charge en natif des fenêtres de contexte pouvant atteindre un million de tokens. Il offre une vitesse d’inférence élevée, une faible latence et un coût d’invocation raisonnable, garantissant ainsi des performances globales bien équilibrées. Conçu pour les charges de travail légères à forte concurrence, il est parfaitement adapté aux cas d'utilisation courants et essentiels tels que les dialogues quotidiens, la création de contenu, les applications RAG de base et le traitement de texte par lots.

DeepSeek V4 Flash 0731 est un modèle conversationnel développé par DeepSeek, disponible sur Eden AI via 11 endpoints chez 10 fournisseurs, à partir de 0,06 $ par million de tokens en entrée et 0,18 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

11 endpoints from 10 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 (États-Unis)Official−%deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731

États-Unis

1.05M

$0.06$0.06

$0.18

$0.015

ReasoningToolsJSONCacheVisionWeb

FlexAIOfficial−%flexai/DeepSeek-V4-Flash-0731

Monde

1.05M

$0.119$0.119

$0.238

$0.0178

ReasoningToolsJSONCacheVisionWeb

FlexAI (Europe)Official−%flexai/DeepSeek-V4-Flash-0731@eu

Europe

1.05M

$0.119$0.119

$0.238

$0.0178

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-deepseek-v4-flash-0731

Monde

$0.14$0.14

$0.28

$0.014

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/deepseek-ai/DeepSeek-V4-Flash-0731

Monde

1.02M

$0.14$0.14

$0.28

$0.14

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/deepseek-ai/DeepSeek-V4-Flash-0731

Monde

1.05M

$0.14$0.14

$0.28

$0.03

ReasoningToolsJSONCacheVisionWeb

QwenOfficial−35%qwen/deepseek-v4-flash-0731

Monde

$0.22$0.143

$0.429

$0.0143

ReasoningToolsJSONCacheVisionWeb

GreenPT (Europe)Official−%greenpt/deepseek-v4-flash-0731

Europe

$0.1575$0.1575

$0.3939

$0.045

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/deepseek/deepseek-v4-flash-0731

Europe

1.05M

$0.25$0.25

$0.3

$0.0625

ReasoningToolsJSONCacheVisionWeb

Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-FLASH-0731)Official−%cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731

CF/DEEPSEEK-AI/DEEPSEEK-V4-FLASH-0731

1.05M

$0.44$0.44

$1.32

$0.014

ReasoningToolsJSONCacheVisionWeb

Scaleway (Europe)Official−%scaleway/deepseek-v4-flash-0731

Europe

256K

$0.4501$0.4501

$0.9002

$0.09

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

0.69 s

GreenPT (Europe)

Lowest latency

0.83 s

FlexAI (Europe)

Highest throughput

131.59 tok/s

GreenPT (Europe)

Best availability

100%

FlexAI (Europe)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

DeepInfra (États-Unis)

1.51 s

1.57 s

28.38 s

24.15 tok/s

99.42%

82.58%

7.29%

0.01%

FlexAI

2.56 s

3.26 s

7.03 s

100.05 tok/s

99.89%

93.07%

1.52%

0.39%

FlexAI (Europe)

1.09 s

0.83 s

3.15 s

86.38 tok/s

100%

94.04%

Databricks

1.03 s

5.58 s

34.72 s

101.3 tok/s

99.54%

78.92%

63.28%

42.99%

Nebius

1.43 s

10.63 s

63.63 s

107.83 tok/s

99.86%

72.84%

4.52%

Together AI

0.97 s

6.11 s

59.52 s

63.81 tok/s

96.6%

77.07%

22.42%

0.45%

Qwen

2.98 s

9.4 s

82.6 s

68.04 tok/s

100%

71%

4.31%

2.19%

GreenPT (Europe)

0.69 s

4 s

36.27 s

131.59 tok/s

99.69%

96.36%

0.5%

TensorX (Europe)

1.37 s

6.35 s

33.77 s

67.6 tok/s

99.9%

66.3%

0.25%

0.13%

Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-FLASH-0731)

tok/s

Scaleway (Europe)

1.14 s

8.63 s

156.55 s

81.35 tok/s

98.12%

24.8%

2.63%

4.98%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call DeepSeek V4 Flash 0731 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": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about DeepSeek V4 Flash 0731

How much does DeepSeek V4 Flash 0731 cost?

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. .

What is the context window of DeepSeek V4 Flash 0731?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve DeepSeek V4 Flash 0731?

11 endpoints from 10 providers, available in: Monde, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run DeepSeek V4 Flash 0731 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 0731?

Over the last 30 days, the fastest first token was 0.69 s (GreenPT (Europe)) and the highest throughput was 131.59 tokens per second (GreenPT (Europe)).

About DeepSeek V4 Flash 0731

Providers and prices

Performance

Estimate your monthly cost

Call DeepSeek V4 Flash 0731 with Eden AI

Questions about DeepSeek V4 Flash 0731

More from DeepSeek