DeepSeek V4 Pro 0813

deepseek-v4-pro-0813 by DeepSeek Released August 13, 2026

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

Input from

$0.429 / 1M

Output from

$1.287 / 1M

Cached input from

$0.022 / 1M

Context window

1.05M

Endpoints

from 8 providers

Regions

Monde, Asie, Europe, États-Unis

About DeepSeek V4 Pro 0813

Un modèle linguistique de grande envergure phare de type « Mixture-of-Experts » (MoE), comptant 1,6 billion de paramètres au total et 49 milliards de paramètres activés. Il prend en charge nativement des fenêtres de contexte pouvant atteindre 1 million de tokens. Entraîné sur un vaste ensemble de données de haute qualité, ce modèle offre d'excellentes performances en matière de raisonnement mathématique et logique, de raisonnement complexe, de génération de code professionnel et d'analyse approfondie de documents volumineux. Il est adapté à des scénarios exigeants tels que la recherche scientifique de pointe, les flux de travail d'entreprise complexes et les applications agentiques sophistiquées.

DeepSeek V4 Pro 0813 est un modèle conversationnel développé par DeepSeek, disponible sur Eden AI via 8 endpoints chez 8 fournisseurs, à partir de 0,429 $ par million de tokens en entrée et 1,29 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

8 endpoints from 8 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

QwenOfficial−35%qwen/deepseek-v4-pro-0813

Monde

$0.66$0.429

$1.287

$0.0429

ReasoningToolsJSONCacheVisionWeb

Tencent Cloud (Asie)Official−%tencent/deepseek-v4-pro-0813

Asie

$0.66$0.66

$1.98

$0.022

ReasoningToolsJSONCacheVisionWeb

DeepInfra (États-Unis)Official−%deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813

États-Unis

1.05M

$1.3$1.3

$2.6

$0.1

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-deepseek-v4-pro-0813

Monde

$1.32$1.32

$3.96

$0.132

ReasoningToolsJSONCacheVisionWeb

Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-PRO-0813)Official−%cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813

CF/DEEPSEEK-AI/DEEPSEEK-V4-PRO-0813

1.05M

$1.32$1.32

$3.96

$0.044

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/deepseek-ai/DeepSeek-V4-Pro-0813

Monde

979K

$1.32$1.32

$3.96

$1.32

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/deepseek-ai/DeepSeek-V4-Pro-0813

Monde

1.05M

$1.32$1.32

$3.96

$0.13

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/deepseek/deepseek-v4-pro-0813

Europe

1.05M

$2$2

$0.5

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

1.33 s

TensorX (Europe)

Lowest latency

2.44 s

TensorX (Europe)

Highest throughput

104.7 tok/s

TensorX (Europe)

Best availability

100%

Tencent Cloud (Asie)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Qwen

2.87 s

8.02 s

54.94 s

50.04 tok/s

99.99%

97.85%

1.8%

Tencent Cloud (Asie)

3.56 s

7.54 s

47.75 s

50.13 tok/s

100%

98.17%

DeepInfra (États-Unis)

2.17 s

7.27 s

75.36 s

44.97 tok/s

100%

86.77%

2.85%

Databricks

tok/s

Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-PRO-0813)

tok/s

Nebius

tok/s

Together AI

tok/s

TensorX (Europe)

1.33 s

2.44 s

14.11 s

104.7 tok/s

99.75%

93.44%

1.08%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call DeepSeek V4 Pro 0813 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 Pro 0813

How much does DeepSeek V4 Pro 0813 cost?

On Eden AI, prices for this model start at $0.429 per million input tokens and $1.287 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of DeepSeek V4 Pro 0813?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve DeepSeek V4 Pro 0813?

8 endpoints from 8 providers, available in: Monde, Asie, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run DeepSeek V4 Pro 0813 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 Pro 0813?

Over the last 30 days, the fastest first token was 1.33 s (TensorX (Europe)) and the highest throughput was 104.7 tokens per second (TensorX (Europe)).

About DeepSeek V4 Pro 0813

Providers and prices

Performance

Estimate your monthly cost

Call DeepSeek V4 Pro 0813 with Eden AI

Questions about DeepSeek V4 Pro 0813

More from DeepSeek