Official 0813 Pro release with major gains across coding, repository work, tool use, and agent tasks, plus hybrid thinking and a 1M context window.
DeepSeekGeração de Texto1M contextoLançado 13 de ago. de 2026SingaporeEndpoint proprietárioNovoOfficial 0813 Pro release with major gains across coding, repository work, tool use, and agent tasks, plus hybrid thinking and a 1M context window.
Supports text input, hybrid thinking with enable_thinking and thinking_budget, function calling, strict JSON Schema output, and optional Linkup web search. Thinking tokens are billed as output tokens.
Também conhecido como DeepSeek Pro 0813, DeepSeek 0813
deepseek-v4-pro-0813/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/deepseek-v4-pro-0813:generateContentdeepseek/deepseek-v4-pro-0813deepseek-ai/deepseek-v4-pro-0813Tarifas pay-as-you-go ao vivo do catálogo EmpirioLabs. Você paga só pelo que usa, sem mínimo mensal.
DeepSeek V4 Pro 0813 atende a API Chat Completions compatível com OpenAI. Aponte qualquer SDK OpenAI para https://api.empiriolabs.ai/v1 com sua chave de API EmpirioLabs e use o id de modelo deepseek-v4-pro-0813. Obtenha uma chave de API no painel EmpirioLabs.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="deepseek-v4-pro-0813",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Parâmetros de requisição suportados pela API DeepSeek V4 Pro 0813 na EmpirioLabs. Os padrões valem quando um campo é omitido.
| Parâmetro | Tipo | Padrão | Intervalo / valores | Descrição |
|---|---|---|---|---|
| temperature | number | 0.7 | 0 a 2 | Sampling temperature. 0 = deterministic, 2 = maximum randomness. |
| top_p | number | 0.9 | 0 a 1 | Nucleus sampling probability mass. Lower = more focused. |
| max_tokens | number | 4096 | 1 a 393216 | Maximum output tokens. |
| stop | string | - | - | Up to 4 strings where the model will stop generating further tokens. |
| enable_thinking | boolean | true | - | Enable step-by-step reasoning before answering. |
| thinking_budget | number | 32768 | 1 a 393216 | Maximum tokens reserved for the reasoning process. Up to 393216. |
| reasoning_effort | enum | medium | none, low, medium, high, max | Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. Sent as an OpenAI-style... |
| response_format | enum | - | - | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide. |
| web_search_linkup | boolean | false | - | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default. |
| disable_formatting | boolean | false | - | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another... |
Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked.
Na EmpirioLabs, DeepSeek V4 Pro 0813 é cobrado por uso: Input $1.32 per 1M prompt tokens; Output $3.96 per 1M generated tokens; Web Search (Linkup) $0.013 per call when invoked. A tabela de tarifas ao vivo desta página sempre corresponde ao que a API cobra.
DeepSeek V4 Pro 0813 suporta uma janela de contexto de 1M tokens com até 393.216 tokens de saída por resposta.
Sim. DeepSeek V4 Pro 0813 atende a API Chat Completions compatível com OpenAI, então SDKs OpenAI existentes funcionam apontando base_url para https://api.empiriolabs.ai/v1 e definindo o id de modelo deepseek-v4-pro-0813.
Sim. O playground da EmpirioLabs executa DeepSeek V4 Pro 0813 no navegador com os mesmos parâmetros que a API expõe, para você testar prompts antes de escrever código.
Crie uma conta EmpirioLabs e gere uma chave em API Keys no painel. A cobrança usa créditos pay-as-you-go, então você paga apenas pelas requisições que faz.
Confira nossos preços ou entre em contato se quiser que seu próprio modelo seja implementado em nossa pilha.
