AI TOOLS RADAR
Explorar
Todos os modelos / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4 Pro 0813 (batch)

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Ver fonte no OpenRouter Hugging Face
Visão geral

Especificações do modelo

Context
1.048.576 tokens
Saída máxima
943.718 tokens
Arquitetura
text->text
Tokenizador
DeepSeek
Limite de conhecimento
Not provided
Moderado
Não
Recursos e modalidades

Input → Output

Input
text
Output
text
Raciocínio

Não · max · high · low

API

Parâmetros de API compatíveis

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Provedores disponíveis

16 provedores

StreamLake

unknown
Context
1.0M
Saída máxima
384K
Input
$1.12
Output
$3.35
Leitura de cache
$0.037
Gravação de cache
Not provided

GMICloud

fp8
Context
1.0M
Saída máxima
944K
Input
$1.12
Output
$3.37
Leitura de cache
$0.037
Gravação de cache
Not provided

Alibaba

unknown
Context
1M
Saída máxima
393K
Input
$1.12
Output
$3.37
Leitura de cache
$0.112
Gravação de cache
Not provided

DeepInfra

fp8
Context
1.0M
Saída máxima
16K
Input
$1.30
Output
$2.60
Leitura de cache
$0.100
Gravação de cache
Not provided

CoreWeave

fp8
Context
1.0M
Saída máxima
944K
Input
$1.31
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

Sail Research

fp4
Context
1.0M
Saída máxima
384K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

DeepSeek

unknown
Context
1.0M
Saída máxima
384K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

Together

unknown
Context
1.0M
Saída máxima
944K
Input
$1.32
Output
$3.96
Leitura de cache
$0.130
Gravação de cache
Not provided

Novita

fp8
Context
1.0M
Saída máxima
393K
Input
$1.32
Output
$3.96
Leitura de cache
$0.132
Gravação de cache
Not provided

Parasail

fp8
Context
1.0M
Saída máxima
944K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

SiliconFlow

fp8
Context
1.0M
Saída máxima
393K
Input
$1.32
Output
$3.96
Leitura de cache
$0.440
Gravação de cache
Not provided

BaseTen

fp4
Context
1.0M
Saída máxima
262K
Input
$1.32
Output
$3.96
Leitura de cache
$0.132
Gravação de cache
Not provided

DigitalOcean

unknown
Context
1.0M
Saída máxima
944K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

Cloudflare

unknown
Context
1.0M
Saída máxima
944K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

Fireworks

unknown
Context
1.0M
Saída máxima
944K
Input
$1.32
Output
$3.96
Leitura de cache
$0.044
Gravação de cache
Not provided

Phala

unknown
Context
1.0M
Saída máxima
393K
Input
$1.45
Output
$4.36
Leitura de cache
$0.150
Gravação de cache
Not provided
deepseek

models

Todos os modelos
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Context
1.0M
Input
text · image
Output
text
Input: $0.440Output: $1.32per 1M tokens
Ver detalhes do modelo →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per 1M tokens
Ver detalhes do modelo →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Context
1.3M
Input
text
Output
text
Input: $0.065Output: $0.180per 1M tokens
Ver detalhes do modelo →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash 0731 (batch)

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Context
1.0M
Input
text
Output
text
Input: $0.140Output: $0.280per 1M tokens
Ver detalhes do modelo →