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

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.

Ver fuente en OpenRouter Hugging Face
Resumen

Especificaciones del modelo

Context
1.048.576 tokens
Salida máxima
384.000 tokens
Arquitectura
text->text
Tokenizador
DeepSeek
Corte de conocimiento
Not provided
Moderado
No
Capacidades y modalidades

Input → Output

Input
text
Output
text
Razonamiento

No · max · high · low

API

Parámetros API compatibles

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Proveedores disponibles

16 proveedores

StreamLake

unknown
Context
1.0M
Salida máxima
384K
Input
$1.12
Output
$3.35
Lectura de caché
$0.037
Escritura de caché
Not provided

GMICloud

fp8
Context
1.0M
Salida máxima
944K
Input
$1.12
Output
$3.37
Lectura de caché
$0.037
Escritura de caché
Not provided

Alibaba

unknown
Context
1M
Salida máxima
393K
Input
$1.12
Output
$3.37
Lectura de caché
$0.112
Escritura de caché
Not provided

DeepInfra

fp8
Context
1.0M
Salida máxima
16K
Input
$1.30
Output
$2.60
Lectura de caché
$0.100
Escritura de caché
Not provided

CoreWeave

fp8
Context
1.0M
Salida máxima
944K
Input
$1.31
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

Sail Research

fp4
Context
1.0M
Salida máxima
384K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

DeepSeek

unknown
Context
1.0M
Salida máxima
384K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

Together

unknown
Context
1.0M
Salida máxima
944K
Input
$1.32
Output
$3.96
Lectura de caché
$0.130
Escritura de caché
Not provided

Novita

fp8
Context
1.0M
Salida máxima
393K
Input
$1.32
Output
$3.96
Lectura de caché
$0.132
Escritura de caché
Not provided

Parasail

fp8
Context
1.0M
Salida máxima
944K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

SiliconFlow

fp8
Context
1.0M
Salida máxima
393K
Input
$1.32
Output
$3.96
Lectura de caché
$0.440
Escritura de caché
Not provided

BaseTen

fp4
Context
1.0M
Salida máxima
262K
Input
$1.32
Output
$3.96
Lectura de caché
$0.132
Escritura de caché
Not provided

DigitalOcean

unknown
Context
1.0M
Salida máxima
944K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

Cloudflare

unknown
Context
1.0M
Salida máxima
944K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

Fireworks

unknown
Context
1.0M
Salida máxima
944K
Input
$1.32
Output
$3.96
Lectura de caché
$0.044
Escritura de caché
Not provided

Phala

unknown
Context
1.0M
Salida máxima
393K
Input
$1.45
Output
$4.36
Lectura de caché
$0.150
Escritura de caché
Not provided
deepseek

models

Todos los 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 detalles del modelo →
deepseek logodeepseek

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.

Context
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per 1M tokens
Ver detalles del 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 detalles del 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 detalles del modelo →