AI TOOLS RADAR
Esplora
Tutti i modelli / 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.

Vedi la fonte su OpenRouter Hugging Face
Panoramica

Specifiche del modello

Context
1.048.576 tokens
Output massimo
943.718 tokens
Architettura
text->text
Tokenizer
DeepSeek
Limite di conoscenza
Not provided
Moderato
No
Capacità e modalità

Input → Output

Input
text
Output
text
Ragionamento

No · max · high · low

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Provider disponibili

16 provider

StreamLake

unknown
Context
1.0M
Output massimo
384K
Input
$1.12
Output
$3.35
Lettura cache
$0.037
Scrittura cache
Not provided

GMICloud

fp8
Context
1.0M
Output massimo
944K
Input
$1.12
Output
$3.37
Lettura cache
$0.037
Scrittura cache
Not provided

Alibaba

unknown
Context
1M
Output massimo
393K
Input
$1.12
Output
$3.37
Lettura cache
$0.112
Scrittura cache
Not provided

DeepInfra

fp8
Context
1.0M
Output massimo
16K
Input
$1.30
Output
$2.60
Lettura cache
$0.100
Scrittura cache
Not provided

CoreWeave

fp8
Context
1.0M
Output massimo
944K
Input
$1.31
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

Sail Research

fp4
Context
1.0M
Output massimo
384K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

DeepSeek

unknown
Context
1.0M
Output massimo
384K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

Together

unknown
Context
1.0M
Output massimo
944K
Input
$1.32
Output
$3.96
Lettura cache
$0.130
Scrittura cache
Not provided

Novita

fp8
Context
1.0M
Output massimo
393K
Input
$1.32
Output
$3.96
Lettura cache
$0.132
Scrittura cache
Not provided

Parasail

fp8
Context
1.0M
Output massimo
944K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

SiliconFlow

fp8
Context
1.0M
Output massimo
393K
Input
$1.32
Output
$3.96
Lettura cache
$0.440
Scrittura cache
Not provided

BaseTen

fp4
Context
1.0M
Output massimo
262K
Input
$1.32
Output
$3.96
Lettura cache
$0.132
Scrittura cache
Not provided

DigitalOcean

unknown
Context
1.0M
Output massimo
944K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

Cloudflare

unknown
Context
1.0M
Output massimo
944K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

Fireworks

unknown
Context
1.0M
Output massimo
944K
Input
$1.32
Output
$3.96
Lettura cache
$0.044
Scrittura cache
Not provided

Phala

unknown
Context
1.0M
Output massimo
393K
Input
$1.45
Output
$4.36
Lettura cache
$0.150
Scrittura cache
Not provided
deepseek

models

Tutti i modelli
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
Vedi i dettagli del modello →
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
Vedi i dettagli del modello →
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
Vedi i dettagli del modello →
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
Vedi i dettagli del modello →