AI TOOLS RADAR
Esplora
Tutti i modelli / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. $0.27 per million input tokens, $0.41 per million output tokens. 163,840 token context window, maximum output of 65,536 tokens. Higher uptime with 3 providers. Includes independent benchmarks from Artificial Analysis.

Vedi la fonte su OpenRouter Hugging Face
Panoramica

Specifiche del modello

Contesto
163.840 tokens
Output massimo
65.536 tokens
Architettura
text->text
Tokenizer
DeepSeek
Limite di conoscenza
2025-07-31
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.27
/M tokens
Output
$0.41
/M tokens
API

Configurazione del modello

Parametri predefiniti

temperature
0.6
top_p
0.95

Ragionamento

Moderato
No
Parametri predefiniti
No
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v3.2-exp","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
text
Output
text
Ragionamento

No

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provider disponibili

3 provider

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

Novita

fp8
Contesto
164K
Output massimo
66K
Input
$0.270
Output
$0.410
Lettura cache
Non indicato
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
164K
Output massimo
147K
Input
$0.270
Output
$0.410
Lettura cache
Non indicato
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
164K
Output massimo
147K
Input
$0.270
Output
$0.410
Lettura cache
$0.270
Scrittura cache
Non indicato
deepseek

modelli

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,...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.440Output: $1.32per milione di token
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.

Contesto
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per milione di token
Vedi i dettagli del modello →
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.

Contesto
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per milione di token
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....

Contesto
1.3M
Input
text
Output
text
Input: $0.065Output: $0.180per milione di token
Vedi i dettagli del modello →