deepseek logo
deepseek

DeepSeek: DeepSeek V3

Descrizione della fonte (inglese)

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Panoramica

Specifiche del modello

Contesto
163.840 tokens
Output massimo
16.000 tokens
Architettura
text->text
Tokenizer
DeepSeek
Limite di conoscenza
2024-07-31
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.2574
per milione di token
Output
$1.0287
per milione di token
API

Avvio rapido

Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.

Documentazione API

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

Input → Output

Input
text
Output
text
API

Parametri API supportati

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Provider disponibili

3 provider

Verificato: 20 ottobre 2026

Provider live su OpenRouter

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

OpenRouter

DeepInfra

fp4
Contesto
164K
Output massimo
147K
Input
$0.256
Output
$0.712
Lettura cache
Non indicato
Scrittura cache
Non indicato

StreamLake

Non indicato
Contesto
128K
Output massimo
16K
Input
$0.2574
Output
$1.0287
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

fp4
Contesto
164K
Output massimo
16K
Input
$0.32
Output
$0.89
Lettura cache
Non indicato
Scrittura cache
Non indicato
deepseek

4 modelli

Tutti i modelli
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.15Output: $0.6per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.02Output: $1per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash (batch)

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.05Output: $0.15per milione di token
Vedi i dettagli del modello →
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: $0.2156Output: $0.6468per milione di token
Vedi i dettagli del modello →