deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0731

Descrizione della fonte (inglese)

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....

Panoramica

Specifiche del modello

Contesto
1.310.720 tokens
Output massimo
943.718 tokens
Architettura
text->text
Tokenizer
DeepSeek
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.04
per milione di token
Output
$0.64
per milione di token
Lettura cache
$0.016
per milione di token
API

Configurazione del modello

Ragionamento

Ragionamento obbligatorio
No
Parametri predefiniti
high
Capacità e modalità
max, high, low
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-v4-flash-0731","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

InputOutput

Input
text
Output
text
Ragionamento

· max · high · low

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Provider disponibili

29 provider

Verificato: 22 settembre 2026

Provider live su OpenRouter

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

OpenRouter

OpenInference

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.03
Output
$1
Lettura cache
$0.012
Scrittura cache
Non indicato

Relace

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.04
Output
$0.64
Lettura cache
$0.016
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.0528
Output
$0.1584
Lettura cache
$0.00168
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.06
Output
$0.18
Lettura cache
$0.015
Scrittura cache
Non indicato

Inceptron

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.06
Output
$0.3
Lettura cache
$0.04
Scrittura cache
Non indicato

Sail Research

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.0741
Output
$0.342
Lettura cache
$0.0228
Scrittura cache
Non indicato

Reka

fp4
Contesto
262K
Output massimo
131K
Input
$0.088
Output
$0.528
Lettura cache
$0.0056
Scrittura cache
Non indicato

Makora

Non indicato
Contesto
1M
Output massimo
384K
Input
$0.09
Output
$0.195
Lettura cache
$0.0196
Scrittura cache
Non indicato

Wafer

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.1
Output
$0.25
Lettura cache
$0.05
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.119
Output
$0.238
Lettura cache
$0.0238
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.13
Output
$0.26
Lettura cache
$0.028
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.13
Output
$0.26
Lettura cache
$0.028
Scrittura cache
Non indicato

CoreWeave

fp8
Contesto
262K
Output massimo
236K
Input
$0.13
Output
$0.28
Lettura cache
$0.07
Scrittura cache
Non indicato

Nebius

fp8
Contesto
1.0M
Output massimo
922K
Input
$0.14
Output
$0.28
Lettura cache
Non indicato
Scrittura cache
Non indicato

Together

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.14
Output
$0.28
Lettura cache
$0.03
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.14
Output
$0.28
Lettura cache
$0.05
Scrittura cache
Non indicato

Morph

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.142
Output
$0.3996
Lettura cache
$0.0359
Scrittura cache
Non indicato

Venice

Non indicato
Contesto
1M
Output massimo
33K
Input
$0.175
Output
$0.35
Lettura cache
$0.035
Scrittura cache
Non indicato

Mancer 2

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.2
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

Fireworks

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.22
Output
$0.66
Lettura cache
$0.007
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.22
Output
$0.66
Lettura cache
$0.028
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.286
Output
$0.858
Lettura cache
$0.0091
Scrittura cache
Non indicato

NextBit

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.352
Output
$1.056
Lettura cache
$0.012
Scrittura cache
Non indicato

Alibaba

Non indicato
Contesto
1M
Output massimo
393K
Input
$0.352
Output
$1.056
Lettura cache
$0.0352
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.4092
Output
$1.2276
Lettura cache
$0.026
Scrittura cache
Non indicato

Phala

Non indicato
Contesto
1.0M
Output massimo
393K
Input
$0.44
Output
$1.32
Lettura cache
$0.028
Scrittura cache
Non indicato

Baidu

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.44
Output
$1.32
Lettura cache
$0.014
Scrittura cache
Non indicato

AtlasCloud

fp4
Contesto
1.0M
Output massimo
393K
Input
$0.44
Output
$1.32
Lettura cache
$0.028
Scrittura cache
Non indicato

Cloudflare

Non indicato
Contesto
1.3M
Output massimo
1.2M
Input
$0.44
Output
$1.32
Lettura cache
$0.014
Scrittura cache
Non indicato
deepseek

4 modelli

Tutti i modelli