GeekRadar / Il banco di confronto
CONFRONTA.
Modelli IA
deepseek

DeepSeek V4 Pro

Modello IA Uscita

Modalità API
Chat*
Finestra di contesto
1.000.000 tokens
Output massimo
384.000 tokens
Pesi aperti
Sì

Capacità e preferenze

Capacità generale · ECI

Stima delle capacità basata su più benchmark. Punti di indice, non una percentuale; gli intervalli mostrano l’incertezza.

DeepSeek V4 Pro 149,1* DeepSeek-V4-Pro · Intervallo 95% 147,2–150,9

Preferenze umane · Arena

Preferenze complessive sul testo da confronti diretti. Non misura accuratezza fattuale o riuscita dei compiti.

DeepSeek V4 Pro 1451,1 DeepSeek-V4-Pro · Intervallo 95% 1447,3–1455,0 · 57,572 voti · 2026-10-28

Prestazioni dei modelli

Punteggio Radar: quattro test, peso uguale. Una sintesi sperimentale di queste prove, non una misura universale di intelligenza.

DeepSeek V4 Pro

Punteggio Radar

Non valutato

3/4 test principali · prove insufficienti

5 risultati di benchmark per questa configurazione

Ragionamento scientifico

GPQA Diamond · 25%

Domande scientifiche di esperti; correzione rigorosa a scelta multipla. Il caso vale il 25%.

DeepSeek V4 Pro 89,6*% Intervallo 95% appross.: 86,2–93,1%

Soluzione di problemi nuovi

Mystery Game Puzzles · 25%

Scelta della mossa migliore in una variante di gioco non divulgata. Una prova circoscritta di ragionamento, non di intelligenza generale.

DeepSeek V4 Pro Non disponibile

Matematica avanzata

FrontierMath Tiers 1-3 · 25%

Problemi matematici privati v2 con strumenti Python. Esclusi versioni precedenti e Tier 4.

DeepSeek V4 Pro 45,3*% Intervallo 95% appross.: 39,5–51,1%

Risposte fattuali

SimpleQA Verified · 25%

Risposte fattuali corrette con invito a tentare, valutate da un modello. Non misura allucinazioni o astensione.

DeepSeek V4 Pro 47,0*% Intervallo 95% appross.: 43,9–50,1%

Matematica da competizione

OTIS Mock AIME 2024-2025 · Risultato separato

Problemi da competizione: risposte estratte da un modello e confrontate con la soluzione esatta. Escluse le procedure di valutazione precedenti.

DeepSeek V4 Pro 96,7*% Intervallo 95% appross.: 92,7–100,0%

Matematica di ricerca

FrontierMath Tier 4 v2 · Risultato separato

I problemi privati più difficili di FrontierMath, versione corretta v2, con strumenti Python. Separati dai Tiers 1-3 del punteggio principale.

DeepSeek V4 Pro 2,4*% Intervallo 95% appross.: 0,0–7,2%

Le barre mostrano i risultati delle prove. I segmenti indicano intervalli approssimativi al 95% quando è disponibile l’errore standard. Budget di ragionamento diversi non implicano costi uguali. I risultati mancanti non valgono zero.

Risultati dei benchmark

  • Punteggio riportato · versione non riportata · intelligence44,30*Piattaforma non riportata Confronta i risultati

Risultati registrati

Ogni riga usa lo stesso benchmark, versione, carico, scenario e unità. I risultati mancanti non valgono zero. I risultati di sistema includono tutta la configurazione hardware e software.

Arena text preference / chinesehuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.481,52 rating

Intervallo di confidenza: 1.470,79 – 1.492,26

3380 voti

Categoria
chinese
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.468,95 rating

Intervallo di confidenza: 1.463,07 – 1.474,84

17146 voti

Categoria
coding
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.446,30 rating

Intervallo di confidenza: 1.439,10 – 1.453,51

9709 voti

Categoria
creative_writing
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.458,97 rating

Intervallo di confidenza: 1.453,88 – 1.464,05

25284 voti

Categoria
english
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.449,77 rating

Intervallo di confidenza: 1.444,73 – 1.454,81

43583 voti

Categoria
exclude_ties
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.462,61 rating

Intervallo di confidenza: 1.454,26 – 1.470,97

5922 voti

Categoria
expert
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.472,61 rating

Intervallo di confidenza: 1.458,21 – 1.487,01

2210 voti

Categoria
french
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.456,74 rating

Intervallo di confidenza: 1.437,50 – 1.475,98

995 voti

Categoria
german
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.460,98 rating

Intervallo di confidenza: 1.456,43 – 1.465,53

38501 voti

Categoria
hard_prompts
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.465,55 rating

Intervallo di confidenza: 1.459,74 – 1.471,36

17844 voti

Categoria
hard_prompts_english
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.443,00 rating

Intervallo di confidenza: 1.436,34 – 1.449,66

11378 voti

Categoria
industry_business_and_management_and_financial_operations
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.430,81 rating

Intervallo di confidenza: 1.424,26 – 1.437,36

12804 voti

Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.464,41 rating

Intervallo di confidenza: 1.454,96 – 1.473,86

4487 voti

Categoria
industry_legal_and_government
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.470,01 rating

Intervallo di confidenza: 1.462,95 – 1.477,07

9171 voti

Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.455,37 rating

Intervallo di confidenza: 1.444,52 – 1.466,22

3293 voti

Categoria
industry_mathematical
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.465,55 rating

Intervallo di confidenza: 1.455,58 – 1.475,52

4060 voti

Categoria
industry_medicine_and_healthcare
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.468,42 rating

Intervallo di confidenza: 1.463,19 – 1.473,66

23647 voti

Categoria
industry_software_and_it_services
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.447,34 rating

Intervallo di confidenza: 1.441,06 – 1.453,62

14120 voti

Categoria
industry_writing_and_literature_and_language
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.445,24 rating

Intervallo di confidenza: 1.439,68 – 1.450,80

20026 voti

Categoria
instruction_following
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.445,40 rating

Intervallo di confidenza: 1.422,08 – 1.468,71

725 voti

Categoria
japanese
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.409,19 rating

Intervallo di confidenza: 1.390,35 – 1.428,02

1107 voti

Categoria
korean
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.457,35 rating

Intervallo di confidenza: 1.452,06 – 1.462,65

25924 voti

Categoria
longer_query
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.442,50 rating

Intervallo di confidenza: 1.431,43 – 1.453,57

3061 voti

Categoria
math
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.467,43 rating

Intervallo di confidenza: 1.460,45 – 1.474,41

10354 voti

Categoria
multi_turn
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.439,01 rating

Intervallo di confidenza: 1.434,31 – 1.443,71

32288 voti

Categoria
non_english
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.451,13 rating

Intervallo di confidenza: 1.447,25 – 1.455,01

57572 voti

Categoria
overall
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.460,75 rating

Intervallo di confidenza: 1.442,90 – 1.478,59

1123 voti

Categoria
polish
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.453,02 rating

Intervallo di confidenza: 1.444,85 – 1.461,19

6314 voti

Categoria
russian
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

DeepSeek V4 Pro

1.455,89 rating

Intervallo di confidenza: 1.440,76 – 1.471,02

1728 voti

Categoria
spanish
Configurazione valutata
DeepSeek-V4-Pro
Tipo di valutazione
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.480,82 rating

Intervallo di confidenza: 1.470,09 – 1.491,55

3389 voti

Categoria
chinese
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.469,32 rating

Intervallo di confidenza: 1.463,43 – 1.475,21

17136 voti

Categoria
coding
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.445,88 rating

Intervallo di confidenza: 1.438,67 – 1.453,09

9726 voti

Categoria
creative_writing
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.459,34 rating

Intervallo di confidenza: 1.454,25 – 1.464,43

25292 voti

Categoria
english
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.449,78 rating

Intervallo di confidenza: 1.444,73 – 1.454,83

43602 voti

Categoria
exclude_ties
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.463,11 rating

Intervallo di confidenza: 1.454,73 – 1.471,48

5913 voti

Categoria
expert
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.472,73 rating

Intervallo di confidenza: 1.458,27 – 1.487,19

2211 voti

Categoria
french
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.458,00 rating

Intervallo di confidenza: 1.438,70 – 1.477,29

997 voti

Categoria
german
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.461,30 rating

Intervallo di confidenza: 1.456,75 – 1.465,86

38511 voti

Categoria
hard_prompts
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.466,05 rating

Intervallo di confidenza: 1.460,23 – 1.471,86

17840 voti

Categoria
hard_prompts_english
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.443,29 rating

Intervallo di confidenza: 1.436,63 – 1.449,95

11386 voti

Categoria
industry_business_and_management_and_financial_operations
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.430,46 rating

Intervallo di confidenza: 1.423,90 – 1.437,01

12801 voti

Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.464,17 rating

Intervallo di confidenza: 1.454,71 – 1.473,63

4494 voti

Categoria
industry_legal_and_government
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.470,11 rating

Intervallo di confidenza: 1.463,04 – 1.477,18

9166 voti

Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.455,16 rating

Intervallo di confidenza: 1.444,29 – 1.466,04

3288 voti

Categoria
industry_mathematical
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.465,51 rating

Intervallo di confidenza: 1.455,54 – 1.475,48

4066 voti

Categoria
industry_medicine_and_healthcare
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.468,95 rating

Intervallo di confidenza: 1.463,71 – 1.474,19

23637 voti

Categoria
industry_software_and_it_services
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.446,96 rating

Intervallo di confidenza: 1.440,68 – 1.453,25

14140 voti

Categoria
industry_writing_and_literature_and_language
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.445,13 rating

Intervallo di confidenza: 1.439,56 – 1.450,70

20027 voti

Categoria
instruction_following
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.445,57 rating

Intervallo di confidenza: 1.422,06 – 1.469,07

722 voti

Categoria
japanese
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.409,13 rating

Intervallo di confidenza: 1.390,28 – 1.427,97

1111 voti

Categoria
korean
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.457,40 rating

Intervallo di confidenza: 1.452,11 – 1.462,70

25932 voti

Categoria
longer_query
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.442,80 rating

Intervallo di confidenza: 1.431,72 – 1.453,87

3063 voti

Categoria
math
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.467,38 rating

Intervallo di confidenza: 1.460,40 – 1.474,36

10357 voti

Categoria
multi_turn
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.438,78 rating

Intervallo di confidenza: 1.434,08 – 1.443,48

32302 voti

Categoria
non_english
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.451,16 rating

Intervallo di confidenza: 1.447,28 – 1.455,04

57594 voti

Categoria
overall
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.461,21 rating

Intervallo di confidenza: 1.443,35 – 1.479,07

1124 voti

Categoria
polish
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.452,46 rating

Intervallo di confidenza: 1.444,29 – 1.460,63

6319 voti

Categoria
russian
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

DeepSeek V4 Pro

1.456,25 rating

Intervallo di confidenza: 1.441,10 – 1.471,40

1731 voti

Categoria
spanish
Configurazione valutata
deepseek-v4-pro
Tipo di valutazione
human preference

Esecuzione locale

Inferenza · stima della memoria

DeepSeek V4 Pro

Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.

Costo API

USD / mese

Stima per token di testo standard. Esclude imposte, cache, sconti batch e costi aggiuntivi per ragionamento e modalità multimediali. Limiti e disponibilità possono variare per provider.

DeepSeek V4 Pro

DeepSeek V4 Pro / Fasce di prezzo 2
Provider / condizioniTariffaValutaImporto / unità
DeepInfradeepseek-ai/DeepSeek-V4-ProStandard Input in cacheUSD0.1 / 1M tokens
InputUSD1.3 / 1M tokens
OutputUSD2.6 / 1M tokens
SiliconFlowdeepseek-ai/DeepSeek-V4-ProStandard Input in cacheCNY1 / 1M tokens
InputCNY12 / 1M tokens
OutputCNY24 / 1M tokens

Capacità

Finestra di contesto
1.000.000 tokens
Input massimo
1.000.000 tokens*
Output massimo
384.000 tokens
Ragionamento
Sì
Uso di strumenti
Sì
Output strutturato
Sì*
Pesi aperti
Sì
Dati di addestramento fino a
2025-05
Modalità API
Chat*
Finestra di contesto dichiarata
1M*
Tipo di modello
LLM (MoE)*
Modalità dichiarate
Text → Text*
Input immagini
No*
Chiamate parallele agli strumenti
Sì*
Cache dei prompt
Sì*
Messaggi di sistema
Sì*
Scelta degli strumenti
Sì*
Licenza del modello
MIT

Modalità di input

  • text

Modalità di output

  • text

Elaborazione e piattaforma

Architettura
deepseek_v4

Configurazione di sistema

Specifiche dettagliate

Specifiche 1 · 17 campi
api providers
DeepSeek, OpenRouter*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
context window
1M*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
developer
DeepSeek*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
input price
0,435*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
intelligence
44,3*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
license
MIT (open)*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
max output
384K*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
min gpu
Multi-GPU server (e.g. 8× H100 80GB)*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
modality
Text → Text*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
model type
LLM (MoE)*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
name
DeepSeek V4-Pro*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
open weights
yes*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
output price
0,87*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
parameters
1.6T total / ~49B active (MoE)*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
release date
2026-04*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
vram q4
~800 GB*
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
vram q4 gb
800* GB
Ambito e condizioni
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Non riportato*
price_tiers
Non riportato*
Specifiche 2 · 44 campi
cache creation input token cost
0,0*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache creation input token cost
0,0*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost
4,4e-8*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost
4,4e-8*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1,32e-6*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1,32e-6*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token cache hit
4,4e-8*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token cache hit
4,4e-8*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
deepseek*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
deepseek*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
1.000.000*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
1.000.000*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
393.216*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
393.216*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
393.216*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
393.216*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
off peak pricing
cache_read_input_token_cost
2,2e-8*
input_cost_per_token
6,6e-7*
output_cost_per_token
1,98e-6*
windows
  • hours_utc
    • 00:00-01:00*
    • 04:00-06:00*
    • 10:00-00:00*
    weekdays
    • 1*
    • 2*
    • 3*
    • 4*
    • 5*
  • hours_utc
    00:00-00:00*
    weekdays
    • 6*
    • 7*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
off peak pricing
cache_read_input_token_cost
2,2e-8*
input_cost_per_token
6,6e-7*
output_cost_per_token
1,98e-6*
windows
  • hours_utc
    • 00:00-01:00*
    • 04:00-06:00*
    • 10:00-00:00*
    weekdays
    • 1*
    • 2*
    • 3*
    • 4*
    • 5*
  • hours_utc
    00:00-00:00*
    weekdays
    • 6*
    • 7*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
3,96e-6*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
3,96e-6*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported endpoints
  • /v1/chat/completions*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported endpoints
  • /v1/chat/completions*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports native streaming
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports native streaming
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports parallel function calling
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports parallel function calling
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports system messages
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports system messages
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Sì*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
No*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
No*
Ambito e condizioni
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-v4-pro*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Dati provvisori