DeepSeek V4 Flash
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
GeekRadar / Il banco di confronto
CONFRONTA.
Modelli IADeepSeek V4 Flash
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.
Preferenze umane · Arena
Preferenze complessive sul testo da confronti diretti. Non misura accuratezza fattuale o riuscita dei compiti.
Risultati dei benchmark
- Punteggio riportato · versione non riportata · intelligence40,30*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 Flash
1.463,90 rating
Intervallo di confidenza: 1.452,61 – 1.475,19
3000 voti
- Categoria
- chinese
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.456,40 rating
Intervallo di confidenza: 1.450,23 – 1.462,56
15295 voti
- Categoria
- coding
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.402,59 rating
Intervallo di confidenza: 1.395,11 – 1.410,07
8541 voti
- Categoria
- creative_writing
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.440,78 rating
Intervallo di confidenza: 1.435,52 – 1.446,03
23116 voti
- Categoria
- english
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.424,18 rating
Intervallo di confidenza: 1.418,97 – 1.429,39
39279 voti
- Categoria
- exclude_ties
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.441,29 rating
Intervallo di confidenza: 1.432,65 – 1.449,94
5404 voti
- Categoria
- expert
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.438,46 rating
Intervallo di confidenza: 1.423,64 – 1.453,28
1989 voti
- Categoria
- french
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.417,84 rating
Intervallo di confidenza: 1.396,54 – 1.439,14
838 voti
- Categoria
- german
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.443,47 rating
Intervallo di confidenza: 1.438,74 – 1.448,19
34750 voti
- Categoria
- hard_prompts
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.448,81 rating
Intervallo di confidenza: 1.442,79 – 1.454,83
16217 voti
- Categoria
- hard_prompts_english
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.425,22 rating
Intervallo di confidenza: 1.418,32 – 1.432,12
10434 voti
- Categoria
- industry_business_and_management_and_financial_operations
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.399,42 rating
Intervallo di confidenza: 1.392,56 – 1.406,27
11202 voti
- Categoria
- industry_entertainment_and_sports_and_media
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.438,95 rating
Intervallo di confidenza: 1.429,22 – 1.448,68
4140 voti
- Categoria
- industry_legal_and_government
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.446,70 rating
Intervallo di confidenza: 1.439,38 – 1.454,02
8388 voti
- Categoria
- industry_life_and_physical_and_social_science
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.432,03 rating
Intervallo di confidenza: 1.420,66 – 1.443,39
2980 voti
- Categoria
- industry_mathematical
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.447,64 rating
Intervallo di confidenza: 1.437,25 – 1.458,04
3672 voti
- Categoria
- industry_medicine_and_healthcare
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.452,68 rating
Intervallo di confidenza: 1.447,23 – 1.458,14
21384 voti
- Categoria
- industry_software_and_it_services
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.409,70 rating
Intervallo di confidenza: 1.403,20 – 1.416,20
12571 voti
- Categoria
- industry_writing_and_literature_and_language
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.420,90 rating
Intervallo di confidenza: 1.415,12 – 1.426,68
17943 voti
- Categoria
- instruction_following
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.388,55 rating
Intervallo di confidenza: 1.363,92 – 1.413,19
652 voti
- Categoria
- japanese
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.382,17 rating
Intervallo di confidenza: 1.361,37 – 1.402,96
901 voti
- Categoria
- korean
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.433,95 rating
Intervallo di confidenza: 1.428,43 – 1.439,47
23338 voti
- Categoria
- longer_query
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.425,77 rating
Intervallo di confidenza: 1.414,06 – 1.437,49
2699 voti
- Categoria
- math
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.448,55 rating
Intervallo di confidenza: 1.441,32 – 1.455,79
9339 voti
- Categoria
- multi_turn
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.419,11 rating
Intervallo di confidenza: 1.414,20 – 1.424,01
28827 voti
- Categoria
- non_english
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.431,83 rating
Intervallo di confidenza: 1.427,82 – 1.435,85
51944 voti
- Categoria
- overall
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.435,25 rating
Intervallo di confidenza: 1.416,61 – 1.453,88
1025 voti
- Categoria
- polish
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.426,44 rating
Intervallo di confidenza: 1.417,99 – 1.434,89
5737 voti
- Categoria
- russian
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1.435,71 rating
Intervallo di confidenza: 1.419,78 – 1.451,64
1578 voti
- Categoria
- spanish
- Configurazione valutata
- DeepSeek-V4-Flash
- Tipo di valutazione
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.462,78 rating
Intervallo di confidenza: 1.451,50 – 1.474,06
3009 voti
- Categoria
- chinese
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.456,61 rating
Intervallo di confidenza: 1.450,44 – 1.462,77
15288 voti
- Categoria
- coding
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.403,29 rating
Intervallo di confidenza: 1.395,82 – 1.410,77
8582 voti
- Categoria
- creative_writing
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.440,79 rating
Intervallo di confidenza: 1.435,53 – 1.446,05
23129 voti
- Categoria
- english
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.424,19 rating
Intervallo di confidenza: 1.418,98 – 1.429,41
39317 voti
- Categoria
- exclude_ties
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.441,10 rating
Intervallo di confidenza: 1.432,44 – 1.449,75
5404 voti
- Categoria
- expert
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.439,02 rating
Intervallo di confidenza: 1.424,19 – 1.453,85
2004 voti
- Categoria
- french
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.418,64 rating
Intervallo di confidenza: 1.397,33 – 1.439,95
841 voti
- Categoria
- german
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.443,38 rating
Intervallo di confidenza: 1.438,66 – 1.448,11
34768 voti
- Categoria
- hard_prompts
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.448,92 rating
Intervallo di confidenza: 1.442,91 – 1.454,94
16226 voti
- Categoria
- hard_prompts_english
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.425,02 rating
Intervallo di confidenza: 1.418,12 – 1.431,92
10441 voti
- Categoria
- industry_business_and_management_and_financial_operations
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.399,68 rating
Intervallo di confidenza: 1.392,81 – 1.406,54
11211 voti
- Categoria
- industry_entertainment_and_sports_and_media
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.438,51 rating
Intervallo di confidenza: 1.428,77 – 1.448,24
4148 voti
- Categoria
- industry_legal_and_government
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.446,51 rating
Intervallo di confidenza: 1.439,20 – 1.453,82
8412 voti
- Categoria
- industry_life_and_physical_and_social_science
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.432,35 rating
Intervallo di confidenza: 1.420,96 – 1.443,75
2975 voti
- Categoria
- industry_mathematical
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.448,01 rating
Intervallo di confidenza: 1.437,62 – 1.458,40
3681 voti
- Categoria
- industry_medicine_and_healthcare
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.452,85 rating
Intervallo di confidenza: 1.447,39 – 1.458,31
21378 voti
- Categoria
- industry_software_and_it_services
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.409,87 rating
Intervallo di confidenza: 1.403,37 – 1.416,36
12604 voti
- Categoria
- industry_writing_and_literature_and_language
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.420,81 rating
Intervallo di confidenza: 1.415,03 – 1.426,59
17963 voti
- Categoria
- instruction_following
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.388,93 rating
Intervallo di confidenza: 1.364,22 – 1.413,63
653 voti
- Categoria
- japanese
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.382,29 rating
Intervallo di confidenza: 1.361,46 – 1.403,12
899 voti
- Categoria
- korean
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.433,99 rating
Intervallo di confidenza: 1.428,47 – 1.439,51
23356 voti
- Categoria
- longer_query
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.426,46 rating
Intervallo di confidenza: 1.414,74 – 1.438,18
2697 voti
- Categoria
- math
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.448,48 rating
Intervallo di confidenza: 1.441,24 – 1.455,72
9346 voti
- Categoria
- multi_turn
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.419,15 rating
Intervallo di confidenza: 1.414,25 – 1.424,06
28857 voti
- Categoria
- non_english
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.431,84 rating
Intervallo di confidenza: 1.427,82 – 1.435,86
51987 voti
- Categoria
- overall
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.435,25 rating
Intervallo di confidenza: 1.416,62 – 1.453,88
1027 voti
- Categoria
- polish
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.427,04 rating
Intervallo di confidenza: 1.418,59 – 1.435,49
5745 voti
- Categoria
- russian
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1.435,53 rating
Intervallo di confidenza: 1.419,58 – 1.451,49
1578 voti
- Categoria
- spanish
- Configurazione valutata
- deepseek-v4-flash
- Tipo di valutazione
- human preference
Esecuzione locale
Costo API
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 Flash
DeepSeek V4 Flash / Fasce di prezzo
| Provider / condizioni | Tariffa | Valuta | Importo / unità |
|---|---|---|---|
| DeepInfradeepseek-ai/DeepSeek-V4-FlashStandard | Input in cache | USD | 0.018 / 1M tokens |
| Input | USD | 0.09 / 1M tokens | |
| Output | USD | 0.18 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard 费用发生时段: 0点～2点/8点～24点 | Input in cache | CNY | 0.3 / 1M tokens |
| Input | CNY | 3 / 1M tokens | |
| Output | CNY | 9 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard 费用发生时段: 2点～8点 | Input in cache | CNY | 0.15 / 1M tokens |
| Input | CNY | 1.5 / 1M tokens | |
| Output | CNY | 4.5 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard | Input in cache | CNY | 0.02 / 1M tokens |
| Input | CNY | 1 / 1M tokens | |
| Output | CNY | 2 / 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
- Sì*
- 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
- 0,14*
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
- 40,3*
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
- 2× H100 80GB (4-bit)*
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-Flash*
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
- 0,28*
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
- 284B total / ~13B 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
- ~140 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
- 140* 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-flash*
- 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-flash*
- 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
- 6,0e-9*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 6,0e-9*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 3,0e-7*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 3,0e-7*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 6,0e-9*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 6,0e-9*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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
- 3,0e-9*
- input_cost_per_token
- 1,5e-7*
- output_cost_per_token
- 6,0e-7*
- 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-flash*
- 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
- 3,0e-9*
- input_cost_per_token
- 1,5e-7*
- output_cost_per_token
- 6,0e-7*
- 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-flash*
- 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
- 1,2e-6*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 1,2e-6*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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-flash*
- 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
- Sì*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- Sì*
Ambito e condizioni
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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.*
0 selezionati Confronta 0
* Dati provvisori