GeekRadar / Il banco di confronto
CONFRONTA.
Modelli IA
anthropic

Claude Sonnet 5.5

Modello IA Uscita

Modalità API
Chat*
Finestra di contesto
1.000.000 tokens
Output massimo
128.000 tokens
Pesi aperti
No

Capacità e preferenze

Capacità generale · ECI

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

Claude Sonnet 5.5 166,7* Claude Sonnet 5.5 · Intervallo 95% 163,6–171,3

Preferenze umane · Arena

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

Claude Sonnet 5.5 1472,9 Claude Sonnet 5.5 (xHigh) · Intervallo 95% 1466,1–1479,6 · 10,033 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.

Claude Sonnet 5.5

Punteggio Radar

74,0* / 100

4/4 test principali · v1 sperimentale

9 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%.

Claude Sonnet 5.5 95,6*% Intervallo 95% appross.: 92,9–98,3%

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.

Claude Sonnet 5.5 65,0*% Intervallo 95% appross.: 55,6–74,4%

Matematica avanzata

FrontierMath Tiers 1-3 · 25%

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

Claude Sonnet 5.5 88,8*% Intervallo 95% appross.: 85,1–92,4%

Risposte fattuali

SimpleQA Verified · 25%

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

Claude Sonnet 5.5 46,5*% Intervallo 95% appross.: 43,4–49,6%

Software completo

MirrorCode · Risultato separato

Reimplementazione di programmi con test nascosti; ML + Private, due linguaggi. Budget: sette giorni e dieci miliardi di token per tentativo.

Claude Sonnet 5.5 97,8*% Intervallo 95% appross.: 94,8–100,0%

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.

Claude Sonnet 5.5 100,0*% Incertezza non disponibile

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.

Claude Sonnet 5.5 80,5*% Intervallo 95% appross.: 68,2–92,8%

Ragionamento visivo e spaziale

Furniture Assembly · Risultato separato

Rilevamento di errori di montaggio da foto e manuali, con zoom e Python. Valutazione assistita da un modello; non misura tutta la comprensione visiva.

Claude Sonnet 5.5 75,0*% Intervallo 95% appross.: 64,2–85,8%

Uso del computer su compiti lunghi

SpireClimb · Risultato separato

Media a peso uguale delle vittorie in due giochi Slay the Spire tramite schermate e controlli. Versioni fisse; non è un tasso di riuscita generale sul desktop.

Claude Sonnet 5.5 1,3*% Intervallo 95% appross.: 0,0–3,2%

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 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

Claude Sonnet 5.5

1.537,45 rating

Intervallo di confidenza: 1.516,67 – 1.558,23

859 voti

Categoria
chinese
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.511,91 rating

Intervallo di confidenza: 1.499,19 – 1.524,64

2339 voti

Categoria
coding
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.470,37 rating

Intervallo di confidenza: 1.456,76 – 1.483,98

2278 voti

Categoria
creative_writing
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.483,81 rating

Intervallo di confidenza: 1.473,48 – 1.494,13

3741 voti

Categoria
english
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.479,65 rating

Intervallo di confidenza: 1.470,58 – 1.488,71

7356 voti

Categoria
exclude_ties
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.527,21 rating

Intervallo di confidenza: 1.508,75 – 1.545,67

1024 voti

Categoria
expert
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.497,67 rating

Intervallo di confidenza: 1.468,41 – 1.526,94

407 voti

Categoria
french
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.425,03 rating

Intervallo di confidenza: 1.384,63 – 1.465,43

178 voti

Categoria
german
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.493,76 rating

Intervallo di confidenza: 1.485,48 – 1.502,05

6168 voti

Categoria
hard_prompts
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.501,45 rating

Intervallo di confidenza: 1.488,73 – 1.514,16

2356 voti

Categoria
hard_prompts_english
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.466,28 rating

Intervallo di confidenza: 1.451,42 – 1.481,15

1666 voti

Categoria
industry_business_and_management_and_financial_operations
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.459,50 rating

Intervallo di confidenza: 1.446,93 – 1.472,07

2615 voti

Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.484,77 rating

Intervallo di confidenza: 1.463,75 – 1.505,79

822 voti

Categoria
industry_legal_and_government
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.486,97 rating

Intervallo di confidenza: 1.472,04 – 1.501,90

1704 voti

Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.513,33 rating

Intervallo di confidenza: 1.488,20 – 1.538,47

536 voti

Categoria
industry_mathematical
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.476,11 rating

Intervallo di confidenza: 1.453,41 – 1.498,81

703 voti

Categoria
industry_medicine_and_healthcare
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.504,26 rating

Intervallo di confidenza: 1.493,64 – 1.514,88

3416 voti

Categoria
industry_software_and_it_services
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.474,30 rating

Intervallo di confidenza: 1.462,29 – 1.486,31

2855 voti

Categoria
industry_writing_and_literature_and_language
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.491,84 rating

Intervallo di confidenza: 1.481,07 – 1.502,61

3357 voti

Categoria
instruction_following
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.456,70 rating

Intervallo di confidenza: 1.416,92 – 1.496,48

205 voti

Categoria
japanese
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.494,45 rating

Intervallo di confidenza: 1.484,40 – 1.504,49

4212 voti

Categoria
longer_query
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.503,89 rating

Intervallo di confidenza: 1.477,82 – 1.529,96

497 voti

Categoria
math
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.468,11 rating

Intervallo di confidenza: 1.452,09 – 1.484,14

1445 voti

Categoria
multi_turn
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.456,10 rating

Intervallo di confidenza: 1.447,91 – 1.464,28

6288 voti

Categoria
non_english
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.472,85 rating

Intervallo di confidenza: 1.466,09 – 1.479,61

10033 voti

Categoria
overall
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.460,95 rating

Intervallo di confidenza: 1.444,43 – 1.477,47

1400 voti

Categoria
russian
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1.447,36 rating

Intervallo di confidenza: 1.417,35 – 1.477,37

359 voti

Categoria
spanish
Configurazione valutata
Claude Sonnet 5.5 (xHigh)
Tipo di valutazione
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.536,90 rating

Intervallo di confidenza: 1.511,44 – 1.562,36

553 voti

Categoria
chinese
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.513,04 rating

Intervallo di confidenza: 1.498,12 – 1.527,96

1627 voti

Categoria
coding
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.466,86 rating

Intervallo di confidenza: 1.450,79 – 1.482,93

1532 voti

Categoria
creative_writing
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.484,53 rating

Intervallo di confidenza: 1.472,52 – 1.496,53

2578 voti

Categoria
english
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.475,90 rating

Intervallo di confidenza: 1.465,46 – 1.486,34

4998 voti

Categoria
exclude_ties
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.532,22 rating

Intervallo di confidenza: 1.510,16 – 1.554,28

700 voti

Categoria
expert
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.496,87 rating

Intervallo di confidenza: 1.460,94 – 1.532,79

259 voti

Categoria
french
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.492,54 rating

Intervallo di confidenza: 1.483,01 – 1.502,07

4222 voti

Categoria
hard_prompts
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.502,72 rating

Intervallo di confidenza: 1.487,71 – 1.517,73

1606 voti

Categoria
hard_prompts_english
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.459,96 rating

Intervallo di confidenza: 1.442,74 – 1.477,18

1177 voti

Categoria
industry_business_and_management_and_financial_operations
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.457,59 rating

Intervallo di confidenza: 1.442,80 – 1.472,38

1741 voti

Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.484,96 rating

Intervallo di confidenza: 1.460,75 – 1.509,18

591 voti

Categoria
industry_legal_and_government
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.478,58 rating

Intervallo di confidenza: 1.461,03 – 1.496,12

1187 voti

Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.506,28 rating

Intervallo di confidenza: 1.475,85 – 1.536,70

362 voti

Categoria
industry_mathematical
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.455,77 rating

Intervallo di confidenza: 1.428,69 – 1.482,85

468 voti

Categoria
industry_medicine_and_healthcare
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.501,29 rating

Intervallo di confidenza: 1.488,83 – 1.513,75

2359 voti

Categoria
industry_software_and_it_services
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.472,04 rating

Intervallo di confidenza: 1.457,82 – 1.486,25

1902 voti

Categoria
industry_writing_and_literature_and_language
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.488,49 rating

Intervallo di confidenza: 1.475,91 – 1.501,07

2303 voti

Categoria
instruction_following
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.493,73 rating

Intervallo di confidenza: 1.482,02 – 1.505,43

2882 voti

Categoria
longer_query
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.498,64 rating

Intervallo di confidenza: 1.467,33 – 1.529,95

345 voti

Categoria
math
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.462,88 rating

Intervallo di confidenza: 1.444,22 – 1.481,53

1008 voti

Categoria
multi_turn
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.454,15 rating

Intervallo di confidenza: 1.444,67 – 1.463,64

4250 voti

Categoria
non_english
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.470,38 rating

Intervallo di confidenza: 1.462,66 – 1.478,10

6831 voti

Categoria
overall
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.445,16 rating

Intervallo di confidenza: 1.426,08 – 1.464,24

955 voti

Categoria
russian
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Claude Sonnet 5.5

1.450,18 rating

Intervallo di confidenza: 1.413,90 – 1.486,46

244 voti

Categoria
spanish
Configurazione valutata
claude-sonnet-5.5-xhigh
Tipo di valutazione
human preference

Esecuzione locale

Inferenza · stima della memoria

Claude Sonnet 5.5

Pesi chiusi. Non sono pubblicati un impiego locale supportato o requisiti GPU.

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.

Claude Sonnet 5.5

Claude Sonnet 5.5 / Fasce di prezzo 3
Provider / condizioniTariffaValutaImporto / unità
AnthropicClaude Sonnet 5.5Batch InputUSD1 / 1M tokens
OutputUSD5 / 1M tokens
AnthropicClaude Sonnet 5.5Standard Input in cacheUSD0.1 / 1M tokens
InputUSD2 / 1M tokens
OutputUSD10 / 1M tokens
AWS BedrockClaude Sonnet 5.5Standard Global cross-region Input in cacheUSD0.1 / 1M tokens
InputUSD2 / 1M tokens
OutputUSD10 / 1M tokens

Capacità

Finestra di contesto
1.000.000 tokens
Input massimo
1.000.000 tokens*
Output massimo
128.000 tokens
Ragionamento
Sì
Uso di strumenti
Sì
Output strutturato
Sì*
Pesi aperti
No
Dati di addestramento fino a
2026-06
Modalità API
Chat*
Input immagini
Sì*
Input PDF
Sì*
Cache dei prompt
Sì*
Scelta degli strumenti
Sì*
Ricerca sul web
Sì*
Licenza del modello
Proprietary

Modalità di input

  • text
  • image
  • pdf

Modalità di output

  • text

Configurazione di sistema

Specifiche dettagliate

Specifiche · 73 campi
bedrock converse supports strict tools
No*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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.*
bedrock output config effort ceiling
xhigh*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
2,5e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
2,5e-6*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 above 1hr
4,0e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 above 1hr
4,0e-6*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 batches
1,25e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
1,0e-7*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
1,0e-7*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 batches
5,0e-8*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
2,0e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
2,0e-6*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 batches
1,0e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
128.000*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
128.000*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
128.000*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
128.000*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
1,0e-5*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
1,0e-5*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 batches
5,0e-6*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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.*
prompt cache min tokens
512*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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.*
prompt cache min tokens
512*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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.*
provider specific entry
us
1,1*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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.*
search context cost per query
search_context_size_high
0,01*
search_context_size_low
0,01*
search_context_size_medium
0,01*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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.*
search context cost per query
search_context_size_high
0,01*
search_context_size_low
0,01*
search_context_size_medium
0,01*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 adaptive thinking
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 adaptive thinking
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 anthropic compaction
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
No*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
No*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 bedrock native structured output
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 computer use
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 computer use
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 forced tool use
No*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 forced tool use
No*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 max reasoning effort
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 max reasoning effort
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 mid conversation system
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 mid conversation system
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 structured output
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 structured output
No*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 output config
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 output config
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 tool use config
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 pdf input
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 pdf input
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 sampling params
No*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 sampling params
No*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 search
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 web search
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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 xhigh reasoning effort
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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 xhigh reasoning effort
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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.*
thinking always on
Sì*
Ambito e condizioni
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-sonnet-5-5*
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.*
thinking always on
Sì*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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.*
token count model
model
anthropic.claude-opus-5-5*
litellm_provider
bedrock_mantle*
region
us-east-1*
Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-sonnet-5-5*
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