AI TOOLS RADAR
Esplora
Tutti i modelli / ANTHROPIC
anthropic logo
anthropic

Anthropic: Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. $1 per million input tokens, $5 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.

Vedi la fonte su OpenRouter
Panoramica

Specifiche del modello

Contesto
200.000 tokens
Output massimo
64.000 tokens
Architettura
text+image+file->text
Tokenizer
Claude
Limite di conoscenza
Non indicato
Moderato
Sì
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$1
/M tokens
Output
$5
/M tokens
Lettura cache
$0.1
/M tokens
Scrittura cache
$1.25
/M tokens
Cache Write (1h)
$2
/M tokens
Ricerca web
$10
/1K calls
API

Configurazione del modello

Ragionamento

Moderato
No
Parametri predefiniti
No
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-haiku-4.5","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
textimagefile
Output
text
Ragionamento

No

API

Parametri API supportati

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Provider disponibili

8 provider

Provider live su OpenRouter

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

OpenRouter

Anthropic

unknown
Contesto
200K
Output massimo
64K
Input
$1.00
Output
$5.00
Lettura cache
$0.100
Scrittura cache
$1.25

Google

unknown
Contesto
200K
Output massimo
64K
Input
$1.00
Output
$5.00
Lettura cache
$0.100
Scrittura cache
$1.25

Azure

unknown
Contesto
200K
Output massimo
64K
Input
$1.00
Output
$5.00
Lettura cache
$0.100
Scrittura cache
$1.25

Amazon Bedrock

unknown
Contesto
200K
Output massimo
64K
Input
$1.00
Output
$5.00
Lettura cache
$0.100
Scrittura cache
$1.25

Amazon Bedrock

unknown
Contesto
200K
Output massimo
64K
Input
$1.10
Output
$5.50
Lettura cache
$0.110
Scrittura cache
$1.38

Amazon Bedrock

unknown
Contesto
200K
Output massimo
64K
Input
$1.10
Output
$5.50
Lettura cache
$0.110
Scrittura cache
$1.38

Google

unknown
Contesto
200K
Output massimo
64K
Input
$1.10
Output
$5.50
Lettura cache
$0.110
Scrittura cache
$1.38

Google

unknown
Contesto
200K
Output massimo
64K
Input
$1.10
Output
$5.50
Lettura cache
$0.110
Scrittura cache
$1.38
anthropic

modelli

Tutti i modelli
anthropic logoanthropic

Claude Opus 5 (Fast)

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Contesto
1M
Input
text · image · file
Output
text
Input: $10.00Output: $50.00per milione di token
Vedi i dettagli del modello →
anthropic logoanthropic

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

Contesto
1M
Input
text · image · file
Output
text
Input: $5.00Output: $25.00per milione di token
Vedi i dettagli del modello →
anthropic logoanthropic

Claude Opus 5 (batch)

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

Contesto
1M
Input
text · image · file
Output
text
Input: $2.50Output: $12.50per milione di token
Vedi i dettagli del modello →
anthropic logoanthropic

Anthropic: Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

Contesto
1M
Input
text · image · file
Output
text
Input: $2.00Output: $10.00per milione di token
Vedi i dettagli del modello →