AI TOOLS RADAR
Explorar
Todos los modelos / 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.

Ver fuente en OpenRouter
Resumen

Especificaciones del modelo

Contexto
200.000 tokens
Salida máxima
64.000 tokens
Arquitectura
text+image+file->text
Tokenizador
Claude
Corte de conocimiento
No indicado
Moderado
Sí
OPENROUTER

Precios completos

Tarifas sincronizadas desde OpenRouter, por millón de tokens.

Entrada
$1
/M tokens
Salida
$5
/M tokens
Lectura de caché
$0.1
/M tokens
Escritura de caché
$1.25
/M tokens
Cache Write (1h)
$2
/M tokens
Búsqueda web
$10
/1K calls
API

Configuración del modelo

Razonamiento

Moderado
No
Parámetros predeterminados
No
API

Inicio rápido

Usa este modelo mediante la API compatible con OpenAI de 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!"}]}'
Capacidades y modalidades

Entrada → Salida

Entrada
textimagefile
Salida
text
Razonamiento

No

API

Parámetros API compatibles

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Proveedores disponibles

8 proveedores

Proveedores en vivo en OpenRouter

Disponibilidad, latencia, rendimiento y enrutamiento cambian continuamente. Consulta la fuente para datos actuales.

OpenRouter

Anthropic

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.00
Salida
$5.00
Lectura de caché
$0.100
Escritura de caché
$1.25

Google

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.00
Salida
$5.00
Lectura de caché
$0.100
Escritura de caché
$1.25

Azure

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.00
Salida
$5.00
Lectura de caché
$0.100
Escritura de caché
$1.25

Amazon Bedrock

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.00
Salida
$5.00
Lectura de caché
$0.100
Escritura de caché
$1.25

Amazon Bedrock

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.10
Salida
$5.50
Lectura de caché
$0.110
Escritura de caché
$1.38

Amazon Bedrock

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.10
Salida
$5.50
Lectura de caché
$0.110
Escritura de caché
$1.38

Google

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.10
Salida
$5.50
Lectura de caché
$0.110
Escritura de caché
$1.38

Google

unknown
Contexto
200K
Salida máxima
64K
Entrada
$1.10
Salida
$5.50
Lectura de caché
$0.110
Escritura de caché
$1.38
anthropic

modelos

Todos los modelos
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

Contexto
1M
Entrada
text · image · file
Salida
text
Entrada: $10.00Salida: $50.00por millón de tokens
Ver detalles del modelo →
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...

Contexto
1M
Entrada
text · image · file
Salida
text
Entrada: $5.00Salida: $25.00por millón de tokens
Ver detalles del modelo →
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...

Contexto
1M
Entrada
text · image · file
Salida
text
Entrada: $2.50Salida: $12.50por millón de tokens
Ver detalles del modelo →
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,...

Contexto
1M
Entrada
text · image · file
Salida
text
Entrada: $2.00Salida: $10.00por millón de tokens
Ver detalles del modelo →