Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

ChatMeta1M tokens$0.218 / $0.872 · 1M

meta-llama/llama-4-maverick

Contexto
1M tokens
Máx. completion
16,384
Tools
Sí
JSON
Sí
Lanzamiento
2025-04-05

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Llama 4 Maverick?
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput. Llama 4 Maverick corre en el API de Geek Hub (compatible con OpenAI). Id: meta-llama/llama-4-maverick.
¿Llama 4 Maverick es gratis?
No. El input cuesta $0.218 / 1M tokens y el output $0.872 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Llama 4 Maverick?
Llama 4 Maverick tiene una ventana de 1M tokens. Soporta hasta 16,384 tokens de completion.
¿Llama 4 Maverick soporta tool calling y structured outputs?
Llama 4 Maverick acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó Llama 4 Maverick?
Llama 4 Maverick se lanzó el 5 de abril de 2025.

Más modelos de Meta