Meta's quality-focused MoE model with 17B active parameters (400B total, 128 experts). Targets quality-critical tasks with benchmark scores competitive with GPT-4o and Gemini 2.5 Pro.
1.0M tokens
8
Disponible
Más económico
Anyscale
$0.50/1M tokens
Amazon Bedrock, Anyscale, Azure AI, Deep Infra, Fireworks, Hugging Face Inference, Replicate, Together AI
Ordenados por coste total (entrada y salida por 1 millón de tokens). Selecciona una fila para ver los detalles del proveedor.
| Proveedor | Precio (por 1 M) | Límites | Regiones | Estado | Latencia |
|---|---|---|---|---|---|
Entrada: $0.25Salida: $0.25 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Operativo | 0ms | |
Entrada: $0.27Salida: $0.27 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Operativo | 0ms | |
Entrada: $0.30Salida: $0.30 | 300 RPM / 500K TPM | us-east-1eu-west-1 | Operativo | 0ms | |
Entrada: $0.37Salida: $0.37 | 200 RPM / 600K TPM | us-east-1us-west-2eu-west-1 | Operativo | 0ms | |
Entrada: $0.20Salida: $0.60 | 600 RPM / 1.0M TPM | us-east-1eu-west-1 | Operativo | 0ms | |
Entrada: $0.22Salida: $0.88 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Operativo | 0ms | |
Entrada: $0.30Salida: $0.95 | 300 RPM / 500K TPM | us-east-1us-west-2 | Operativo | 0ms | |
Entrada: $0.34Salida: $0.99 | 100 RPM / 400K TPM | us-east-1us-west-2 | Operativo | 0ms |
Usa este modelo mediante Anyscale con un SDK compatible con OpenAI.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.anyscale.com/v1",
apiKey: process.env.ANYSCALE_API_KEY,
});
const response = await client.chat.completions.create({
model: "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);API de Anyscale · SDK compatible con OpenAI