meta-llama/llama-4-maverick
1,048,576 context · $0.15/M input tokens · $0.60/M output tokens
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...
Harga
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Coba model
Penggunaan API
Gunakan contoh kode berikut untuk integrasi dengan API kami:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/llama-4-maverick",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Pengenalan Model
Meta-Llama llama-4-maverick
meta-llama llama-4-maverick
Why It Looks Great
- Large Language Model architecture for efficient processing
- 1048576 context window for long document handling
- Competitive pricing at $0.2/$0.7 per million tokens
Key Features
- Context Window: 1048576 tokens
- Max Output: 16384 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Meta-Llama |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 1048576 tokens |
| Max Output | 16384 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.2 |
| Output | $0.7 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: meta-llama/llama-4-maverick
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/llama-4-maverick",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "meta-llama/llama-4-maverick",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: meta-llama/llama-4-maverick
- Provider: Meta-Llama
Info
Fitur yang Didukung
Panduan Akses API
Llama 4 Maverick API
meta-llama/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...
Input
$0.15 /M
Output
$0.6 /M
Konteks
1049K
Output Maks.
16K
Vision
Didukung
Penggunaan Tool
Didukung
Coba Llama 4 Maverick di WaveSpeedAI
Akses Llama 4 Maverick melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Pertanyaan Umum tentang Llama 4 Maverick
Berapa biaya Llama 4 Maverick melalui API?+
Harga di WaveSpeedAI: $0.15 per juta token input dan $0.60 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Berapa context window Llama 4 Maverick?+
Llama 4 Maverick mendukung hingga 1049K token konteks dengan hingga 16K token output per permintaan.
Apakah Llama 4 Maverick kompatibel dengan OpenAI?+
Ya. WaveSpeedAI menyediakan Llama 4 Maverick melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Bagaimana memulai dengan Llama 4 Maverick?+
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Llama 4 Maverick.