amazon/nova-pro-v1
300,000 context · $0.80/M input tokens · $3.20/M output tokens
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
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="amazon/nova-pro-v1",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)amazon nova-pro-v1
| Specification | Value |
|---|---|
| Provider | Amazon |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 300000 tokens |
| Max Output | 5120 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.9 |
| Output | $3.5 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: amazon/nova-pro-v1
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="amazon/nova-pro-v1",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "amazon/nova-pro-v1",
"messages": [{"role": "user", "content": "Hello!"}]
}'amazon/nova-pro-v1
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
Input
$0.8 /M
Output
$3.2 /M
Konteks
300K
Output Maks.
5K
Vision
Didukung
Penggunaan Tool
Didukung
Akses Nova Pro V1 melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Harga di WaveSpeedAI: $0.80 per juta token input dan $3.20 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Nova Pro V1 mendukung hingga 300K token konteks dengan hingga 5K token output per permintaan.
Ya. WaveSpeedAI menyediakan Nova Pro V1 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.
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 Nova Pro V1.