alpindale/goliath-120b
6,144 context · $3.75/M input tokens · $7.50/M output tokens
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - @chargoddard for developing the framework used to merge...
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="alpindale/goliath-120b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)A large LLM created by combining two fine-tuned Llama 70B models into one 120B model
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.
Credits to
#merge
| Specification | Value |
|---|---|
| Provider | Alpindale |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 6144 tokens |
| Max Output | 1024 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $4.1 |
| Output | $8.2 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: alpindale/goliath-120b
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="alpindale/goliath-120b",
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": "alpindale/goliath-120b",
"messages": [{"role": "user", "content": "Hello!"}]
}'alpindale/goliath-120b
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...
Input
$3.75 /M
Output
$7.5 /M
Konteks
6K
Output Maks.
1K
Akses Goliath 120b melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Buka PlaygroundHarga di WaveSpeedAI: $3.75 per juta token input dan $7.50 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Goliath 120b mendukung hingga 6K token konteks dengan hingga 1K token output per permintaan.
Ya. WaveSpeedAI menyediakan Goliath 120b 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 Goliath 120b.