Compare LlamaFree to compare in the browser. No signup.
Speed
4 of 4
Fastest in the catalog
Context window
131K tokens
How much text fits in one request
Who can use it
Every wallet
Free: 20 API requests a day with a wallet
Input, per 1M tokens
$0.10
What the provider charges. Explorer and Holder pay nothing.
Output, per 1M tokens
$0.32
Builder pays this + 15% from prepaid credits.
Community ranking
Not ranked yet
Rankings appear after the first community votes.
Call it from your code
Use the model id llama with any OpenAI SDK. Streaming, tools and JSON mode pass straight through.
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.dualyne.com/v1", api_key=os.environ["DUALYNE_KEY"])
reply = client.chat.completions.create(
model="llama",
messages=[{"role": "user", "content": "Hello"}],
)
