Unlimited AI is OpenAI-compatible. It's a drop-in replacement for any OpenAI client - just change the base URL and API key.
ul_sk_ API key from the dashboardPOST /v1/chat/completions - chat completions, streaming or notPOST /v1/audio/transcriptions - Whisper transcriptionGET /v1/models - list available models| Model | Daily cap | Use case |
|---|---|---|
qwen3-235b |
NONE | General-purpose. Code, reasoning, chat. Default. |
llama-3.3-70b |
1M tokens combined | Fast inference via Groq. |
llama-3.2-90b-vision |
1M tokens combined | Image understanding. |
whisper-large-v3 |
30 min audio | Speech-to-text. |
curl https://unlimited-ai.net/v1/chat/completions \
-H "Authorization: Bearer $UL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-235b",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'
from openai import OpenAI
client = OpenAI(
api_key="ul_sk_...",
base_url="https://unlimited-ai.net/v1"
)
response = client.chat.completions.create(
model="qwen3-235b",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
https://unlimited-ai.net/v1ul_sk_ keyqwen3-235bSame drill - configure as an OpenAI-compatible provider:
{
"openai": {
"baseURL": "https://unlimited-ai.net/v1",
"apiKey": "ul_sk_...",
"model": "qwen3-235b"
}
}
We don't count daily tokens on Qwen3-235B. Make as many requests as you want for the entire week. We only block bots that exceed 10 RPS (which no human can reach by typing).
Prices may change for new subscriptions with 7 days notice. Existing active weekly subs are honored at the price you paid until they expire.