Access world-class AI models through a single OpenAI-compatible endpoint. Use your own API key with any client that supports the OpenAI API format.
Register at shopno.freedev.app/register.php and log in to your dashboard.
Go to the 🔑 API Keys section in your Dashboard and click "Generate New Key". Your key will look like: sk-shopno-a1b2c3d4...
Use the key in the Authorization header with any OpenAI-compatible client.
# Your first API call
curl https://mail.surveymentor.org/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "copilot::claude-haiku-4-5",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'
All API requests require a valid API key sent via the Authorization header:
Authorization: Bearer sk-shopno-YOUR_API_KEY
Shopno API keys always start with sk-shopno- followed by 48 hexadecimal characters. Example:
sk-shopno-a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6
Shopno Cloud routes your requests to the best available provider for each model. All models are accessed through the same endpoint.
| Model ID | Provider | Tier Required |
|---|---|---|
copilot::claude-haiku-4-5 |
copilot | FREE |
google-antigravity::gemini-2.5-flash |
google-antigravity | FREE |
google-antigravity::gemma-4-31b-it |
google-antigravity | FREE |
nvidia::nvidia/nemotron-3-ultra-550b-a55b |
nvidia | FREE |
nvidia::mistralai/mistral-small-4-119b-2603 |
nvidia | FREE |
nvidia::mistralai/ministral-14b-instruct-2512 |
nvidia | FREE |
nvidia::minimaxai/minimax-m3 |
nvidia | FREE |
nvidia::meta/llama-3.1-8b-instruct |
nvidia | FREE |
nvidia::deepseek-ai/deepseek-v4-pro |
nvidia | FREE |
nvidia::bigcode/starcoder2-15b |
nvidia | FREE |
nvidia::nvidia/nemotron-nano-3-30b-a3b |
nvidia | FREE |
nvidia::openai/gpt-oss-20b |
nvidia | FREE |
nvidia::qwen/qwen3.5-122b-a10b |
nvidia | FREE |
nvidia::z-ai/glm-5.2 |
nvidia | FREE |
nvidia::nvidia/nemotron-4-340b-instruct |
nvidia | FREE |
ollama::llama3 |
ollama | FREE |
ollama::mistral |
ollama | FREE |
ollama::phi3 |
ollama | FREE |
ollama::gemma |
ollama | FREE |
openrouter::meta-llama/llama-3.3-70b-instruct:free |
openrouter | FREE |
pollinations::openai-fast |
pollinations | FREE |
google::gemini-2.0-flash |
PRO | |
nvidia::nvidia/nemotron-3-nano-30b-a3b |
nvidia | PRO |
nvidia::qwen/qwen3.5-397b-a17b |
nvidia | PRO |
nvidia::deepseek-ai/deepseek-v4-flash |
nvidia | PRO |
nvidia::openai/gpt-oss-120b |
nvidia | PRO |
nvidia::nvidia/nemotron-3-super-120b-a12b |
nvidia | PRO |
nvidia::stepfun-ai/step-3.5-flash |
nvidia | PRO |
nvidia::stepfun-ai/step-3.7-flash |
nvidia | PRO |
nvidia::meta/llama-3.1-70b-instruct |
nvidia | PRO |
nvidia::moonshotai/kimi-k2.6 |
nvidia | PRO |
nvidia::minimaxai/minimax-m2.7 |
nvidia | PRO |
nvidia::z-ai/glm-5.1 |
nvidia | PRO |
nvidia::google/gemma-4-31b-it |
nvidia | PRO |
nvidia::nvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
nvidia | PRO |
nvidia::mistralai/mistral-large-3-675b-instruct-2512 |
nvidia | PRO |
nvidia::mistralai/mistral-medium-3.5-128b |
nvidia | PRO |
nvidia::nvidia/llama-3.3-nemotron-super-49b-v1.5 |
nvidia | PRO |
nvidia::meta/llama-3.2-11b-vision-instruct |
nvidia | PRO |
nvidia::nvidia/llama-3.1-nemotron-safety-guard-8b-v3 |
nvidia | PRO |
nvidia::nvidia/nemotron-content-safety-reasoning-4b |
nvidia | PRO |
openai::gpt-4o-mini |
openai | PRO |
openai::gpt-5.4-mini |
openai | PRO |
openai::gpt-5.4 |
openai | PRO |
groq::openai/gpt-oss-120b |
groq | ULTRA |
openai::gpt-5.5 |
openai | ULTRA |
openrouter::deepseek/deepseek-chat |
openrouter | ULTRA |
shopno-cloud-{profile_id} to target a specific model profile by its database ID.
https://mail.surveymentor.org/v1
POST /chat/completions
Creates a model response for the given chat conversation. Supports streaming via SSE.
{
"model": "shopno-cloud-2",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain quantum computing in simple terms."}
],
"stream": true,
"temperature": 0.7,
"max_tokens": 2048
}
from openai import OpenAI
client = OpenAI(
api_key="sk-shopno-YOUR_KEY_HERE",
base_url="https://mail.surveymentor.org/v1"
)
response = client.chat.completions.create(
model="copilot::claude-haiku-4-5",
messages=[
{"role": "user", "content": "Write a Python function to reverse a string"}
],
stream=True
)
for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
const response = await fetch('https://mail.surveymentor.org/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'copilot::claude-haiku-4-5',
messages: [{ role: 'user', content: 'Hello!' }],
stream: true,
}),
});
const reader = response.body.getReader();
const decoder = new TextDecoder();
while (true) {
const { done, value } = await reader.read();
if (done) break;
console.log(decoder.decode(value));
}
curl -X POST https://mail.surveymentor.org/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"copilot::claude-haiku-4-5","messages":[{"role":"user","content":"Hi"}],"stream":true}'
API usage is limited per day based on your subscription plan:
| Plan | Daily Requests | Max API Keys | Price |
|---|---|---|---|
| FREE | 50 / day | 5 | $0 |
| PRO | 450 / day | 5 | $5/mo |
| ULTRA | 1,400 / day | 5 | $19/mo |
Shopno Chat natively supports Shopno Cloud. To use your API key:
Go to Settings → Providers → Shopno Cloud
Paste your sk-shopno-... key in the API Key field.
Select any Shopno Cloud model from the model dropdown and start a conversation!