Model API gateway: one API key for OpenAI, Claude and more
Cloudigo model gateway is the single entry point for model calls. Create a key in API key management, then call any available model through the gateway without applying for provider keys. The base URL is https://cloudigo.ai/api/v1, supporting Chat Completions, messages and Responses.
1. One integration for many models
Using several models usually means registering, getting keys and topping up with each provider. Call records and bills are spread across consoles, so adding up total spend takes manual work.
With the Cloudigo model gateway you call several available models with one API key and review call records and cost in one place.
2. Integration steps
Create an API key
Sign in to Cloudigo and create a key in API key management. The full key is shown only once at creation, so save it securely. Never put keys in front-end code or commit them to public repositories.
Choose a model
Find a model by type or name in the marketplace, open its detail page to review context length, billing items, unit price and supported calling methods, then copy the model ID.
Configure the request
The base URL is https://cloudigo.ai/api/v1. Authenticate with Authorization: Bearer YOUR_CLOUDIGO_API_KEY. Supported calling methods differ by model; follow the request format and example on each detail page. Each model supports only part of the gateway’s calling methods — GPT-5.4 and GPT-5.5, for example, use Responses rather than Chat Completions.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_CLOUDIGO_API_KEY",
base_url="https://cloudigo.ai/api/v1",
)
response = client.chat.completions.create(
model="YOUR_MODEL_ID",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)curl "https://cloudigo.ai/api/v1/messages" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_CLOUDIGO_API_KEY" \
-d '{
"model": "YOUR_MODEL_ID",
"messages": [{"role": "user", "content": "Hello!"}],
"max_tokens": 1024
}'Replace YOUR_CLOUDIGO_API_KEY with your key and YOUR_MODEL_ID with the model ID from the marketplace.
Review usage and cost
Token Usage shows call records and cost by model or API key, updated in real time, with full history and CSV export.
3. Billing and balance
Model APIs need no subscription: billing follows actual token usage and each model’s rules; items and unit prices are on the marketplace and model detail pages.
Requests that fail without producing valid output are not billed. For streaming requests interrupted after content started returning, the usage already produced is billed.
Model calls use a separate LLM account. When its balance is insufficient, new calls are rejected.
4. Frequently asked
Do I need to change code to switch models?
It depends on the calling methods the new model supports. Each detail page lists methods and examples. If the new model’s request format differs from what you use, adjust your code accordingly.
How do I top up the LLM account?
Paid Cloudigo services are prepaid. After topping up, allocate funds to the cloud account or LLM account you will use. Crypto payment is supported with a minimum single top-up of USD 100. Fees are USD 3 for USD 1,000 or less and USD 5 above USD 1,000.
Does Cloudigo store my prompts and responses?
Prompt and response content is not stored in our database, and Cloudigo does not train its own models on call requests. Requests are forwarded to the corresponding provider for processing.
Create an API key and start calling
Pick a model in the marketplace, create an API key, and integrate through the gateway.