Product
One AI Gateway for every leading model, paid in Thai baht
One endpoint to call, one place to manage every key in the organisation, and the cost of every request in plain sight
Getting started
Start calling the AI Gateway in 3 steps
1
Create an API key
Open the dashboard and create a key on the API Keys page. Keys start with sk-
2
Change the base URL
Keep OpenAI's request format — only the base URL and API key change
3
Pick a model by one name
Pass provider/model, e.g. openai/gpt-5.5 or anthropic/claude-sonnet-5
first request
curl https://api.wisporta.com/v1/chat/completions \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.5",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'streaming
# add "stream": true to receive tokens as they are produced
data: {"choices":[{"delta":{"content":"Why"},"index":0}]}
data: {"choices":[{"delta":{"content":" did"},"index":0}]}
data: [DONE]Error handling
The same error shape across every provider
| Error type | HTTP | Meaning |
|---|---|---|
| unauthorized | 401 | API key is invalid or missing |
| insufficient_credit | 402 | Credit balance is too low |
| too_many_requests | 429 | Too many requests in flight for this organization |
| upstream_error | 502 | The upstream provider returned an error |
API key management
Issue as many API keys as you need inside one organisation
Sample
| Key | Name | Status |
|---|---|---|
| sk-8f2c… | production-web | Active |
| sk-1a90… | support-bot | Active |
| sk-77bd… | data-team | Revoked |
Credit remaining 12,480 pts62%
