คู่มือการใช้งาน API

เริ่มต้นเรียก AI Gateway ของ Wisporta ใน 3 ขั้นตอน

1. Get your API key

2. Make your first request

Use the same OpenAI-compatible format — just change the base URL and API key.

bash

curl https://api.wisporta.com/v1/chat/completions \
  -H "Authorization: Bearer sk-live-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

3. Streaming response

Add "stream": true to receive real-time tokens.

bash

curl https://api.wisporta.com/v1/chat/completions \
  -H "Authorization: Bearer sk-live-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-6",
    "messages": [{ "role": "user", "content": "Tell me a joke" }],
    "stream": true
  }'

# Response stream:
# data: {"choices":[{"delta":{"content":"Why"},"index":0}]}
# data: {"choices":[{"delta":{"content":" did"},"index":0}]}
# data: [DONE]

4. Error handling

json

{
  "error": {
    "message": "Insufficient credit balance",
    "type": "insufficient_credit",
    "code": 402
  }
}

Error type	HTTP	Meaning
unauthorized	401	Invalid or missing API key
insufficient_credit	402	Credit balance is zero
rate_limited	429	Too many requests
upstream_error	502	Provider returned an error

5. Supported providers

•OpenAI — openai/gpt-4o, openai/gpt-4o-mini
•Anthropic — anthropic/claude-sonnet-4-6
•Google — google/gemini-2.5-pro
•Mistral — mistral/mistral-large

See full model list on the Pricing page.