cURL (general)

Use cURL to smoke-test each endpoint — handy for quick verification and debugging. First put the key in an environment variable:

export TT_API_KEY="sk-your-key"

Examples use the gateway address https://gateway.mindproxy.ai.

Chat (OpenAI-compatible)

curl https://gateway.mindproxy.ai/v1/chat/completions \
  -H "Authorization: Bearer $TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Add "stream": true for streaming:

curl https://gateway.mindproxy.ai/v1/chat/completions \
  -H "Authorization: Bearer $TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o-mini", "stream": true,
       "messages": [{"role": "user", "content": "Tell me a joke"}]}'

Claude native (Anthropic Messages)

curl https://gateway.mindproxy.ai/v1/messages \
  -H "x-api-key: $TT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-5-sonnet",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Also accepts Authorization: Bearer $TT_API_KEY.

Gemini native (generateContent)

curl "https://gateway.mindproxy.ai/v1beta/models/gemini-1.5-pro:generateContent?key=$TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Hello"}]}]}'

Use :streamGenerateContent for streaming.

Embeddings

curl https://gateway.mindproxy.ai/v1/embeddings \
  -H "Authorization: Bearer $TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "text-embedding-3-small", "input": "some text"}'

Image generation

curl https://gateway.mindproxy.ai/v1/images/generations \
  -H "Authorization: Bearer $TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-1", "prompt": "a city at night", "n": 1, "size": "1024x1024"}'

Billed by the actual number of images returned. See Image generation.

List available models

curl https://gateway.mindproxy.ai/v1/models \
  -H "Authorization: Bearer $TT_API_KEY"

Handy debugging tips

• See response headers: add -i (or -D -) to print headers, including X-TT-Request-ID for troubleshooting.
• Dry run (no model call, no charge): add -H "X-TT-Dry-Run: true" to exercise auth and billing hold only and return a billing estimate.
• Idempotency: when retrying the same request, add -H "Idempotency-Key: <your-unique-key>" to avoid double charges.

Next: Python · Node.js · Streaming & tools