Your first request

With your API key ready, follow Installation if you plan to use the openai client; then make your first call below.

Example

curl https://api-inference.bitdeer.ai/v1/chat/completions \
  -H "Authorization: Bearer $BITDEER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Explain distributed inference in 3 bullet points."}],
    "max_tokens": 256
  }'

What to expect

• Responses use the documented JSON shape — fields such as choices, usage, and id as in the API Reference.
• Streaming is available by setting stream: true — see the Streaming guide.
• Every response includes a unique ID you can use for debugging.

Next steps

• Browse the API Reference for all available endpoints and parameters.
• Check the Model Catalog to see all available models.
• Explore Guides for advanced features like Vision and Function Calling.