Send the whole conversation each turn so the model keeps context.
# 1) Ask the first question
curl -X POST "https://api.incredible.one/v1/chat-completion" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $INCREDIBLE_API_KEY" \
  -d '{
    "model": "small-1",
    "stream": false,
    "messages": [
      { "role": "user", "content": "What\'s the capital of France?" }
    ]
  }'

# 2) Add the assistant reply to your local history, then ask a follow‑up
# Replace ASSISTANT_REPLY with the text from result.response[0].content
curl -X POST "https://api.incredible.one/v1/chat-completion" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $INCREDIBLE_API_KEY" \
  -d '{
    "model": "small-1",
    "stream": false,
    "messages": [
      { "role": "user", "content": "What\'s the capital of France?" },
      { "role": "assistant", "content": "ASSISTANT_REPLY" },
      { "role": "user", "content": "What\'s the population of that city?" }
    ]
  }'
View source on GitHub → 3_conversation.py