Basic text generation
Send a prompt to the/v1/responses endpoint:
With reasoning
Enable reasoning for complex tasks:OpenAI-compatible format
Use/v1/chat/completions if you prefer the OpenAI message format:
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Send prompts to /v1/responses to generate text with AtlasFlux, control output with max_output_tokens and temperature, and enable reasoning effort levels.
/v1/responses endpoint:
curl https://api.atlasflux.my/v1/responses \
-H "Authorization: Bearer $ATLASFLUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": "Explain quantum computing in simple terms",
"max_output_tokens": 512,
"temperature": 0.7
}'
curl https://api.atlasflux.my/v1/responses \
-H "Authorization: Bearer $ATLASFLUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": "Solve this step by step: If a train travels 120km in 2 hours, what is its average speed?",
"reasoning": {"effort": "medium"},
"max_output_tokens": 1024
}'
/v1/chat/completions if you prefer the OpenAI message format:
curl https://api.atlasflux.my/v1/chat/completions \
-H "Authorization: Bearer $ATLASFLUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is the capital of Japan?"}
],
"max_tokens": 256,
"temperature": 0.5
}'
| Value | Behavior |
|---|---|
| 0.0 | Deterministic, most focused |
| 0.3 | Conservative, low variation |
| 0.7 | Balanced (default) |
| 1.0 | Creative, high variation |
| 2.0 | Maximum randomness |
Was this page helpful?
