Skip to main content
Enable real-time response streaming for interactive conversations and immediate feedback in your AI applications. Get responses in real-time:
  • CLI
  • Python SDK
  • JavaScript SDK
gravixlayer chat --model "meta-llama/llama-3.1-8b-instruct" --user "Tell me a short story" --stream
Example Output:
Once upon a time, in a small village nestled between rolling hills, there lived a young baker named Elena. Every morning, she would wake before dawn to prepare fresh bread for the townspeople. One day, she discovered that her sourdough starter had developed an unusual golden glow...

[Content streams in real-time as the model generates it]

​
Streaming Completions

  • CLI
  • Python SDK
  • JavaScript SDK
gravixlayer chat --mode completions --model "meta-llama/llama-3.1-8b-instruct" --prompt "Write a poem" --stream
⌘I