CosmicAC Logo

Inference

Send chat completion requests to managed inference endpoints. Supports text prompts and optional video URL inputs.

Command

cosmicac inference <subcommand> [options]

Subcommands

SubcommandDescription
chatChat with AI models

inference chat

Send chat completion requests to a managed inference endpoint. Supports text prompts and optional video URL inputs. Run without --message to start an interactive chat session.

Usage

cosmicac inference chat [options]

Options

OptionDescription
--api-keyAPI key for authentication (prompted if not provided)
--endpoint-idInference endpoint ID
--modelAI model to use for completion (e.g., qwen3-vl-thinking-fp8-prod)
--messageMessage to send to the model (omit for interactive mode)
--video-urlURL of video to analyze
--streamEnable streaming response for real-time output

On this page