Alibaba Cloud Model Studio:Text Chat & Omni

Bailian CLI command reference for text chat and Omni multimodal interaction.

A single command invokes Bailian's text chat and Omni multimodal interaction capabilities from the terminal.

Command reference

bl text chat

Send a text model request (OpenAI compatible, DashScope). Requires API Key authentication.

Usage

bl text chat --message <text> [flags]

Parameter	Type	Required	Description
--api <chat|responses>	string	no	API to call (default: chat)
--model <model>	string	no	Model ID (default: qwen3.8-max)
--message <text>	array	no	Message text (repeatable, prefix role: to set role); or use --messages-file
--messages-file <path>	string	no	JSON file with messages array (use - for stdin)
--system <text>	string	no	System prompt
--max-tokens <n>	number	no	Maximum tokens to generate (default: 4096)
--temperature <n>	number	no	Sampling temperature (0.0, 2.0]
--top-p <n>	number	no	Nucleus sampling threshold
--stream	switch	no	Stream response tokens (default: on in TTY)
--tool <json-or-path>	array	no	Tool definition as JSON or file path (repeatable)
--enable-thinking	switch	no	Enable thinking/reasoning mode (for qwen3/qwq models)
--thinking-budget <n>	number	no	Max tokens for thinking (default: 4096)
--batch	switch	no	Send a single synchronous Batch Chat request (non-streaming)
--prime	switch	no	Use Prime mode with a workspace-scoped endpoint
--workspace-id <id>	string	no	Workspace ID for the default Prime endpoint (or set BAILIAN_WORKSPACE_ID)

Example: Send message asking What is Qwen?

bl text chat --message "What is Qwen?"

Example: Send a synchronous Batch Chat request

bl text chat --batch --model qwen-plus --message "Hello" --timeout 3600

• --batch sends one synchronous Batch Chat request and forces non-streaming even in a TTY. It cannot be combined with --prime, --api responses, or --stream. --message or --messages-file supplies the conversation context for one request, not independent requests from a file.
• Batch Chat total request timeout defaults to 300 seconds; --timeout must be 60–3600 seconds. For file-based batch inference, use batch create/get/download; create returns a task ID without waiting for completion.
• --batch rejects explicitly specified realtime, international, or Token Plan endpoints; explicitly specified Batch or custom proxy URLs retain existing credentials. No automatic fallback or POST replay occurs.
• Prime mode requires an explicit model and currently supports only the Chat Completions API.
• Prime endpoint: configured --base-url, DASHSCOPE_BASE_URL, or profile base_url takes precedence; otherwise workspace is resolved from --workspace-id, BAILIAN_WORKSPACE_ID, then config workspace_id.

bl omni

Multimodal chat with text + audio output (Qwen-Omni). Requires API Key authentication.

Usage

bl omni --message <text> [flags]

Parameter	Type	Required	Description
--message <text>	array	no	Message text (repeatable, prefix role: to set role)
--model <model>	string	no	Model ID (default: qwen3.5-omni-plus)
--system <text>	string	no	System prompt
--image <url>	array	no	Image URL or local file (repeatable)
--audio <url>	array	no	Audio URL or local file (.wav/.mp3/.amr/.aac/.m4a/.ogg/.3gp/.3gpp)
--video <url>	array	no	Video file URL / local path, or comma-separated frame URLs
--voice <voice>	string	no	Output voice ID (default: Tina). Use --list-voices to see all options
--list-voices	switch	no	List available output voices and exit
--audio-format <fmt>	string	no	Audio output format (default: wav)
--audio-out <path>	string	no	Save audio to file (default: auto-generate)
--text-only	switch	no	Output text only, no audio generation
--max-tokens <n>	number	no	Maximum tokens to generate
--temperature <n>	number	no	Sampling temperature (0.0, 2.0]

Example: List available output voices for Qwen-Omni

bl omni --list-voices