Aliyun Model Studio CLI MCP server

The official command-line interface for Aliyun Model Studio (DashScope) AI Platform

Aliyun Model Studio CLI Site · 中文文档 · API Documentation · Get API Key

---

Chat with Qwen, generate and edit images and videos, understand images, synthesize and recognize speech, call apps, manage memory, retrieve knowledge, search the web — every AI capability, one command away.

Built for AI Agents. Every command works as a structured tool call.

Features

• Model generation — Full-modality generation across text, image, video, and speech, with editing and reference-based generation
• Asset understanding — Parse and ask questions about images, documents, audio, and long videos
• App orchestration — Call Managed Agents, agents, and workflows published on Aliyun Model Studio, wired to knowledge bases, memory, web search, and MCP tools
• Native MCP setup — Register Bailian MCP servers in Codex, Claude Code, Cursor, Qoder, Qoder Work, QwenWork (千问办公), Qwen Code, Gemini CLI, or Pi
• Training & deployment — Validate and upload datasets, fine-tune models, deploy dedicated models as endpoints
• Batch inference — Prepare CSV/JSONL, create and follow asynchronous Chat/Embedding tasks, download original results/errors with optional CSV, or send one synchronous Batch Chat request
• Account operations — Login, UI-based configuration, model marketplace, usage and quota, rate-limit increases, team seat management
• Plan onboarding — Connect subscription plans such as Token Plan to the CLI and common coding agents in one step

Note: App orchestration, native MCP setup, training & deployment, account operations, and plan onboarding are currently available only to China site (aliyun.com) account holders and are not yet supported for international / global site accounts.

Showcase 1: A Cinematic Short Film from One Sentence

A complete 2-minute, 16:9 cinematic short film — produced end-to-end from a single natural-language sentence, with zero manual editing. This showcase demonstrates how an AI Agent can compose a multi-step creative pipeline by orchestrating three primitives:

• Qwen Code — the agentic coding model that interprets the user's intent and drives the workflow
• Aliyun Model Studio CLI — invokes HappyHorse 1.1, Aliyun Model Studio's text-/image-/reference-to-video generation model
• spark-video Skill — handles scene decomposition, storyboarding, shot continuity, and final stitching

The single prompt

"Generate a roughly 2-minute video in Japanese cinematic style — a sweet, innocent first-love story about a high-school girl. The plot should be heart-fluttering enough to make viewers want to fall in love. Aspect ratio: 16:9."

Showcase 2: A Short-Film Director Managed Agent from One Sentence

One sentence builds a reusable cloud-side short-film director for storyboarding, storyboard image generation, and video creation:

• Qwen Code — understands the requirement and generates the agent configuration
• Aliyun Model Studio CLI — validates the configuration, previews the changes, and completes the deployment
• Managed Agent — runs the director role along with its skills and tools in the cloud

The single prompt

"Build me a Managed Agent app that can produce short films — a director expert that generates videos and can also design the matching storyboards."

Installation

Agent install (recommended)

Send the following to your Agent — it will detect your environment, then install and verify the CLI for you:

Please read https://bailian.aliyun.com/cli/install.md and install the Aliyun Model Studio CLI for me

Install with NPM

npm install -g bailian-cli
bl skill init

Requires Node.js >= 18.17.

Install on macOS/Linux

curl -fsSL https://bailian.aliyun.com/cli/install.sh | bash

No Node.js required. The installer automatically installs Bailian Skills.

Install on Windows

irm https://bailian.aliyun.com/cli/install.ps1 | iex

No Node.js required. The installer automatically installs Bailian Skills.

Quick Start

Once installed, just describe your task to your AI Agent — no need to assemble commands by hand.

Scenario	What to say to your Agent
Managed Agent	"Create a Managed Agent that can generate short-film storyboards and videos."
Image & video generation	"Generate an image of a cat in a spacesuit on Mars, then turn it into a video."
Speech recognition	"Transcribe this audio; if proper nouns are wrong, add hot words and try again."
Usage & quota	"Show my recent model usage, free-tier quota, and rate limits."
Monitoring & alerts	"Show my model call stats, failures and logs, and create an alert rule."
Throughput reservations	"List my throughput reservations and capacity instances, then scale, renew or release capacity and wait for the operation to finish."
Model selection	"Recommend a model for image understanding and customer support."
Decision model	"Use the Bailian decision model to route this ticket and assess whether it needs escalation."
About Bailian CLI	"Tell me what Bailian CLI can do for me, and suggest how to use it for my needs."

More examples and scenarios: Aliyun Model Studio CLI Site

Try a knowledge base

With a valid API key and workspace, preview initialization first:

bl knowledge init --workspace-id <workspace-id> --dry-run

Knowledge bases accrue running-time charges from creation, even without queries. The one-time Standard Edition 720-hour allowance is shared across knowledge bases and expires 30 days after activation for new users. Model calls cost extra; your remaining allowance is unknown. Review the plan and billing rules, then add --yes to the same command after confirming the operation, removing --dry-run to execute.

Keep the returned IDs and recovery record. Closing the CLI or a later failure does not stop billing; follow the reported cleanup actions to delete unused knowledge bases. See the Knowledge Studio quick start for retrieval and cleanup. The bailian-knowledge Skill is available through bl skill init.

RAG audio and video

bl knowledge doc import --index-id <id> --doc-id <fileId> imports an existing file into a knowledge base; doc list --details shows per-file processing settings. Media support includes parser options, streaming uploads, and media references in search/chunk output. Chat JSON separates the final answer from phases, tools, docs, usage, and raw events; quiet mode hides progress and informational messages while preserving the final result, including every JSON field. See the command guide.

ParseX

Parse documents or audio/video and extract structured fields through the workspace-scoped ParseX API:

bl parsex parse submit --workspace-id <workspace-id> --file-url "https://example.com/document.pdf" --file-name document.pdf --output-file-format markdown --output json
bl parsex parse result --workspace-id <workspace-id> --biz-id <parse-biz-id> --follow --output json
bl parsex extract submit --workspace-id <workspace-id> --parsed-file-biz-id <parse-biz-id> --schema-file schema.json --output json
bl parsex extract result --workspace-id <workspace-id> --biz-id <extract-biz-id> --follow --output json

Use an ordinary API key and a workspace with ParseX access. Submission returns data.biz_id immediately; result --follow waits for completion. schema.json contains a JSON Schema object, for example {"type":"object","properties":{"title":{"type":"string"}}}. Inputs are accessible HTTP(S) URLs; extraction also accepts a retained document parsing task. See the ParseX command guide for processing options, result slices, OSS credentials, dry-run and polling behavior.

Batch Inference

bl batch convert --help
bl batch convert --file input.csv --output-file input.jsonl --model qwen-plus
bl batch create --file input.jsonl --dry-run
bl batch create --file input.jsonl
bl batch get --batch-id <id> --follow
bl batch download --batch-id <id> --csv
bl text chat --batch --model qwen-plus --message "Hello" --timeout 3600

--help includes CSV, JSONL and result data examples. convert is local and needs no key; inference/task commands use a model API key. File inference uses asynchronous tasks via create → get → download: create uploads/submits and returns a task ID without waiting for completion. Query with get and download results after completion. Conversion/download files are atomically published per file and never silently overwritten. Use --force to recover partial downloads. JSONL is the authoritative result, while CSV is a lossy display; import IDs as text to preserve leading zeros. Ctrl-C stops local polling, not the remote task.

text chat --batch sends one synchronous request and waits for its response; it does not create an asynchronous task ID. Use --message or --messages-file, which contains one request's conversation context, not independent file requests. The total request timeout defaults to 300 seconds (--timeout: 60–3600 seconds). Timeout/Ctrl-C/disconnection do not guarantee server cancellation.

Synchronous Batch Chat is non-streaming; explicit realtime/international/Token Plan endpoints are rejected. An explicit realtime profile requires --base-url https://batch.dashscope.aliyuncs.com. Batch availability and limits depend on the service/model. Dry-run avoids business requests and output/directory writes; framework update checks/telemetry follow their settings.

Authentication

Console Login (OAuth, Recommended)

Required for console capability commands (model list, app list, MCP list, workspace, usage queries, rate-limit increases, direct console calls). It can create an ordinary API key when needed. Token Plan and other subscription plans cannot use --console; use the API Key login below.

bl auth login --console

Use --console-site international for the international console.

The CLI always prints the login URL. To choose a browser yourself, keep the command running and open the URL on the same machine:

bl auth login --console --no-browser --console-site international

If the browser blocks the local callback, check the console site's local-network permission or try Firefox. The PNA compatibility header does not bypass Chrome's local-network permission or Safari's mixed-content restrictions. No callback within 15 minutes is a failure (exit code 5), not a successful login.

If you already have a valid console access token, import it via stdin without a browser or local callback server. Specify the token's actual region and site; for example, in a POSIX shell:

bl auth login --console --token-stdin --console-site international --console-region ap-southeast-1 < /path/to/console-token.txt

Input must be one raw token (up to 64 KiB), not JSON or Bearer ...; interactive terminal input is rejected to avoid echoing secrets. Use a protected file or trusted pipe, never put the token in command arguments or shell history, and remove temporary secret files after use. The CLI validates the token before saving; failure leaves existing credentials and the active Profile unchanged. Add --config <name> to save and activate a specific Profile on success. This imports only the console session, not a model API key.

API Key

To use an existing ordinary API key or a Token Plan subscription key, run the same command:

bl auth login --api-key <API_KEY>

Get an ordinary key from the DashScope Console, or a Token Plan key from the subscription overview.

Alibaba Cloud OpenAPI AK/SK

Token Plan seat and member management requires an Alibaba Cloud AccessKey. Get yours from the RAM Console.

Recommended: create a RAM sub-account with minimum privileges instead of using the root account's AK/SK.

bl auth login --open-api --access-key-id LTAI5t... --access-key-secret ...

Configuration

# View current config
bl config show

# List all config profiles
bl config list

# Switch config profile
bl config use --name token-plan

# Switch the CLI interface to Chinese
bl config set --key language --value zh-CN

Config file location: ~/.bailian/config.json

Update

bl update

Upgrades the CLI to the latest version and refreshes the installed Agent Skills. Release notes for every version live in CHANGELOG.md.

Contributing

Bug reports, feature requests, and PRs are welcome. See CONTRIBUTING.md for developer setup, repo layout, and the workflow for adding or changing commands.

Scan the QR code to join the Aliyun Model Studio CLI DingTalk user group for usage help, troubleshooting, bug reports, and tips from other users.

Links

Memory documentation (Chinese): capability matrix · command guide.

Resource	URL
Aliyun Model Studio CLI Site	https://bailian.console.aliyun.com/cli?spm=a2ty07.github
DashScope API Docs	https://help.aliyun.com/zh/model-studio/
Qwen Model List	https://help.aliyun.com/zh/model-studio/getting-started/models
Aliyun Model Studio Console	https://bailian.console.aliyun.com/?spm=a2ty07.github
Get API Key	https://bailian.console.aliyun.com/cn-beijing/?spm=a2ty07.github&tab=app#/api-key
Get Token Plan API Key	https://bailian.console.aliyun.com/cn-beijing?spm=a2ty07.github&tab=plan#/efm/subscription/overview
Get AccessKey	https://ram.console.aliyun.com/manage/ak