Token Plan integration overview-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

Agent tools natively handle only text generation protocols. Image generation, video generation, speech synthesis, speech recognition, real-time voice, and decision models require Slash Commands, Skills, or Agents to call their interfaces.

Why integration is needed

Agent tools such as Claude Code, Codex, OpenCode, and Qwen Code natively handle only text generation protocols (OpenAI-compatible or Anthropic-compatible). Image generation, video generation, speech synthesis, speech recognition, real-time voice, and decision models in Token Plan are outside these protocols. Use Slash Commands, Skills, or Agents to call their interfaces.

Interface overview

Capability	Interface
Decision model	`https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/systemone`
Image generation	`https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation`
Video generation (submit)	`https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis`
Video generation (query)	`https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1/tasks/{task_id}`
Speech synthesis	`https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1/services/audio/tts/SpeechSynthesizer`
Speech recognition	`https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation`
Real-time voice	`wss://token-plan.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime?model=qwen-audio-3.0-realtime-plus`

Quick start

Choose the document for the capability you want to integrate. Configuration steps are in each document.

Integrate decision models

Synchronous, structured response

Integrate the image generation model

Synchronous

Integrate the video generation model

Asynchronous task

Integrate the speech synthesis model

Synchronous

Integrate the speech recognition model

Synchronous

Integrate the real-time voice conversation model

WebSocket

Prerequisites

A Token Plan subscription. For the Personal Edition, get the sk-sp- API key from My Subscription (Personal). For the Team Edition, assign a seat in Member Management, then get the API key.
Your tool supports one of the extension mechanisms in the preceding table.

Tool configuration paths

The following table uses image generation as an example. For other capabilities, replace text-to-image with the command name for that capability, and replace token-plan-image with the corresponding Skill name.

Tool	Extension mechanism	Configuration file path
Claude Code	Slash Command	`.claude/commands/text-to-image.md`
Codex	Skill	`~/.codex/skills/token-plan-image/SKILL.md`
Qwen Code	Skill	`~/.qwen/skills/text-to-image/SKILL.md`
OpenCode	Agent	`.opencode/agents/text-to-image.md`
OpenClaw	Skill	`~/.openclaw/workspace/skills/token-plan-image/SKILL.md`
Hermes Agent	Skill	`~/.hermes/skills/media/text-to-image/SKILL.md`
Qoder	Skill	`~/.qoder/skills/text-to-image/SKILL.md`

Billing and security

Billing differs by capability. Actual Credits consumption is shown in Usage in the console.
Use the API key only in tool configuration or environment variables. Do not write it to command files, code repositories, or logs.
Generated URLs expire. Download the results promptly.