Add visual understanding capabilities

Some Token Plan models (qwen3.7-plus, qwen3.6-plus, qwen3.5-plus) natively support visual understanding and can process image inputs directly. For text-only models such as glm-5 and MiniMax-M2.5, you can add visual capabilities by configuring a local Skill.

Running the image understanding Skill consumes Token Plan Credits. No additional charges apply.

Prerequisites

You have subscribed to Token Plan. See Getting started.
You have completed the integration configuration in a Token Plan tool and can chat normally. See Clients and Developer Tools for your tool's setup guide.

Vision support

Model	Vision support	Description
qwen3.7-plus, qwen3.6-plus, qwen3.5-plus	Yes	No additional configuration required. You can pass images directly.
qwen3-max-2026-01-23, qwen3-coder-next, qwen3-coder-plus, glm-5, glm-4.7, MiniMax-M2.5	No	Requires a Skill or Agent to enable visual capabilities

Method 1: Use a vision model directly (recommended)

qwen3.7-plus, qwen3.6-plus, and qwen3.5-plus have visual understanding capabilities. If you frequently need to process images, switching to one of these models is the simplest and recommended approach.

Tool	How to switch
Claude Code	`/model qwen3.7-plus` or `/model qwen3.6-plus` or `/model qwen3.5-plus`
OpenCode	`/models` then search and select `qwen3.7-plus` or `qwen3.6-plus` or `qwen3.5-plus`
Qwen Code	`/model` then select `qwen3.7-plus` or `qwen3.6-plus` or `qwen3.5-plus`

For more information about switching models in other coding tools, see Clients and Developer Tools. After switching, you can reference image paths directly in your conversation, or drag-and-drop/paste images.

Method 2: Add visual capabilities via Skill or Agent

If you need to use text-only models such as glm-5 or MiniMax-M2.5 for image processing, you can configure a Skill or Agent to enable visual capabilities.

Claude Code
OpenCode

Add the Skill

Create an .claude folder in your project directory, then create a skills/image-analyzer directory inside it:

mkdir -p .claude/skills/image-analyzer

Create a SKILL.md file in that directory with the following content:

---
name: image-analyzer
description: Helps models without vision capabilities understand images. Use this skill when you need to analyze image content, extract information, text, or UI elements from images, or understand screenshots, charts, architecture diagrams, or any visual content. Simply pass in the image path to get a description.
model: qwen3.7-plus
---
qwen3.7-plus has visual understanding capabilities. Use qwen3.7-plus directly for image understanding.

The resulting directory structure is as follows:

.claude/
└── skills/
  └── image-analyzer/
    └── SKILL.md

Getting started

Run claude in your project directory to start Claude Code, then run /model glm-5 to switch to the glm-5 model.
Reference an image path in the conversation and ask a question, for example: Load image-analyzer skill and describe the content in screenshot.png.

Add the Agent

Create an .opencode folder in your project directory, then create an agents directory inside it:

mkdir -p .opencode/agents

Create an image-analyzer.md file in that directory with the following content:

The model field must use the provider and model name defined in the OpenCode configuration file. Refer to the configuration example in the OpenCode documentation. It should be qwen-cloud-token-plan/qwen3.7-plus.

---
description: Analyzes images using a vision-capable model. Use this agent when the user needs to understand image content, extract information from screenshots, diagrams, UI mockups, or any visual content. Invoke with @image-analyzer followed by the image path and your question.
mode: subagent
model: qwen-cloud-token-plan/qwen3.7-plus
tools:
  write: false
  edit: false
---
You have vision capabilities. Analyze the provided image and return a clear, structured description focused on what the user is asking about.

The resulting directory structure is as follows:

.opencode/
└── agents/
  └── image-analyzer.md

Getting started

Run opencode in your project directory to start OpenCode, then switch to the glm-5 model.
Invoke @ image-analyzer and ask a question, for example: @image-analyzer describe the content in screenshot.png.

FAQ

Why can't OpenCode + a vision model understand images?

Cause: OpenCode does not enable a model's vision capabilities by default. You must explicitly declare the modalities parameter in the configuration file.Solution: Add a modalities field to the model definition in your OpenCode configuration file, and set input to ["text", "image"], as shown below:

Replace sk-sp-xxx with your Token Plan API Key.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "qwen-cloud-token-plan": {
      "npm": "@ai-sdk/anthropic",
      "name": "Qwen Cloud Token Plan",
      "options": {
        "baseURL": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "apiKey": "sk-sp-xxx"
      },
      "models": {
        "qwen3.7-plus": {
          "name": "Qwen3.7 Plus",
          "modalities": {
            "input": [
              "text",
              "image"
            ],
            "output": [
              "text"
            ]
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 1024
            }
          }
        },
        "qwen3.6-plus": {
          "name": "Qwen3.6 Plus",
          "modalities": {
            "input": [
              "text",
              "image"
            ],
            "output": [
              "text"
            ]
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 1024
            }
          }
        },
        "qwen3.5-plus": {
          "name": "Qwen3.5 Plus",
          "modalities": {
            "input": [
              "text",
              "image"
            ],
            "output": [
              "text"
            ]
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 1024
            }
          }
        }
      }
    }
  }
}

Why can't OpenClaw + a vision model understand images?

Cause: OpenClaw requires the input field in the configuration file to determine whether a model supports vision capabilities.Solution:

In the ~/.openclaw/openclaw.json configuration file, ensure the model definition includes the "input": ["text", "image"] field.

{
  "models": {
    "mode": "merge",
    "providers": {
      "bailian": {
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "apiKey": "YOUR_API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3.7-plus",
            "name": "qwen3.7-plus",
            "reasoning": false,
            "input": ["text", "image"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "qwen3.6-plus",
            "name": "qwen3.6-plus",
            "reasoning": false,
            "input": ["text", "image"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "qwen3.5-plus",
            "name": "qwen3.5-plus",
            "reasoning": false,
            "input": ["text", "image"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 1000000,
            "maxTokens": 65536
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "bailian/qwen3.6-plus"
      },
      "models": {
        "bailian/qwen3.7-plus": {},
        "bailian/qwen3.6-plus": {},
        "bailian/qwen3.5-plus": {}
      }
    }
  },
  "gateway": {
    "mode": "local"
  }
}

After modifying the configuration, you must clear the OpenClaw model cache and restart. Otherwise, the old configuration will remain in effect.

rm ~/.openclaw/agents/main/agent/models.json
openclaw gateway restart

​Prerequisites

​Vision support

​Method 1: Use a vision model directly (recommended)

​Method 2: Add visual capabilities via Skill or Agent

Add the Skill

Getting started

​FAQ

Prerequisites

Vision support

Method 1: Use a vision model directly (recommended)

Method 2: Add visual capabilities via Skill or Agent

FAQ