Integrate Morpheus AI with OpenCode

Learn how to set up Morpheus AI as a custom provider in OpenCode, giving you access to powerful, decentralized AI models for coding assistance. This guide walks you through credential setup, provider configuration, and model selection.

What is OpenCode?

OpenCode is an open-source AI coding agent that helps you write code in your terminal, IDE, or desktop application. It’s a powerful alternative to proprietary coding assistants like Claude Code, offering complete flexibility and privacy for developers.

Open Source & Free

Over 41,000 GitHub stars and 450 contributors building the future of AI-powered coding.

Privacy First

OpenCode doesn’t store any of your code or context data, making it ideal for sensitive projects.

Any Model, Any Provider

Connect to 75+ LLM providers including Claude, GPT, Gemini, local models, and now Morpheus AI.

Multi-Platform

Available as terminal interface, desktop app (macOS, Windows, Linux), and IDE extensions.

Key Features

LSP Enabled: Automatically loads the right Language Server Protocols for enhanced LLM understanding
Multi-Session: Run multiple AI agents in parallel on the same project
Share Links: Share session links for collaboration and debugging
Claude Pro Support: Use your existing Claude Pro or Max subscription
400,000 Monthly Users: Trusted by developers worldwide for production use

By integrating Morpheus AI with OpenCode, you combine the power of decentralized, free AI inference with OpenCode’s privacy-first, open-source architecture.

Overview

OpenCode is an open-source AI coding assistant that supports multiple AI providers. By integrating Morpheus AI, you gain access to free, decentralized AI inference through the Morpheus marketplace with models optimized for code generation, reasoning, and development tasks.

The Morpheus API Gateway is currently in Open Beta, providing free access to AI inference without requiring wallet connections or staking MOR tokens.

Prerequisites

Before you begin, ensure you have:

OpenCode installed on your system opencode.ai/docs
A Morpheus AI account at app.mor.org
Basic familiarity with JSON configuration files
Access to your system’s terminal or command line

Get Your Morpheus AI API Key

Visit app.mor.org and create your API key.

On the main page (API Keys) Click Create New Key
Provide a descriptive name for the key
Copy the generated API key (starts with sk-)

Store your API key securely. You won’t be able to view it again after the initial creation. Never commit API keys to version control.

Install OpenCode

If you haven’t already, install OpenCode on your system:

macOS
Linux
Windows

brew install opencode

curl -fsSL https://opencode.ai/install.sh | sh

irm https://opencode.ai/install.ps1 | iex

Verify installation by running opencode --version in your terminal.

Launch OpenCode

Start OpenCode for the first time:

opencode

You’re now ready to configure Morpheus AI as a provider.

Configuring the Provider

Create or update your OpenCode configuration to define the Morpheus AI provider and available models.

Configuration Location

Global Configuration (Recommended)
Project Configuration

Edit the global configuration file:

~/.config/opencode/opencode.json

This makes Morpheus AI available across all your projects.

Create a configuration file in your project root:

./opencode.json

This makes Morpheus AI available only for the specific project.

Full Provider Configuration

Add the following configuration to your opencode.json file:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "morpheus-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Morpheus AI",
      "options": {
        "baseURL": "https://api.mor.org/api/v1"
      },
      "models": {
        "glm-4.6": {
          "name": "GLM 4.6",
          "limit": {
            "context": 200000,
            "output": 65536
          }
        },
        "glm-4.6-web": {
          "name": "GLM 4.6 (Web)",
          "limit": {
            "context": 200000,
            "output": 65536
          }
        },
        "kimi-k2-thinking": {
          "name": "Kimi K2 Thinking",
          "limit": {
            "context": 256000,
            "output": 16384
          }
        },
        "kimi-k2-thinking-web": {
          "name": "Kimi K2 Thinking (Web)",
          "limit": {
            "context": 256000,
            "output": 16384
          }
        },
        "qwen3-coder-480b-a35b-instruct": {
          "name": "Qwen3 Coder 480B",
          "limit": {
            "context": 262144,
            "output": 16384
          },
          "options": {
            "timeout": 600000
          }
        },
        "qwen3-coder-480b-a35b-instruct-web": {
          "name": "Qwen3 Coder 480B (Web)",
          "limit": {
            "context": 262144,
            "output": 16384
          },
          "options": {
            "timeout": 600000
          }
        },
        "hermes-3-llama-3.1-405b": {
          "name": "Hermes 3 Llama 3.1 405B",
          "limit": {
            "context": 128000,
            "output": 8192
          },
          "options": {
            "timeout": 600000
          }
        },
        "hermes-3-llama-3.1-405b-web": {
          "name": "Hermes 3 Llama 3.1 405B (Web)",
          "limit": {
            "context": 128000,
            "output": 8192
          },
          "options": {
            "timeout": 600000
          }
        },
        "qwen3-235b": {
          "name": "Qwen3 235B",
          "limit": {
            "context": 131072,
            "output": 8192
          }
        },
        "qwen3-235b-web": {
          "name": "Qwen3 235B (Web)",
          "limit": {
            "context": 131072,
            "output": 8192
          }
        },
        "qwen3-next-80b": {
          "name": "Qwen3 Next 80B",
          "limit": {
            "context": 131072,
            "output": 4096
          }
        },
        "qwen3-next-80b-web": {
          "name": "Qwen3 Next 80B (Web)",
          "limit": {
            "context": 131072,
            "output": 4096
          }
        },
        "llama-3.3-70b": {
          "name": "Llama 3.3 70B",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "llama-3.3-70b-web": {
          "name": "Llama 3.3 70B (Web)",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "mistral-31-24b": {
          "name": "Mistral 31 24B",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "mistral-31-24b-web": {
          "name": "Mistral 31 24B (Web)",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "venice-uncensored": {
          "name": "Venice Uncensored",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "venice-uncensored-web": {
          "name": "Venice Uncensored (Web)",
          "limit": {
            "context": 128000,
            "output": 8192
          }
        },
        "qwen3-4b": {
          "name": "Qwen3 4B",
          "limit": {
            "context": 131072,
            "output": 4096
          }
        },
        "qwen3-4b-web": {
          "name": "Qwen3 4B (Web)",
          "limit": {
            "context": 131072,
            "output": 4096
          }
        },
        "llama-3.2-3b": {
          "name": "Llama 3.2 3B",
          "limit": {
            "context": 32000,
            "output": 4096
          }
        },
        "llama-3.2-3b-web": {
          "name": "Llama 3.2 3B (Web)",
          "limit": {
            "context": 32000,
            "output": 4096
          }
        },
        "hermes-4-14b": {
          "name": "Hermes 4 14B",
          "limit": {
            "context": 128000,
            "output": 4096
          }
        }
      }
    }
  }
}

Understanding the Configuration

Provider Settings

npm: The AI SDK package used (@ai-sdk/openai-compatible for OpenAI-compatible APIs)
name: Display name shown in the OpenCode UI
options.baseURL: The Morpheus AI API endpoint (https://api.mor.org/api/v1)

Model Configuration

Each model includes:

name: Human-readable model name displayed in the UI
limit.context: Maximum input tokens the model accepts
limit.output: Maximum tokens the model can generate
options.timeout: Optional timeout in milliseconds (used for large models)

Web Model Variants

Models with the -web suffix have enhanced capabilities:

Web search integration
Current information access
Browser-optimized responses

Standard models without -web are optimized for pure reasoning and code generation tasks.

Minimal Configuration

If you prefer a simpler setup with just essential models:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "morpheus-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Morpheus AI",
      "options": {
        "baseURL": "https://api.mor.org/api/v1"
      },
      "models": {
        "glm-4.6": {
          "name": "GLM 4.6"
        },
        "kimi-k2-thinking": {
          "name": "Kimi K2 Thinking"
        },
        "qwen3-coder-480b-a35b-instruct": {
          "name": "Qwen3 Coder 480B"
        }
      }
    }
  }
}

Start with a minimal configuration and add more models as needed. This keeps your model selection clean and focused.

Adding Morpheus AI Credentials

OpenCode stores API credentials securely in ~/.local/share/opencode/auth.json. Use the /connect command to add your Morpheus AI API key.

Using the `/connect` Command

Execute the connect command

In the OpenCode terminal, run:

/connect

Select 'Other' as the provider

When prompted to select a provider, choose Other:

┌  Add credential
│
│ ◆  Select provider
│  ...
│  ● Other
└

Enter the provider ID

Type morpheus-ai as the provider identifier:

┌  Add credential
│
│ ◇  Enter provider id
│  morpheus-ai
└

The provider ID must exactly match morpheus-ai for the configuration to work correctly.

Paste your API key

Enter your Morpheus AI API key when prompted:

┌  Add credential
│
│ ▲  This only stores a credential for morpheus-ai - you will need to configure it in opencode.json
│
│ ◇  Enter your API key
│  sk-xxxxxxxxxxxxx
└

Your Morpheus AI credentials are now securely stored and ready to use with your configured provider!

Setting Default Models

Configure your preferred models for different types of tasks:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "morpheus-ai/glm-4.6",
  "small_model": "morpheus-ai/llama-3.3-70b",
  "provider": {
    "morpheus-ai": {
      ...
    }
  }
}

model

string

Default model used for main coding tasks, complex reasoning, and detailed responses.

small_model

string

Faster, smaller model used for quick tasks like syntax checking, simple completions, and rapid iterations.

Using Morpheus AI in OpenCode

Once configured, restart OpenCode to load the new provider settings.

Restart OpenCode

# Press Ctrl+C to exit the current session
# Then restart
opencode

Select a Model

Use the /models command to view and select from available Morpheus AI models:

/models

You’ll see all configured Morpheus AI models listed. Select one to start using it for your coding tasks.

Switch models at any time using the /models command. Different models excel at different tasks - experiment to find the best fit for your workflow.

Start Coding

With Morpheus AI configured, you can now:

Generate code - Ask for implementations, algorithms, or functions
Debug issues - Get help troubleshooting errors and bugs
Refactor code - Request improvements and optimizations
Explain code - Understand complex codebases
Write tests - Generate test cases and test suites

> Create a Python function that validates email addresses using regex

> Debug this TypeScript error: Type 'number' is not assignable to type 'string'

> Refactor this code to use async/await instead of callbacks

> Explain how this binary search algorithm works

Available Models

The Morpheus marketplace offers a diverse range of models optimized for different tasks:

Premium Models (Best Performance)

Model	Context	Output	Best For
Qwen3 Coder 480B	262K	16K	Complex code generation, architecture design
Hermes 3 Llama 405B	128K	8K	Advanced reasoning, system design
Kimi K2 Thinking	256K	16K	Complex problem solving, multi-step reasoning
GLM 4.6	200K	65K	Long-form code generation, documentation

Balanced Models (Great All-Rounders)

Model	Context	Output	Best For
Qwen3 235B	131K	8K	General coding tasks
Llama 3.3 70B	128K	8K	Code completion, debugging
Qwen3 Next 80B	131K	4K	Fast responses, quick iterations
Mistral 31 24B	128K	8K	Balanced performance, good reasoning

Lightweight Models (Fast & Efficient)

Model	Context	Output	Best For
Hermes 4 14B	128K	4K	Quick completions, syntax help
Qwen3 4B	131K	4K	Simple tasks, rapid iteration
Llama 3.2 3B	32K	4K	Lightweight tasks, low-latency responses

Specialized Models

Model	Context	Output	Best For
Venice Uncensored	128K	8K	Unrestricted content generation

Model availability depends on provider availability in the Morpheus marketplace. The API automatically routes to the highest-rated provider for your selected model. Check the API documentation for the latest model availability.

Verifying Your Setup

Check Authentication Status

Verify that your Morpheus AI credentials are stored correctly:

opencode auth list

You should see morpheus-ai in the list of configured credentials.

If morpheus-ai appears in the list, your credentials are configured correctly.

Test the Connection

Start a conversation in OpenCode and ask a simple question:

> What is Python?

If you receive a response from the selected Morpheus AI model, your integration is working correctly!

Troubleshooting

Models not appearing in OpenCode

Cause: Provider ID mismatch, configuration syntax error, or OpenCode not restarted.Solution:

Verify the provider ID in both /connect and opencode.json exactly matches morpheus-ai
Check that your JSON configuration is valid (no missing commas, brackets)
Restart OpenCode completely
Verify credentials with opencode auth list

# Validate JSON syntax
cat ~/.config/opencode/opencode.json | python -m json.tool

# Check credentials
opencode auth list

Authentication errors when using models

Cause: Invalid or expired API key, or incorrect provider configuration.Solution:

Ensure your API key is valid and active at app.mor.org
Verify the provider ID matches what you used in /connect
Try regenerating your API key if needed
Reconfigure credentials using /connect command

# Remove old credentials and reconfigure
opencode auth remove morpheus-ai
opencode
/connect

Connection errors or timeouts

Cause: Network connectivity issues, firewall blocking, or service unavailability.Solution:

Check your internet connection
Verify the baseURL is correct: https://api.mor.org/api/v1
Ensure your firewall allows HTTPS connections
Check the Morpheus AI service status

For large models like Qwen3 Coder 480B and Hermes 3 Llama 405B, timeouts are pre-configured to 600000ms (10 minutes). If you still experience timeouts, consider using a smaller model or checking your network connection.

Slow response times

Cause: Large model selected, high marketplace demand, or network latency.Solution:

Use smaller models for quick tasks (e.g., llama-3.3-70b, hermes-4-14b)
Configure a small_model in your opencode.json for rapid iterations
Try different models to find the best balance of performance and speed
Check your network latency to the Morpheus API

{
  "model": "morpheus-ai/qwen3-coder-480b-a35b-instruct",
  "small_model": "morpheus-ai/hermes-4-14b"
}

Configuration file not found or ignored

Cause: Wrong file location or OpenCode not looking in the right directory.Solution:

For global configuration: ~/.config/opencode/opencode.json
For project-specific: ./opencode.json in your project root
Ensure the file has correct permissions
Verify JSON syntax is valid

# Create config directory if missing
mkdir -p ~/.config/opencode

# Set proper permissions
chmod 644 ~/.config/opencode/opencode.json

Best Practices

Choose the right model

Select models based on your task complexity. Use large models for complex reasoning and smaller models for quick completions.

Configure small_model

Set a lightweight model as your small_model for faster responses on simple tasks, improving your coding workflow.

Secure your API key

Never commit your API key to version control. Keep it in the secure OpenCode auth storage or environment variables.

Switch models freely

Use the /models command to try different models. Each excels at different tasks - find what works best for you.

Use Web variants strategically

Leverage -web suffix models when you need current information or web-enhanced responses. Use standard models for pure coding tasks.

Monitor performance

Pay attention to response times and quality. Adjust your model selection based on your workflow needs.

Advanced Configuration

Project-Specific Models

Override global settings for specific projects:

project-root/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "morpheus-ai/qwen3-coder-480b-a35b-instruct",
  "small_model": "morpheus-ai/qwen3-4b"
}

Use project-specific configurations when working on specialized projects that benefit from particular models.

Custom Model Limits

Adjust context and output limits based on your needs:

opencode.json

{
  "provider": {
    "morpheus-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Morpheus AI",
      "options": {
        "baseURL": "https://api.mor.org/api/v1"
      },
      "models": {
        "custom-model": {
          "name": "Custom Model",
          "limit": {
            "context": 100000,
            "output": 4096
          },
          "options": {
            "timeout": 300000,
            "temperature": 0.7
          }
        }
      }
    }
  }
}

Additional Resources

Morpheus AI Portal

Manage your API keys, view usage, and access your Morpheus AI account.

API Documentation

Complete reference documentation for the Morpheus API Gateway.

OpenCode Documentation

Learn more about OpenCode provider configuration and advanced features.

Community Support

Join the OpenCode Discord community for help and discussions.

Security Notes

Follow these security best practices to protect your API credentials:

Local storage: Your API key is stored locally in ~/.local/share/opencode/auth.json
Never commit keys: Don’t commit API keys or configuration files with credentials to public repositories
Add to .gitignore: Include both ~/.config/opencode/opencode.json and ~/.local/share/opencode/auth.json in your .gitignore if sharing config files
Rotate compromised keys: If your API key is compromised, immediately rotate it via the Morpheus AI dashboard
Use project configs carefully: Ensure project-specific opencode.json files don’t contain sensitive information

Next Steps

Once configured, you can:

Switch between models

Use the /models command to select different models for various tasks and compare their performance.

Create project configurations

Set up project-specific opencode.json files with models optimized for each project’s needs.

Optimize your workflow

Adjust context and output limits based on your typical use cases to balance performance and capability.

Monitor usage

Track your usage and billing in the Morpheus AI dashboard at app.mor.org.

Summary

You’ve successfully integrated Morpheus AI with OpenCode! Here’s what you’ve accomplished:

Credentials configured: Added your Morpheus AI API key securely to OpenCode

Provider setup: Configured the Morpheus AI provider with access to powerful coding models

Model selection: Learned how to choose and switch between models for different tasks

Best practices: Understand security, performance optimization, and troubleshooting

Free inference: Enabled access to decentralized AI models during the Open Beta

Happy coding with Morpheus AI! 🚀

Getting started

How to guides

Integration guides

​Integrate Morpheus AI with OpenCode

​What is OpenCode?

Open Source & Free

Privacy First

Any Model, Any Provider

Multi-Platform

​Key Features

​Overview

​Prerequisites

​Configuring the Provider

​Configuration Location

​Full Provider Configuration

​Understanding the Configuration

​Minimal Configuration

​Adding Morpheus AI Credentials

​Using the /connect Command

​Setting Default Models

​Using Morpheus AI in OpenCode

​Restart OpenCode

​Select a Model

​Start Coding

​Available Models

​Premium Models (Best Performance)

​Balanced Models (Great All-Rounders)

​Lightweight Models (Fast & Efficient)

​Specialized Models

​Verifying Your Setup

​Check Authentication Status

​Test the Connection

​Troubleshooting

​Best Practices

Choose the right model

Configure small_model

Secure your API key

Switch models freely

Use Web variants strategically

Monitor performance

​Advanced Configuration

​Project-Specific Models

​Custom Model Limits

​Additional Resources

Morpheus AI Portal

API Documentation

OpenCode Documentation

Community Support

​Security Notes

​Next Steps

​Summary

Integrate Morpheus AI with OpenCode

What is OpenCode?

Key Features

Overview

Prerequisites

Configuring the Provider

Configuration Location

Full Provider Configuration

Understanding the Configuration

Minimal Configuration

Adding Morpheus AI Credentials

Using the `/connect` Command

Setting Default Models

Using Morpheus AI in OpenCode

Restart OpenCode

Select a Model

Start Coding

Available Models

Premium Models (Best Performance)

Balanced Models (Great All-Rounders)

Lightweight Models (Fast & Efficient)

Specialized Models

Verifying Your Setup

Check Authentication Status

Test the Connection

Troubleshooting

Best Practices

Advanced Configuration

Project-Specific Models

Custom Model Limits

Additional Resources

Security Notes

Next Steps

Summary