OpenCode

OpenCode integration for NanoGPT

OpenCode Integration

Use NanoGPT with OpenCode, the open source AI coding agent for your terminal.

One-Click Setup (Mac/Linux)

Run this command in your terminal:

curl -fsSL "https://nano-gpt.com/install/opencode_nanogpt.sh" | bash

This will:

1. Open your browser to authenticate with NanoGPT (or let you paste an API key)
2. Configure OpenCode to use NanoGPT as your AI provider
3. Set up popular models like Claude Sonnet 4.5, Claude 4.5 Opus, GPT 5.2, Gemini 3 Flash (Preview), Gemini 3 Pro, GLM 4.7

Manual Setup

If you prefer to configure manually:

1. Create the auth file

Add your NanoGPT API key to ~/.local/share/opencode/auth.json:

{
  "nano-gpt": {
    "type": "api",
    "key": "your-nano-gpt-api-key"
  }
}

2. Create the config file

Create ~/.config/opencode/.opencode.json:

{
  "model": "nano-gpt/claude-sonnet-4-5-20250929",
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "NanoGPT",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "claude-opus-4-5-20251101": {
          "name": "Claude 4.5 Opus",
          "limit": { "context": 200000, "output": 32000 }
        },
        "claude-sonnet-4-5-20250929": {
          "name": "Claude Sonnet 4.5",
          "limit": { "context": 1000000, "output": 64000 }
        },
        "openai/gpt-5.2": {
          "name": "GPT 5.2",
          "limit": { "context": 128000, "output": 128000 }
        },
        "deepseek/deepseek-v4-pro": {
          "name": "DeepSeek V4 Pro",
          "limit": { "context": 1048576, "output": 384000 }
        },
        "deepseek/deepseek-v4-pro:thinking": {
          "name": "DeepSeek V4 Pro Thinking",
          "limit": { "context": 1048576, "output": 384000 }
        },
        "deepseek/deepseek-v4-flash": {
          "name": "DeepSeek V4 Flash",
          "limit": { "context": 1048576, "output": 384000 }
        },
        "deepseek/deepseek-v4-flash:thinking": {
          "name": "DeepSeek V4 Flash Thinking",
          "limit": { "context": 1048576, "output": 384000 }
        },
        "google/gemini-3-flash-preview": {
          "name": "Gemini 3 Flash (Preview)",
          "limit": { "context": 1048756, "output": 65536 }
        },
        "gemini-3-pro-preview": {
          "name": "Gemini 3 Pro",
          "limit": { "context": 1048756, "output": 65536 }
        },
        "zai-org/glm-4.7": {
          "name": "GLM 4.7",
          "limit": { "context": 200000, "output": 65535 }
        }
      }
    }
  }
}

Usage

After setup, start OpenCode:

opencode

Switching Models

Use the /model command inside OpenCode to switch between models, or edit the model field in your .opencode.json:

{
  "model": "nano-gpt/deepseek/deepseek-v4-pro"
}

Available Models

The setup script preconfigures these models:

Model ID	Description
nano-gpt/claude-sonnet-4-5-20250929	Claude Sonnet 4.5 (default)
nano-gpt/claude-opus-4-5-20251101	Claude 4.5 Opus
nano-gpt/openai/gpt-5.2	GPT 5.2
nano-gpt/deepseek/deepseek-v4-pro	DeepSeek V4 Pro
nano-gpt/deepseek/deepseek-v4-pro:thinking	DeepSeek V4 Pro Thinking
nano-gpt/deepseek/deepseek-v4-flash	DeepSeek V4 Flash
nano-gpt/deepseek/deepseek-v4-flash:thinking	DeepSeek V4 Flash Thinking
nano-gpt/google/gemini-3-flash-preview	Gemini 3 Flash (Preview)
nano-gpt/gemini-3-pro-preview	Gemini 3 Pro
nano-gpt/zai-org/glm-4.7	GLM 4.7

Adding More Models

Add any of NanoGPT’s 250+ models to the models section in your config:

"models": {
  "zai-org/glm-4.7": {
    "name": "GLM 4.7",
    "limit": { "context": 200000, "output": 65535 }
  }
}

List available models with GET https://nano-gpt.com/api/v1/models.

Requirements

• OpenCode installed (curl -fsSL https://opencode.ai/install | bash)
• A NanoGPT account with API access

Troubleshooting

OpenCode not finding the config?

OpenCode searches for config in this order:

1. ./.opencode.json (current directory)
2. $XDG_CONFIG_HOME/opencode/.opencode.json
3. $HOME/.opencode.json

Authentication errors?

Check that your API key is correctly set in ~/.local/share/opencode/auth.json (as an object with type and key) and that the key name matches the provider ID (nano-gpt).