OpenCode Models & LLM Providers

OpenCode is model-agnostic and supports 75+ LLM providers through Models.dev. Use built-in free models, connect your existing subscriptions, or bring your own API keys.

Quick Model Selection

Use Case	Recommended Model	Provider
Getting Started	Zen Default	OpenCode (Free)
Complex Tasks	Zen Advanced	OpenCode (Free)
Fast Responses	Zen Fast	OpenCode (Free)
Best Reasoning	Claude 3.5 Sonnet	Anthropic
Large Context	Gemini 1.5 Pro	Google
Existing Subscription	GPT-4o	OpenAI

Built-in Models (Zen)

The easiest way to get started is with OpenCode Zen - no API key required:

opencode auth login --provider zen

See OpenCode Zen for detailed information about built-in models.

Major Providers

Anthropic (Claude)

Claude models are known for excellent reasoning and code understanding.

Available Models:

• Claude 3.5 Sonnet (Recommended)
• Claude 3.5 Haiku
• Claude 3 Opus

Setup:

opencode auth login --provider anthropic

Or configure manually:

{
  "provider": "anthropic",
  "apiKey": "sk-ant-..."
}

Use Cases:

• Complex reasoning: Best for multi-step problem solving
• Code understanding: Excellent at analyzing large codebases
• Documentation: Great for generating detailed documentation

---

OpenAI (GPT)

GPT models excel at general-purpose coding tasks and have strong tool use capabilities.

Available Models:

• GPT-4o (Recommended)
• GPT-4 Turbo
• GPT-4o Mini

Setup:

opencode auth login --provider openai

Or configure manually:

{
  "provider": "openai",
  "apiKey": "sk-..."
}

Use Cases:

• General coding: Well-rounded for most coding tasks
• Fast iterations: Quick responses for rapid development
• Tool integration: Strong function calling capabilities

---

Google (Gemini)

Gemini models offer large context windows and strong multimodal capabilities.

Available Models:

• Gemini 1.5 Pro (Recommended)
• Gemini 1.5 Flash
• Gemini 1.0 Ultra

Setup:

opencode auth login --provider google

Or configure manually:

{
  "provider": "google",
  "apiKey": "AIza..."
}

Use Cases:

• Large codebases: 1M+ token context window
• Fast responses: Flash models for quick tasks
• Multimodal: Can analyze images and diagrams

---

Additional Providers

Groq

Ultra-fast inference for supported models.

Available Models:

• Llama 3.1 70B
• Mixtral 8x7B
• Gemma 2 9B

Setup:

opencode auth login --provider groq

Use Cases:

• Speed priority: Fastest response times available
• High throughput: Great for batch processing

---

GitHub Copilot

Use your existing GitHub Copilot subscription with OpenCode.

Setup:

opencode auth login --provider github

Use Cases:

• Existing subscription: No additional API costs
• Familiar models: GPT-4 and Claude models

---

Azure OpenAI

Use Azure-hosted OpenAI models with enterprise features.

Available Models:

• GPT-4
• GPT-4 Turbo
• GPT-3.5 Turbo

Setup:

opencode auth login --provider azure

Use Cases:

• Enterprise: Data privacy and compliance requirements
• SLA guarantees: Azure’s enterprise support

---

Local Models

Run models locally with Ollama for complete privacy.

Ollama

Setup:

1. Install Ollama from ollama.com
2. Pull a model:

ollama pull llama3.1
ollama pull codellama
ollama pull qwen2.5-coder

3. Configure OpenCode:

opencode auth login --provider ollama

Recommended Local Models:

• Llama 3.1 70B: Best overall quality (requires 40GB+ RAM)
• Llama 3.1 8B: Good balance of quality and speed (requires 8GB+ RAM)
• Code Llama 34B: Specialized for code (requires 20GB+ RAM)
• Qwen 2.5 Coder: Excellent code understanding (various sizes)

Use Cases:

• Privacy: Code never leaves your machine
• Offline: Works without internet connection
• Cost: No API costs after setup

---

Model Comparison

Provider	Best For	Speed	Privacy	Cost
Anthropic	Complex reasoning	Medium	Cloud	$15/M tokens
OpenAI	General coding	Medium	Cloud	$10/M tokens
Google	Large context	Fast	Cloud	$7/M tokens
Groq	Speed	Very Fast	Cloud	Free tier
GitHub	Existing subscription	Medium	Cloud	Free with sub
Ollama	Privacy	Depends	Local	Free

Model Configuration

Default Model

Set your default model in the OpenCode configuration:

opencode config set model anthropic/claude-3.5-sonnet

Per-Session Model

Override the default for a specific session:

opencode tui --model openai/gpt-4o

Model Fallback

Configure fallback models for when the primary model is unavailable:

{
  "models": {
    "primary": "anthropic/claude-3.5-sonnet",
    "fallback": ["openai/gpt-4o", "google/gemini-1.5-pro"]
  }
}

Provider Authentication

Interactive Setup

The easiest way to configure providers:

opencode auth login

This will guide you through setting up each provider.

Manual Configuration

For automated setup or CI/CD environments:

# Set API keys via environment variables
export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."
export GOOGLE_API_KEY="AIza..."

# Or use the config file
opencode config set providers.anthropic.apiKey "sk-ant-..."

Multiple Providers

You can use multiple providers and switch between them:

# List configured providers
opencode auth list

# Switch default provider
opencode config set provider anthropic

# Use specific provider for one session
opencode tui --provider openai

Cost Management

Track Usage

Monitor your API costs:

opencode stats

This shows:

• Tokens used per provider
• Estimated costs
• Usage trends

Set Limits

Configure spending limits:

opencode config set budget.monthly 100  # USD
opencode config set budget.alerts true

Optimize Costs

1. Use smaller models for simple tasks: GPT-4o Mini is 10x cheaper than GPT-4o
2. Use free tiers: Groq and GitHub Copilot offer free usage
3. Use local models: Ollama has no API costs
4. Compact sessions: Use /compact to reduce token usage

Troubleshooting

Rate Limits

If you hit rate limits:

• Wait for the limit to reset
• Switch to a different provider
• Use local models (Ollama)

API Errors

Common issues:

• 401 Unauthorized: Check your API key
• 429 Rate Limited: You’ve exceeded your quota
• 500 Server Error: Provider issue, try again later

Model Not Found

If a model isn’t available:

• Check the model name is correct
• Verify your provider supports that model
• Check if the model requires special access

Next Steps

• Quick Start Guide - Get started with OpenCode
• Free Models Guide - Use OpenCode for free
• Configuration - Customize your setup