DeepSeek Chat with OpenCode via LLM Gateway

Model Overview

• Model ID: deepseek-chat
• Provider: DeepSeek
• Strengths: Cost-effective, strong coding capability, open-weights model
• Context: 64K tokens

Configuration

Add to ~/.config/opencode/config.json:

{
  "provider": "openai-compatible",
  "apiKey": "your-llmgateway-api-key",
  "baseUrl": "https://api.llmgateway.io/v1",
  "model": "deepseek-chat"
}

Or via environment:

export OPENCODE_PROVIDER="openai-compatible"
export OPENCODE_API_KEY="your-llmgateway-api-key"
export OPENCODE_BASE_URL="https://api.llmgateway.io/v1"
export OPENCODE_MODEL="deepseek-chat"

Usage

opencode --model deepseek-chat "add error handling to this function"

Best Use Cases

• Day-to-day coding tasks on a budget
• Code generation and completion
• Bug fixes and simple refactoring
• Learning and experimentation
• High-volume coding assistance

Pricing Tier

Budget - excellent value for standard coding tasks.