Superconductor Docs

OpenCode

Superconductor is the best place to run OpenCode in the cloud.

OpenCode model selector listing Opus 4.8, Opus 5, Sonnet 4.6, Gemini 3.1 Pro, Gemini 3.6 Flash, Gemini 3 Flash, GPT-5.5, GPT-5.5 Pro, GPT-5.6 Sol, Grok 4.5, DeepSeek V4 Flash, GLM 5.2, Kimi K2.6, MiniMax M2.7, Qwen3.6 Plus, and Big Pickle

Credentials

Configure your OpenCode API key at the Project or Workspace level.

You can get an API key from OpenCode Zen.

Models

OpenCode supports models from multiple providers:

Anthropic

  • Opus 4.8 - Previous-generation Opus, still available
  • Opus 5 (High) - Most capable Opus-tier model for complex reasoning
  • Sonnet 4.6 - Balanced performance and capability

Google

  • Gemini 3.1 Pro - Advanced reasoning and code generation
  • Gemini 3.6 Flash - Google's newest Flash model, for fast iteration
  • Gemini 3 Flash - Fast and efficient for quick tasks

OpenAI

  • GPT-5.5 - OpenAI's newer general coding model
  • GPT-5.5 Pro - Higher-capability GPT-5.5 variant for complex tasks
  • GPT-5.6 Sol (Xhigh) - The most capable GPT-5.6 option for complex coding, reasoning, and polish

Other Providers

  • Grok 4.5 (High) - xAI's previous-generation model, for comparing against Grok Build
  • DeepSeek V4 Flash - Fast DeepSeek model for lighter changes
  • GLM 5.2 - Z.ai's coding model
  • Kimi K2.6 - Moonshot AI's coding model
  • MiniMax M2.7 - Efficient general-purpose model
  • Qwen3.6 Plus - Alibaba's coding model
  • Big Pickle - High-performance coding model

Learn more about OpenCode Zen in the OpenCode documentation.

On this page