Skip to content

Instantly share code, notes, and snippets.

View steebchen's full-sized avatar
🌴
Working remotely

Luca Steeb steebchen

🌴
Working remotely
View GitHub Profile
@steebchen
steebchen / minimax-m2.md
Created January 25, 2026 19:21
MiniMax M2 with OpenCode via LLM Gateway

MiniMax M2 with OpenCode via LLM Gateway

Model Overview

  • Model ID: minimax-m2
  • Provider: MiniMax
  • Strengths: Long context, efficient inference, strong code generation
  • Context: 1M tokens

Configuration

@steebchen
steebchen / glm-4-7.md
Created January 25, 2026 19:21
GLM-4.7 with OpenCode via LLM Gateway

GLM-4.7 with OpenCode via LLM Gateway

Model Overview

  • Model ID: glm-4-plus
  • Provider: Zhipu AI
  • Strengths: Strong multilingual support, competitive reasoning, Chinese language excellence
  • Context: 128K tokens

Configuration

@steebchen
steebchen / minimax-m2.md
Created January 25, 2026 19:21
MiniMax M2 with Claude Code via LLM Gateway

MiniMax M2 with Claude Code via LLM Gateway

Model Overview

  • Model ID: minimax-m2
  • Provider: MiniMax
  • Strengths: Long context, efficient inference, strong code generation
  • Context: 1M tokens

Configuration

@steebchen
steebchen / glm-4-7.md
Created January 25, 2026 19:21
GLM-4.7 with Claude Code via LLM Gateway

GLM-4.7 with Claude Code via LLM Gateway

Model Overview

  • Model ID: glm-4-plus
  • Provider: Zhipu AI
  • Strengths: Strong multilingual support, competitive reasoning, Chinese language excellence
  • Context: 128K tokens

Configuration

@steebchen
steebchen / qwen-coder-plus.md
Created January 25, 2026 17:28
Qwen Coder Plus with OpenCode via LLM Gateway

Qwen Coder Plus with OpenCode via LLM Gateway

Model Overview

  • Model ID: qwen-coder-plus-latest
  • Provider: Alibaba
  • Strengths: Code-specialized, strong at generation, open-source foundation
  • Context: 128K tokens

Configuration

@steebchen
steebchen / deepseek-chat.md
Created January 25, 2026 17:28
DeepSeek Chat with OpenCode via LLM Gateway

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

@steebchen
steebchen / gemini-2-0-flash.md
Created January 25, 2026 17:28
Gemini 2.0 Flash with OpenCode via LLM Gateway

Gemini 2.0 Flash with OpenCode via LLM Gateway

Model Overview

  • Model ID: gemini-2.0-flash
  • Provider: Google
  • Strengths: Fast responses, cost-effective, good for iterations
  • Context: 1M tokens

Configuration

@steebchen
steebchen / o3.md
Created January 25, 2026 17:28
o3 with OpenCode via LLM Gateway

o3 with OpenCode via LLM Gateway

Model Overview

  • Model ID: o3
  • Provider: OpenAI
  • Strengths: Advanced multi-step reasoning, complex problem solving
  • Context: 128K tokens

Configuration

@steebchen
steebchen / gpt-4o.md
Last active January 25, 2026 17:28
GPT-4o with OpenCode via LLM Gateway

GPT-4o with OpenCode via LLM Gateway

Model Overview

  • Model ID: gpt-4o
  • Provider: OpenAI
  • Strengths: General-purpose coding, broad knowledge base
  • Context: 128K tokens

Configuration

@steebchen
steebchen / claude-sonnet-4.md
Created January 25, 2026 17:28
Claude Sonnet 4 with OpenCode via LLM Gateway

Claude Sonnet 4 with OpenCode via LLM Gateway

Model Overview

  • Model ID: claude-sonnet-4-20250514
  • Provider: Anthropic
  • Strengths: Balanced speed and quality, daily coding tasks
  • Context: 200K tokens

Configuration