OpenCode

Kickstart OpenCode with Infron

Account & API Keys Setup

The first step to start using Infron is to create an account and get your API key.

Installation OpenCode

# Official install script
curl -fsSL https://opencode.ai/install | bash

# npm
npm install -g opencode-ai

# pnpm
pnpm install -g opencode-ai

# bun
bun install -g opencode-ai

# macOS / Linux Homebrew tap
brew install anomalyco/tap/opencode

# Verify
opencode --version
opencode

Full docs: opencode.ai/docs

Inside the TUI, run /connect, choose Other, set provider id to infronai, then paste the Infron API key. Alternatively use INFRON_API_KEY through environment variables.​​

Infron model discovery

open https://infron.ai/models

curl -sL --noproxy '*' 'https://infron.ai/llms-full.txt' | less

curl -sL --noproxy '*' 'https://infron.ai/llms-full.txt' \
  | rg -n 'gpt-5|claude|gemini|deepseek|qwen|kimi|glm'

opencode.json setup

By default, the customer provider configuration in Opencode enables only text‑chat capabilities. To enable the full range of model features (such as multimodal file inputs), you must manually add the following configuration items to the configuration file.

cd ~/.config/opencode/

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "infronai": {
      "name": "Infron AI",
      "npm": "@ai-sdk/openai-compatible",
      "models": {
        "openai/gpt-5.2": {
          "name": "GPT-5.2",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text", "image"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 400000,
            "output": 128000
          }
        },
        "openai/gpt-5-mini": {
          "name": "GPT-5 Mini",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text", "image"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 400000,
            "output": 128000
          }
        },
        "anthropic/claude-opus-4.8": {
          "name": "Claude Opus 4.8",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text", "image", "pdf"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 200000,
            "output": 32000
          }
        },
        "anthropic/claude-opus-4.6": {
          "name": "Claude Opus 4.6",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text", "image", "pdf"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 200000,
            "output": 32000
          }
        },
        "anthropic/claude-sonnet-4.5": {
          "name": "Claude Sonnet 4.5",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2025-09-29",
          "modalities": {
            "input": ["text", "image", "pdf"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 200000,
            "output": 32000
          }
        },
        "google/gemini-3-flash-preview": {
          "name": "Gemini 3 Flash Preview",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2025-11-01",
          "modalities": {
            "input": ["text", "image", "pdf"],
            "output": ["text"]
          },
          "cost": {
            "input": 0.5,
            "output": 3
          },
          "limit": {
            "context": 1000000,
            "output": 65535
          }
        },
        "google/gemini-2.5-flash": {
          "name": "Gemini 2.5 Flash",
          "attachment": true,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2025-06-01",
          "modalities": {
            "input": ["text", "image", "pdf"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 1000000,
            "output": 65535
          }
        },
        "deepseek/deepseek-v3.2": {
          "name": "DeepSeek V3.2",
          "attachment": false,
          "reasoning": false,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 128000,
            "output": 32000
          }
        },
        "qwen/qwen3-coder-plus": {
          "name": "Qwen3 Coder Plus",
          "attachment": false,
          "reasoning": false,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 128000,
            "output": 32000
          }
        },
        "moonshotai/kimi-k2-0905": {
          "name": "Kimi K2 0905",
          "attachment": false,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2025-09-05",
          "modalities": {
            "input": ["text"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 128000,
            "output": 32000
          }
        },
        "z-ai/glm-5": {
          "name": "GLM-5",
          "attachment": false,
          "reasoning": true,
          "tool_call": true,
          "temperature": true,
          "release_date": "2026-06-01",
          "modalities": {
            "input": ["text"],
            "output": ["text"]
          },
          "cost": {
            "input": 0,
            "output": 0
          },
          "limit": {
            "context": 128000,
            "output": 32000
          }
        }
      },
      "options": {
        "baseURL": "https://llm.onerouter.pro/v1",
        "apiKey": "{env:INFRON_API_KEY}"
      }
    }
  }
}

After completing the configuration, you can start the Opencode CLI.

Basic Usage

Run opencode in a repo to init: It prompts project context, then use slash commands in the TUI.​

• /connect: Link Infron (auto-detects env vars).

• /models: List/select (e.g., Claude 3.5 Sonnet or Gemini 3 Flash).

• /init: Scans repo, suggests plan (e.g., "Analyze main.rs and create layers").

• Core flow: /plan for outline, /build to generate/run code, /improve for refinements.