We're live on Product Hunt todaysupport our launch
OpenCodeOpenCode + General Compute

Use your $200 free credit with OpenCode.

Point OpenCode at General Compute's OpenAI-compatible API and run coding agents on purpose-built inference hardware. You can do the setup by hand or hand the prompts below to an agent.

Step 1

Install or open OpenCode

Install OpenCode, then start the terminal UI with opencode or the browser UI with opencode web.

# Install OpenCode
curl -fsSL https://opencode.ai/install | bash

# Or install with npm
npm install -g opencode-ai

# Optional browser UI
opencode web
Step 2

Get a General Compute API key

Create an account at app.generalcompute.com. New accounts receive $200 in free credit. If you want an agent to handle the signup flow, copy this prompt:

Sign me up for a General Compute API account and get an API key. Use https://docs.generalcompute.com/agent-signup for the signup flow. New accounts receive $200 in free credit. When you finish, return the API key and do not commit it to the repo.

Keep the key out of source control. Replace <key> in the config below with your API key.

Step 3

Add General Compute as a provider

General Compute is not a listed OpenCode provider yet. Update or create ~/.config/opencode/opencode.json with this custom OpenAI-compatible provider config, replacing <key> with your API key.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "myprovider": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "General Compute",
      "options": {
        "baseURL": "https://api.generalcompute.com/v1",
        "apiKey": "<key>"
      },
      "models": {
        "minimax-m2.7": {
          "contextWindow": 160000
        },
        "deepseek-v3.2": {
          "contextWindow": 32000
        },
        "deepseek-v3.1": {
          "contextWindow": 128000
        }
      }
    }
  }
}
Step 4

Let an agent do the wiring

If you already have an agent with file-system access, hand it this prompt. It should update or create the global OpenCode config and replace the placeholder API key before starting OpenCode.

Configure OpenCode to use General Compute.

1. Update or create ~/.config/opencode/opencode.json.
2. Replace "<key>" in the JSON below with my General Compute API key.
3. Keep the provider id "myprovider" unless I ask for a different local alias.
4. General Compute is not a listed OpenCode provider yet, so use the OpenAI-compatible custom provider package.
5. Start OpenCode and run /models so I can verify the provider appears.

Use this exact file content:
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "myprovider": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "General Compute",
      "options": {
        "baseURL": "https://api.generalcompute.com/v1",
        "apiKey": "<key>"
      },
      "models": {
        "minimax-m2.7": {
          "contextWindow": 160000
        },
        "deepseek-v3.2": {
          "contextWindow": 32000
        },
        "deepseek-v3.1": {
          "contextWindow": 128000
        }
      }
    }
  }
}
Step 5

Verify models and run a test

Start OpenCode, run /models, and select a General Compute model. These are good starting points:

ModelUse

minimax-m2.7

MiniMax M2.7

Main recommendation for OpenCode on General Compute.

deepseek-v3.2

DeepSeek V3.2

Alternate for coding and tool-heavy sessions.

deepseek-v3.1

DeepSeek V3.1

Longer-context DeepSeek option.

curl https://api.generalcompute.com/v1/chat/completions \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.7",
    "messages": [{"role": "user", "content": "Hello from OpenCode"}],
    "stream": true
  }'

Need help with the config?

Reach out at founders@generalcompute.com or open the full General Compute docs.

ModeHumanAgent
OpenCode Integration | General Compute | General Compute