Coding tools

Any coding tool that lets you set an OpenAI or Anthropic base URL can run on Helipod models. You pay per token from your AI balance, in Rupiah, with the same key for every tool.

Create a key under AI Gateway → API keys and keep it in an environment variable:

export HELIPOD_AI_KEY=hel_ai_your_key

Pick a model from GET /v1/models or Models & pricing in the dashboard. For agentic coding, start with a larger model (glm-5.3, kimi-k3, deepseek-v4-pro) and use a fast one (deepseek-v4.1-flash, glm-5.3-flash) for background tasks.

CodexCopy Anchor Link

Codex talks to the Responses API. Add Helipod as a model provider:

model = "glm-5.3"
model_provider = "helipod"

[model_providers.helipod]
name = "Helipod AI Gateway"
base_url = "https://ai.helipod.io/v1"
env_key = "HELIPOD_AI_KEY"
wire_api = "responses"

Then run codex as usual. To keep your OpenAI login as the default and use Helipod only sometimes, leave out the first two lines and start Codex with codex -c model_provider=helipod -m glm-5.3.

Codex's shell, patch and MCP tools all work, including the Helipod MCP server. Codex may print that it has no metadata for the model; that is only a notice.

Claude CodeCopy Anchor Link

Claude Code speaks the Anthropic format:

export ANTHROPIC_BASE_URL=https://ai.helipod.io
export ANTHROPIC_AUTH_TOKEN=$HELIPOD_AI_KEY
export ANTHROPIC_MODEL=glm-5.3
export ANTHROPIC_DEFAULT_HAIKU_MODEL=deepseek-v4.1-flash   # background tasks
claude

See Anthropic compatible for details.

opencodeCopy Anchor Link

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "helipod": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Helipod AI Gateway",
      "options": {
        "baseURL": "https://ai.helipod.io/v1",
        "apiKey": "{env:HELIPOD_AI_KEY}"
      },
      "models": {
        "glm-5.3": { "name": "GLM-5.3" },
        "kimi-k3": { "name": "Kimi K3" },
        "deepseek-v4.1-flash": { "name": "DeepSeek V4.1 Flash" }
      }
    }
  }
}

Choose the model with /models in opencode, or run opencode run -m helipod/glm-5.3 "…".

Cline, Roo Code and Kilo CodeCopy Anchor Link

In the extension's settings:

Set the context window and output limit to the model's values from Models & pricing, so the extension does not send more than the model accepts.

ContinueCopy Anchor Link

models:
  - name: GLM-5.3 (Helipod)
    provider: openai
    model: glm-5.3
    apiBase: https://ai.helipod.io/v1
    apiKey: ${{ secrets.HELIPOD_AI_KEY }}
    roles: [chat, edit, apply]

AiderCopy Anchor Link

export OPENAI_API_BASE=https://ai.helipod.io/v1
export OPENAI_API_KEY=$HELIPOD_AI_KEY
aider --model openai/glm-5.3

CursorCopy Anchor Link

In Settings → Models, enter your hel_ai_… key as the OpenAI API key, turn on Override OpenAI Base URL with https://ai.helipod.io/v1, and add the model ids you want (for example glm-5.3). Which Cursor features use custom models depends on your Cursor plan.

Other toolsCopy Anchor Link

Anything built on the OpenAI or Anthropic SDKs works when you can change the base URL and the key:

• OpenAI-style: base URL https://ai.helipod.io/v1, key in Authorization: Bearer.
• Anthropic-style: base URL https://ai.helipod.io, key in x-api-key or Authorization: Bearer.

Tools that only talk to one vendor's own API (for example Gemini CLI) cannot be pointed at the gateway.

TipsCopy Anchor Link

• Long agent sessions cost tokens fast. Each turn resends the conversation. Cached input is billed at the lower cached price where the model supports caching; check Usage in the dashboard and set a monthly spend limit on the key.
• One key per tool. Revoke one without breaking the others, and see each tool's spend separately.
• Errors. 402 means the AI balance ran out (turn on auto top-up), 429 means slow down; see Limits and errors.