Run coding agents on open-weight models

​

Before you start

• A key with the chat:write scope and a funded API wallet. See Before you start in the chat completions guide.
• The key in the HEDRA_KEY environment variable of the terminal that starts the agent:

export HEDRA_KEY="<key_id>:<secret>"

​

Choose a model

​

Connect an agent

npm install -g @openai/codex

model = "zai-org/glm-5.3"
model_provider = "hedra"

[features]
apps = false

[model_providers.hedra]
name = "Hedra"
base_url = "https://api.hedra.com/v3"
env_key = "HEDRA_KEY"

codex --profile hedra

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

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "hedra": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Hedra",
      "options": {
        "baseURL": "https://api.hedra.com/v3",
        "apiKey": "{env:HEDRA_KEY}"
      },
      "models": {
        "zai-org/glm-5.3": { "name": "GLM-5.3" },
        "zai-org/glm-5.3-flash": { "name": "GLM-5.3 Flash" },
        "moonshotai/kimi-k3": { "name": "Kimi K3" },
        "deepseek-ai/deepseek-v4-pro-0813": { "name": "DeepSeek V4 Pro 0813" },
        "deepseek-ai/deepseek-v4.1-flash": { "name": "DeepSeek V4.1 Flash" }
      }
    }
  }
}

opencode --model hedra/zai-org/glm-5.3

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

{
  "providers": {
    "hedra": {
      "baseUrl": "https://api.hedra.com/v3",
      "api": "openai-completions",
      "apiKey": "$HEDRA_KEY",
      "compat": { "supportsStore": false },
      "models": [
        { "id": "zai-org/glm-5.3" },
        { "id": "zai-org/glm-5.3-flash" },
        { "id": "moonshotai/kimi-k3" },
        { "id": "deepseek-ai/deepseek-v4-pro-0813" },
        { "id": "deepseek-ai/deepseek-v4.1-flash" }
      ]
    }
  }
}

pi --provider hedra --model zai-org/glm-5.3

​

Keep sessions inexpensive

• Turn off the MCP servers a session does not need. Each MCP server adds its tool definitions to every request. In Codex, codex mcp list prints your servers’ names, and -c mcp_servers.<name>.enabled=false turns one off for the session:
  codex --profile hedra -c mcp_servers.linear.enabled=false
  
  In OpenCode, set "mcp": { "linear": { "enabled": false } } in opencode.json. By default, Pi adds no MCP tool definitions to the prompt.
• Keep AGENTS.md focused. Codex, OpenCode and Pi send the repository’s AGENTS.md with every request.
• Leave Claude Code’s files out of OpenCode. OpenCode also reads Claude Code’s instructions and skills from ~/.claude into its prompt. Set OPENCODE_DISABLE_CLAUDE_CODE=1 to leave them out.

curl "https://api.hedra.com/v3/usage?start=2026-09-30T21:00:00Z&group_by=model" \
  -H "Authorization: Key $HEDRA_KEY"

​

Troubleshooting

• Codex prints Model metadata for zai-org/glm-5.3 not found. Codex has no metadata for Hedra’s models, and the session runs normally without it.
• A 401 response. Set HEDRA_KEY in the terminal that starts the agent, and restart the agent.
• A 402 response. Your API wallet’s balance cannot cover the request. Add funds and send the message again.