--- title: Codex App | RunAPI description: Use RunAPI as the model provider in Codex App, choose a Responses-compatible model, and verify the connection. url: https://runapi.ai/docs/resources/tool-integrations/codex-app.md canonical: https://runapi.ai/docs/resources/tool-integrations/codex-app locale: en --- > HTML version: https://runapi.ai/docs/resources/tool-integrations/codex-app > Site index for agents: https://runapi.ai/llms.txt # Codex App ## Overview Codex is available in the ChatGPT desktop app for Windows and macOS. This guide points the local Codex App at RunAPI's OpenAI-compatible Responses endpoint, selects a RunAPI model, and verifies the connection. This changes the model provider used to generate responses and code. It does not add RunAPI tools. [Hosted MCP](https://runapi.ai/docs/resources/mcp/hosted.md) is a separate integration with its own client and authentication requirements. ## Before you begin * Install the current [ChatGPT desktop app][1], sign in, and open Codex at least once. * Create a dedicated standard RunAPI API key by following the [Authentication Guide](https://runapi.ai/docs/guides/authentication.md). Do not commit the key to a repository. * From the [Model Catalog](https://runapi.ai/models), copy the exact identifier of a model that supports the Responses API. [1]: https://developers.openai.com/codex/app These steps configure local Codex clients that read your user-level configuration. They do not configure hosted Codex cloud tasks. ## Save the API key Desktop apps may not inherit environment variables from your shell. Create or edit `~/.codex/.env` and add the key on its own line: ```dotenv export RUNAPI_API_KEY=YOUR_RUNAPI_API_KEY ``` Keep this file outside your repositories. On macOS and Linux, restrict it to your user account: ```shell chmod 600 ~/.codex/.env ``` ## Configure RunAPI Open the user-level `~/.codex/config.toml`. Merge the following values into the existing file; do not replace unrelated settings or add a second copy of an existing top-level key: ```toml model = "YOUR_RUNAPI_MODEL_ID" model_provider = "runapi" [model_providers.runapi] name = "RunAPI" base_url = "https://runapi.ai/v1" env_key = "RUNAPI_API_KEY" wire_api = "responses" ``` Provider and authentication settings must be user-level. Codex ignores `model_provider` and `model_providers` in a project's `.codex/config.toml`. The TOML stores only the environment variable name; the API key remains in `~/.codex/.env`. The `base_url` is the API root, not an operation URL. With `wire_api = "responses"`, Codex sends `POST /v1/responses`. See OpenAI's [custom model provider configuration][1] for the provider contract. [1]: https://developers.openai.com/codex/config-advanced#custom-model-providers ## Choose a model Replace `YOUR_RUNAPI_MODEL_ID` with the exact identifier copied from the [Model Catalog](https://runapi.ai/models). Select a model that exposes the Responses API; support for Chat Completions alone is not sufficient for this configuration. When you change `model`, completely restart the app and start a new task. An existing task may retain the model and provider with which it started. ## Restart and verify 1. Completely quit and reopen the ChatGPT desktop app. 2. Open Codex and start a new task in a repository. 3. Send a short prompt such as `Describe this repository in one sentence.` 4. Confirm that Codex returns a normal response and that RunAPI records a `POST /v1/responses` request for the selected model. The first verification should stay short so configuration errors are easy to separate from task-specific behavior. ## Add RunAPI tools The model provider above routes Codex inference through RunAPI. MCP is separate: it can let supported clients call RunAPI tools for model discovery, account information, and supported task workflows. The [Hosted MCP guide](https://runapi.ai/docs/resources/mcp/hosted.md) documents the currently supported client and authentication requirements. Codex-specific Hosted MCP authentication has not been verified, so this page does not provide Codex MCP setup steps. Do not replace the model-provider configuration with an MCP server entry; the two integrations serve different purposes. ## Troubleshoot * **Codex still uses the previous provider:** confirm the file is `~/.codex/config.toml`, remove duplicate `model` or `model_provider` keys, completely restart the app, and start a new task. * **`RUNAPI_API_KEY` is missing:** confirm the key is in `~/.codex/.env`, not only in a terminal profile, then restart the app. * **Authentication fails:** create or rotate a standard key through the [Authentication Guide](https://runapi.ai/docs/guides/authentication.md). Do not paste the key into `config.toml` or support logs. * **The request returns `404`:** set `base_url` to `https://runapi.ai/v1`, not `https://runapi.ai/v1/responses`. * **The model is unavailable or rejects a field:** copy the exact identifier again and confirm that the model supports the Responses API and the requested capability. * **Codex selects a different model:** check trusted project `.codex/config.toml` files for a `model` override. Project config can select a model even though it cannot replace the user-level provider. * **The CLI works but the app fails:** check `~/.codex/.env`, then fully restart the app. GUI applications may not read variables exported only by your shell. * **A cloud task does not use RunAPI:** this local configuration applies to local Codex clients; hosted cloud tasks do not read files from your computer. ## Remove RunAPI 1. Remove the RunAPI `model`, `model_provider`, and `[model_providers.runapi]` values from `~/.codex/config.toml`, or restore the provider values you used previously. 2. Remove `RUNAPI_API_KEY` from `~/.codex/.env` if no other local tool uses it. 3. Completely restart the app and start a new task. 4. Revoke the dedicated key in RunAPI when it is no longer needed. ## Next steps Use the [LLM API Quickstart](https://runapi.ai/docs/guides/llm-api/quickstart.md) for shared protocol behavior and the [Responses API Reference](https://runapi.ai/docs/api/openai/responses.md) for exact request and response fields. Continue with the [Model Catalog](https://runapi.ai/models), [Authentication Guide](https://runapi.ai/docs/guides/authentication.md), or [Hosted MCP](https://runapi.ai/docs/resources/mcp/hosted.md) as needed. --- ## More from RunAPI - [Home](https://runapi.ai/.md) - [Models](https://runapi.ai/models.md) - [AI Video API Comparison](https://runapi.ai/ai-video-api-comparison.md) - [OpenClaw Integration](https://runapi.ai/openclaw.md) - [Best API for OpenClaw](https://runapi.ai/best-api-for-openclaw.md) - [OpenClaw Image Generation](https://runapi.ai/openclaw-image-generation.md) - [Hermes Agent Integration](https://runapi.ai/hermes-agent.md) - [Pricing](https://runapi.ai/pricing.md) - [Claude API Pricing](https://runapi.ai/claude-api-pricing.md) - [ChatGPT API Pricing](https://runapi.ai/chatgpt-api-pricing.md) - [OpenAI API Pricing](https://runapi.ai/openai-api-pricing.md) - [Gemini API Pricing](https://runapi.ai/gemini-api-pricing.md) - [Claude Code Pricing](https://runapi.ai/claude-code-pricing.md) - [Claude Code API](https://runapi.ai/claude-code-api.md) - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Claude Max vs API](https://runapi.ai/claude-max-vs-api.md) - [Requesty Alternative](https://runapi.ai/requesty-alternative.md) - [Docs](https://runapi.ai/docs/guides) - [SDK](https://runapi.ai/sdk.md) - [Skills](https://runapi.ai/skills.md) - [MCP Server](https://runapi.ai/mcp.md) - [CLI](https://runapi.ai/cli.md) - [Feedback](https://runapi.ai/) - [Contact](mailto:support@runapi.ai) - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "TechArticle", "headline": "Codex App", "description": "Use RunAPI as the model provider in Codex App, choose a Responses-compatible model, and verify the connection.", "url": "https://runapi.ai/docs/resources/tool-integrations/codex-app", "mainEntityOfPage": "https://runapi.ai/docs/resources/tool-integrations/codex-app" } ] ```