Add Codex CLI integration guide

README.md

@@ -15,6 +15,7 @@ Each guide walks through installation, configuration, and model selection so you
 | OpenClaw | [openclaw.md](./openclaw.md) | [YouTube](https://youtu.be/HxIAYOQT90Q) | [edenai.co/integrations/openclaw](https://www.edenai.co/integrations/openclaw) |
 | OpenCode | [opencode.md](./opencode.md) | [YouTube](https://youtu.be/OYHRY5rblz0) | [edenai.co/integrations/opencode](https://www.edenai.co/integrations/opencode) |
 | Cline | [cline.md](./cline.md) | [YouTube](https://youtu.be/_M8PwHSwgMQ) | [edenai.co/integrations/cline](https://www.edenai.co/integrations/cline) |
+| Codex | [codex.md](./codex.md) | [YouTube](https://youtu.be/sVLPbencnnM) | [edenai.co/integrations/codex](https://www.edenai.co/integrations/codex) |
 
 More integrations are added regularly. Open an issue if there's a tool you'd like us to cover.
 

codex.md

@@ -0,0 +1,148 @@
+# Codex + Eden AI
+
+Connect [OpenAI Codex CLI](https://github.com/openai/codex) to Eden AI and route your terminal coding agent through **500+ models** with smart routing, automatic fallbacks, and a single API key.
+
+> Get your Eden AI key at [app.edenai.run](https://app.edenai.run/) → **API Keys**.
+
+Follow this tuto in the same time with our video tuto on [Youtube](https://youtu.be/sVLPbencnnM)
+
+---
+
+## 1. System dependencies
+
+On a fresh Linux machine (Ubuntu / Debian / WSL):
+
+```bash
+sudo apt update
+sudo apt install -y curl git
+```
+
+## 2. Install Node.js
+
+Codex CLI requires **Node.js 22+**.
+
+```bash
+sudo apt install -y nodejs npm
+
+# Verify
+node --version   # v22.x or newer
+```
+
+If the packaged version is too old, install via [nvm](https://github.com/nvm-sh/nvm) or [nodesource](https://github.com/nodesource/distributions).
+
+## 3. Install Codex CLI
+
+```bash
+# Via npm
+npm install -g @openai/codex
+
+# Or via Homebrew (macOS)
+brew install codex
+```
+
+Verify the binary is on your PATH:
+
+```bash
+codex --version
+```
+
+## 4. Add Eden AI as a custom provider
+
+Codex stores its config at `~/.codex/config.toml`. Open it and add the Eden AI provider, then set it as the default with the `@edenai` smart-router model:
+
+```bash
+nano ~/.codex/config.toml
+```
+
+```toml
+model = "@edenai"
+model_provider = "edenai"
+
+[model_providers.edenai]
+name = "Eden AI"
+base_url = "https://api.edenai.run/v3"
+env_key = "EDENAI_API_KEY"
+wire_api = "chat"
+```
+
+Codex reads the API key from the environment variable named in `env_key`. Export your Eden AI key (add this to `~/.bashrc` or `~/.zshrc` to make it permanent):
+
+```bash
+export EDENAI_API_KEY="YOUR_EDEN_AI_API_KEY"
+```
+
+### Why `@edenai`?
+
+`@edenai` is Eden AI's **smart router**. For every request, it automatically picks the best-performing model based on quality, latency, cost and live provider health, so your Codex agent always uses the right model without a config change.
+
+[How smart routing works →](https://www.edenai.co/docs/v3/llms/smart-routing)
+
+## 5. Start Codex
+
+Launch the agent in any project:
+
+```bash
+codex
+```
+
+That's it. Every LLM call now flows through Eden AI, with built-in fallbacks, unified billing, and per-request cost visibility.
+
+---
+
+## Using specific models
+
+`@edenai` handles routing automatically, but you can target a specific model by changing the top-level `model` value to a `provider/model` string:
+
+```toml
+model = "anthropic/claude-sonnet-4-5"
+model_provider = "edenai"
+```
+
+You can also override the model for a single run from the command line:
+
+```bash
+codex -c model='"anthropic/claude-sonnet-4-5"'
+```
+
+Common choices:
+
+| Model | Best for |
+|---|---|
+| `@edenai` | **Default** — smart routing across all providers |
+| `anthropic/claude-sonnet-4-5` | Balanced reasoning |
+| `anthropic/claude-opus-4-7` | Maximum capability |
+| `anthropic/claude-haiku-4-5` | Fast and cheap |
+| `openai/gpt-5` | OpenAI's frontier model |
+| `google/gemini-2.5-pro` | Long context, multimodal |
+
+Browse the full catalog at [app.edenai.run/models](https://app.edenai.run/models).
+
+## Troubleshooting
+
+### `401 Unauthorized`
+Verify your Eden AI key, and confirm the `EDENAI_API_KEY` environment variable is exported in the same shell you launched Codex from. Grab a fresh key at [app.edenai.run → API Keys](https://app.edenai.run/).
+
+### `model not found`
+Ensure the model uses the `provider/model` format (or `@edenai` for the smart router). No bare model names.
+
+### Provider not used
+Confirm both `model_provider = "edenai"` at the top level and the `[model_providers.edenai]` table are present, and that `wire_api` is set to `"chat"`.
+
+### Connection issues
+Confirm the base URL is exactly `https://api.edenai.run/v3` and check Eden AI status at [app-edenai.instatus.com](https://app-edenai.instatus.com/).
+
+## Uninstall
+
+```bash
+npm uninstall -g @openai/codex
+rm -rf ~/.codex
+```
+
+---
+
+## Next steps
+
+- [Smart routing](https://www.edenai.co/docs/v3/llms/smart-routing)
+- [Fallbacks](https://www.edenai.co/docs/v3/llms/fallback)
+- [Eden AI pricing](https://www.edenai.co/pricing)
+- [Codex CLI GitHub](https://github.com/openai/codex)