diff --git a/README.md b/README.md
index e5690d7d..1abae778 100644
--- a/README.md
+++ b/README.md
@@ -78,6 +78,25 @@ export OPENAI_API_KEY="your-api-key-here"
 >
 > The CLI will automatically load variables from `.env` (via `dotenv/config`).
 
+> **Note:** Codex also allows you to use other providers that support the OpenAI Chat Completions API. You can set the provider in the config file or use the `--provider` flag.
+>
+> The possible options for `--provider` are:
+>
+> - openai (default)
+> - openrouter
+> - gemini
+> - ollama
+> - mistral
+> - deepseek
+> - xai
+> - groq
+>
+> If you use a provider other than OpenAI, you will need to set the API key for the provider in the config file or in the environment variable as:
+>
+> ```shell
+> export <provider>_API_KEY="your-api-key-here"
+> ```
+
 Run interactively:
 
 ```shell
diff --git a/codex-cli/src/cli.tsx b/codex-cli/src/cli.tsx
index d716a07b..65147b9e 100644
--- a/codex-cli/src/cli.tsx
+++ b/codex-cli/src/cli.tsx
@@ -54,6 +54,7 @@ const cli = meow(
   Options
     -h, --help                      Show usage and exit
     -m, --model <model>             Model to use for completions (default: o4-mini)
+    -p, --provider <provider>       Provider to use for completions (default: openai)
     -i, --image <path>              Path(s) to image files to include as input
     -v, --view <rollout>            Inspect a previously saved rollout instead of starting a session
     -q, --quiet                     Non-interactive mode that only prints the assistant's final output