docs(config): clarify openai-compatible providers

README.md

@@ -163,7 +163,7 @@ qwen --version
 code [options] [prompt]
 
 Options:
-  --model <name>        Override the model (gpt-5.1, claude-opus, etc.)
+  --model <name>        Override the model for the active provider (e.g. gpt-5.1)
   --read-only          Prevent file modifications
   --no-approval        Skip approval prompts (use with caution)
   --config <key=val>   Override config values
@@ -174,6 +174,8 @@ Options:
   --version           Show version number
 ```
 
+Note: `--model` only changes the model name sent to the active provider. To use a different provider, set `model_provider` in `config.toml`. Providers must expose an OpenAI-compatible API (Chat Completions or Responses).
+
 &ensp;
 ## Memory & project docs
 
@@ -265,7 +267,7 @@ model_reasoning_summary = "detailed"
 
 - `CODE_HOME`: Override config directory location
 - `OPENAI_API_KEY`: Use API key instead of ChatGPT auth
-- `OPENAI_BASE_URL`: Use alternative API endpoints
+- `OPENAI_BASE_URL`: Use OpenAI-compatible API endpoints (chat or responses)
 - `OPENAI_WIRE_API`: Force the built-in OpenAI provider to use `chat` or `responses` wiring
 
 &ensp;

code-rs/config.md

@@ -22,7 +22,7 @@ model = "o3"  # overrides the default of "gpt-5.1"
 
 ## model_providers
 
-This option lets you override and amend the default set of model providers bundled with Codex. This value is a map where the key is the value to use with `model_provider` to select the corresponding provider.
+This option lets you override and amend the default set of model providers bundled with Codex. This value is a map where the key is the value to use with `model_provider` to select the corresponding provider. Providers must expose an OpenAI-compatible HTTP API (Chat Completions or Responses); native Anthropic/Gemini APIs are not supported directly without a proxy.
 
 For example, if you wanted to add a provider that uses the OpenAI 4o model via the chat completions API, then you could add the following configuration:
 

docs/config.md

@@ -27,7 +27,7 @@ model = "o3"  # overrides the default of "gpt-5.1-codex"
 
 ## model_providers
 
-This option lets you override and amend the default set of model providers bundled with Code. This value is a map where the key is the value to use with `model_provider` to select the corresponding provider.
+This option lets you override and amend the default set of model providers bundled with Code. This value is a map where the key is the value to use with `model_provider` to select the corresponding provider. Providers must expose an OpenAI-compatible HTTP API (Chat Completions or Responses); native Anthropic/Gemini APIs are not supported directly without a proxy.
 
 For example, if you wanted to add a provider that uses the OpenAI 4o model via the chat completions API, then you could add the following configuration:
 
@@ -70,6 +70,20 @@ base_url = "https://api.mistral.ai/v1"
 env_key = "MISTRAL_API_KEY"
 ```
 
+Or a proxy that converts OpenAI-compatible requests to another vendor (e.g., Anthropic or Gemini):
+
+```toml
+model = "claude-opus-4.5"
+model_provider = "claude-proxy"
+
+[model_providers.claude-proxy]
+name = "Claude (proxy)"
+base_url = "http://127.0.0.1:8000/v1"
+env_key = "ANTHROPIC_API_KEY"
+wire_api = "responses"  # or "chat" if your proxy only supports chat-completions
+requires_openai_auth = false
+```
+
 It is also possible to configure a provider to include extra HTTP headers with a request. These can be hardcoded values (`http_headers`) or values read from environment variables (`env_http_headers`):
 
 ```toml