Codex CLI (gateway)

Route Codex CLI’s LLM calls through the Respan gateway for automatic logging, caching, and model switching. Only your RESPAN_API_KEY is needed.

Setup

Install Codex CLI

$ npm install -g @openai/codex

Set environment variable

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Configure Codex

Add to ~/.codex/config.toml (user-level) or .codex/config.toml (project-level):

1 model = "openai/gpt-5.5"  # provider prefix required for Codex CLI
2 model_provider = "respan"
3 
4 [model_providers.respan]
5 name = "Respan Gateway"
6 base_url = "https://api.respan.ai/api/"
7 wire_api = "responses"
8 env_key = "RESPAN_API_KEY"

env_key is the name of the environment variable that holds your API key, not the actual key. The wire_api = "responses" setting tells Codex to use the HTTP Responses API instead of WebSockets, which the gateway supports.

Run Codex

$ codex "your prompt"

All LLM calls now route through Respan.

Switch models

Change the model parameter in ~/.codex/config.toml to use any supported model.

1 model = "openai/gpt-5.5"
2 # model = "openai/claude-sonnet-4-5-20250929"
3 # model = "openai/gemini-2.5-flash"

See the full model list.

1	model = "openai/gpt-5.5" # provider prefix required for Codex CLI
2	model_provider = "respan"
3
4	[model_providers.respan]
5	name = "Respan Gateway"
6	base_url = "https://api.respan.ai/api/"
7	wire_api = "responses"
8	env_key = "RESPAN_API_KEY"

1	model = "openai/gpt-5.5"
2	# model = "openai/claude-sonnet-4-5-20250929"
3	# model = "openai/gemini-2.5-flash"