Skip to main content
GoModel is a good fit for Codex because Codex already targets the OpenAI Responses API. Flow: Codex -> GoModel -> OpenAI

​
Before you start

  • Install Codex on your machine.
  • Choose a GoModel master key, for example change-me.
  • Make sure GoModel has the upstream provider key for the models you want to use.

​
1. Run GoModel

Start GoModel with a master key and an OpenAI provider key: 
docker run --rm -p 8080:8080 \
  -e GOMODEL_MASTER_KEY="change-me" \
  -e OPENAI_API_KEY="sk-..." \
  enterpilot/gomodel

​
2. Confirm the Responses API with curl

Before testing Codex itself, you can optionally verify that GoModel answers a normal Responses API request: This step is optional. If you are sure you have configured a valid OPENAI_API_KEY in GoModel, you can skip it and go straight to step 3. 
curl -s http://localhost:8080/v1/responses \
  -H "Authorization: Bearer change-me" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1-mini",
    "input": "Reply with exactly ok",
    "max_output_tokens": 16
  }'
If the gateway is wired correctly, the response will contain ok.

​
3. Configure Codex to use GoModel

Point Codex at GoModel’s standard OpenAI-compatible API: 
export OPENAI_BASE_URL=http://localhost:8080/v1
export OPENAI_API_KEY=change-me
If you keep a Codex provider config file, use a Responses-based provider: 
[model_providers.gomodel]
name = "GoModel"
base_url = "http://localhost:8080/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

​
4. Run a Codex test prompt

codex exec -m gpt-4.1-mini --disable enable_request_compression \
  'Reply with exactly ok and no punctuation.'

​
5. Check the traffic in GoModel

Open the GoModel dashboard audit logs: http://localhost:8080/admin/dashboard/audit This lets you confirm that Codex is reaching GoModel even before full support is finished. From the same dashboard, you can keep following your GoModel traffic and usage as the integration matures.

​
Current status

  • the target integration path is correct: standard http://localhost:8080/v1
  • Codex already uses POST /v1/responses, which is what GoModel should support
  • the missing piece on the tested GoModel instance is request decompression for Content-Encoding: zstd

​
References

​
Validated on March 10, 2026

This guide was validated against:
  • a local GoModel instance on http://localhost:8080
  • Codex CLI 0.113.0
Local validation confirmed:
  • POST /v1/responses returned 200 OK with curl
  • Codex sent requests to POST /v1/responses
  • the tested GoModel instance does not yet accept Codex’s Content-Encoding: zstd request bodies

​
Known issues

In the March 10, 2026 validation, Codex reached the correct GoModel endpoint, but the request failed because Codex compressed the body with zstd. The observed error from GoModel was: 
{"error":{"message":"invalid request body: invalid character '(' looking for beginning of value","type":"invalid_request_error"}}
Workaround: disable request compression in Codex CLI: 
codex exec -m gpt-4.1-mini --disable enable_request_compression \
  'Reply with exactly ok and no punctuation.'