Codex CLI & Extension Setup (OpenAI API)

Overview

OpenAI's Codex CLI and the Codex VS Code extension talk to a model provider over the Responses API (/v1/responses). ClaudeStore serves that endpoint, so you can drive the OpenAI API through your existing ClaudeStore credits and a single universal key.

Step 1 — Create a universal key

In the dashboard → API keys, create a universal key. It looks likesk-cs4-…. Copy it once — it's shown only at creation.

Step 2 — Switch the tier to Codex

On the universal key, change the upstream selector to ClaudeStore Codex. This routes the key to the OpenAI API. You can switch the same key back to Basic or Pro (Claude models) at any time — no new key needed.

Step 3 — Configure Codex CLI

Codex CLI reads ~/.codex/config.toml. Add ClaudeStore Codex as a model provider that uses the Responses API:

model = "gpt-5.5"
model_provider = "claudestore"

[model_providers.claudestore]
name = "ClaudeStore Codex"
base_url = "https://api3.claudestore.store/v1"
env_key = "CLAUDESTORE_API_KEY"
wire_api = "responses"

Export your universal key as the provider env var, then launch Codex:

export CLAUDESTORE_API_KEY="sk-cs4-your-key"
codex

Step 4 — Codex VS Code extension

The Codex VS Code extension shares the same ~/.codex/config.toml. Once the provider above is set and CLAUDESTORE_API_KEY is exported in your shell environment, the extension picks up ClaudeStore Codex automatically. Select the gpt-5.5 model from the extension's model picker.

Step 5 — Test

You can verify the endpoint directly without the CLI:

curl https://api3.claudestore.store/v1/responses \
  -H "Authorization: Bearer sk-cs4-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "Say hello in 3 words."
  }'

A successful response confirms the key, tier, and endpoint are wired correctly. If you get a model error, run GET /v1/models to confirm the model id.

Troubleshooting

• Unknown model — the key isn't on the Codex tier, or the model id is wrong. Switch the tier and check GET /v1/models.
• 401 / unauthorized — the env var isn't exported in the shell that launched Codex.
• Endpoint not found — make sure the base URL ends in /v1 and the provider uses wire_api = "responses".