Best API & Subscription for OpenAI Codex CLI

To run Codex CLI cost-efficiently, run standardcompute launch codex: Standard Compute's router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), and it serves the OpenAI Responses API (/v1/responses) at https://api.stdcmpt.com/v1, which current Codex CLI releases require for custom providers, on a plan from $19 a month with a $20 compute budget. Compare that with your ChatGPT plan's native Codex allowance, and check the API protocol your installed version supports. Its fixed monthly price includes a finite compute budget; parallel tasks consume that allowance faster.

Light or occasional use

Compare your existing native plan with the cost of a small task on a supported custom provider. An OpenAI-compatible label alone does not establish support for every protocol and feature Codex needs.

Daily use, cost-optimized

Standard Compute sends each Codex step to the cheapest model that can do it, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. It is one fixed monthly bill, so check that its documented integration and monthly compute budget fit your tasks: start with one task before parallel runs and plan for requests stopping at the budget.

API and subscription options for Codex CLI

Prices and allowances can change. OpenCode Go prices were checked against its linked public pages on October 13, 2026, DevPass prices on September 5, 2026; other entries link to current plans without quoting an unverified price. Spot an error? Tell us.

Or configure Codex CLI by hand

model = "standardcompute"
model_provider = "standardcompute"

[model_providers.standardcompute]
name = "Standard Compute"
base_url = "https://api.stdcmpt.com/v1"
env_key = "STANDARD_COMPUTE_API_KEY"
wire_api = "responses"

Then run export STANDARD_COMPUTE_API_KEY=your key, and start codex. The key lives in that environment variable, never in the file.

Setup for one model in Codex CLI: DeepSeek · Kimi K3 · GLM 5.3 · Gemini

Codex CLI questions

Where does the base URL live for Codex CLI with a subscription key: config.toml, an env var or a CLI flag?

In ~/.codex/config.toml, and the key in an environment variable. Add a [model_providers.standardcompute] table with base_url = "https://api.stdcmpt.com/v1", env_key = "STANDARD_COMPUTE_API_KEY" and wire_api = "responses", set model = "standardcompute" and model_provider = "standardcompute" at the top of the file, export STANDARD_COMPUTE_API_KEY and run codex. Current Codex releases only talk to custom providers over the Responses API, which Standard Compute serves at /v1/responses. To skip the file, standardcompute launch codex connects one session after a browser sign-in and leaves your own config untouched. A 404 almost always means base_url is missing /v1 or wire_api is not "responses".