Codex CLI

OpenAI. Config reference checked 2026-10-12. Built-in ids openai, ollama, lmstudio are reserved.

Official Codex CLI reads ~/.codex/config.toml. Custom providers use wire_api = responses (the only supported value in the current config reference).

What it’s for

OpenAI’s coding CLI against a local server that implements POST /v1/responses.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: model = plus model_provider = your custom id
API key: env_key on the provider table (placeholder env is fine locally)

Tool calling

Codex agent tools. Completeness against llama.cpp’s Responses translator is not documented here.

Long context

Not documented as a Codex-side window for custom providers.

ROCm / Radeon gotchas

None. llama.cpp documents /v1/responses; LM Studio documents Codex because they implement Responses. Strata Responses support is not documented — treat as TODO.

Hybrid local + cloud

Default is OpenAI / ChatGPT login. Local is a custom model_providers row.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

Codex CLI → llama-server :8080~/.codex/config.toml

model = "qwen"
model_provider = "llama_local"

[model_providers.llama_local]
name = "llama-server"
base_url = "http://127.0.0.1:8080/v1"
wire_api = "responses"
env_key = "LOCAL_NOT_A_SECRET"

Current official wire_api is responses only. Reserved provider ids: openai, ollama, lmstudio. llama.cpp documents POST /v1/responses.

Codex CLI → Strata :8083~/.codex/config.toml

model = "qwen"
model_provider = "llama_local"

[model_providers.llama_local]
name = "Strata"
base_url = "http://127.0.0.1:8083/v1"
wire_api = "responses"
env_key = "LOCAL_NOT_A_SECRET"

Current official wire_api is responses only. llama.cpp documents POST /v1/responses. Strata Responses support is not documented — treat as TODO.