Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
TypeScript a2aai-agentsai-gatewayanthropicclaudeclaude-codeclinecodexcopilotcursordeepseekfree-aigeminikimillm-gatewaymcpopenaiopenai-proxyqwentoken-saver
docs: update Codex CLI profile naming guidance
diegosouzapw717f56bf930d
diff --git a/docs/guides/CODEX-CLI-CONFIGURATION.md b/docs/guides/CODEX-CLI-CONFIGURATION.mdindex 9e37bfc32c..531782cc3d 100644--- a/docs/guides/CODEX-CLI-CONFIGURATION.md+++ b/docs/guides/CODEX-CLI-CONFIGURATION.md@@ -193,7 +193,9 @@ codex -m ds/deepseek-v4-pro -c model_context_window=1000000 -c model_auto_compac## Profiles — named usage profiles-Profiles let you have named configurations for different workflows. Each profile is a file at `~/.codex/profile-<name>.config.toml` that overlays the base `config.toml`.+Profiles let you have named configurations for different workflows. Each profile is a file at `~/.codex/<name>.config.toml` that layers on top of the base `config.toml`.++> **Naming rule (Codex CLI v0.137+):** the file must be named `~/.codex/<name>.config.toml` — **no `profile-` prefix**. The CLI resolves `-p chat` to `~/.codex/chat.config.toml`. If the file is not found, the default silently applies with no error.### How to use@@ -206,14 +208,14 @@ codex -p chat "explain this function"### All available profiles-#### `profile-chat` — no reasoning effort (server default = medium)+#### `chat.config.toml` — no reasoning effort (server default = medium)```tomlmodel = "cx/gpt-5.5"model_provider = "omniroute"# No model_reasoning_effort — uses server default (medium)```-#### `profile-low` / `profile-medium` / `profile-high` / `profile-xhigh`+#### `low.config.toml` / `medium.config.toml` / `high.config.toml` / `xhigh.config.toml````tomlmodel = "cx/gpt-5.5"model_reasoning_effort = "low" # or medium / high / xhigh@@ -221,7 +223,7 @@ model_provider = "omniroute"```Context window is inherited from `config.toml` (400k for gpt-5.5).-#### `profile-deepseek` — DeepSeek V4 Pro, 1M context+#### `deepseek.config.toml` — DeepSeek V4 Pro, 1M context```tomlmodel = "ds/deepseek-v4-pro"model_provider = "omniroute"@@ -232,7 +234,7 @@ model_max_output_tokens = 65536 # practical cap; model max = 384ktool_output_token_limit = 65536```-#### `profile-mistral` — Mistral Large Latest, 256k context+#### `mistral.config.toml` — Mistral Large Latest, 256k context```tomlmodel = "mistral/mistral-large-latest"model_provider = "omniroute"@@ -332,7 +334,7 @@ Auto-generated by the Codex CLI to record acknowledged deprecation warnings. **N| Flag | Short | Effect ||------|-------|--------|| `--model <id>` | `-m` | Overrides `model` for the current invocation |-| `--profile <name>` | `-p` | Loads `~/.codex/profile-<name>.config.toml` |+| `--profile <name>` | `-p` | Loads `~/.codex/<name>.config.toml` || `--config key=value` | `-c` | Overrides any config.toml field || `--enable <feature>` | — | Force-enables a feature flag || `--disable <feature>` | — | Force-disables a feature flag |diff --git a/skills/config-codex-cli/SKILL.md b/skills/config-codex-cli/SKILL.mdindex db75f91d81..8c2daf46c9 100644--- a/skills/config-codex-cli/SKILL.md+++ b/skills/config-codex-cli/SKILL.md@@ -3,7 +3,7 @@ name: config-codex-clidescription: Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.----# /setup-codex-cli — Codex CLI Configuration Workflow+# /config-codex-cli — Codex CLI Configuration WorkflowConfigure the Codex CLI on this machine to use an OmniRoute instance as backend.@@ -179,16 +179,18 @@ wire_api = "responses"## Step 5 — Write profile files-Create each file below in the Codex config directory. If a file already exists, overwrite it.+> **Naming rule (Codex CLI v0.137+):** files must be `~/.codex/<name>.config.toml` — **no `profile-` prefix**. The CLI resolves `-p chat` to `~/.codex/chat.config.toml`. If the file is not found, the default applies silently with no error.-### `profile-chat.config.toml` — no reasoning (server default = medium)+Create each file below in the Codex config directory (`~/.codex/`). If a file already exists, overwrite it.++### `chat.config.toml` — no reasoning (server default = medium)```tomlmodel = "cx/gpt-5.5"model_provider = "omniroute"```-### `profile-low.config.toml`+### `low.config.toml````tomlmodel = "cx/gpt-5.5"@@ -196,7 +198,7 @@ model_reasoning_effort = "low"model_provider = "omniroute"```-### `profile-medium.config.toml`+### `medium.config.toml````tomlmodel = "cx/gpt-5.5"@@ -204,7 +206,7 @@ model_reasoning_effort = "medium"model_provider = "omniroute"```-### `profile-high.config.toml`+### `high.config.toml````tomlmodel = "cx/gpt-5.5"@@ -212,7 +214,7 @@ model_reasoning_effort = "high"model_provider = "omniroute"```-### `profile-xhigh.config.toml`+### `xhigh.config.toml````tomlmodel = "cx/gpt-5.5"@@ -220,7 +222,7 @@ model_reasoning_effort = "xhigh"model_provider = "omniroute"```-### `profile-deepseek.config.toml` — DeepSeek V4 Pro, 1M context+### `deepseek.config.toml` — DeepSeek V4 Pro, 1M context```tomlmodel = "ds/deepseek-v4-pro"@@ -232,7 +234,7 @@ model_max_output_tokens = 65536tool_output_token_limit = 65536```-### `profile-mistral.config.toml` — Mistral Large Latest, 256k context+### `mistral.config.toml` — Mistral Large Latest, 256k context```tomlmodel = "mistral/mistral-large-latest"