Skip to content

Use Claude Code with your ChatGPT, Kimi, Cursor or Grok subscription via a local Anthropic-compatible proxy

Rust

docs: scope the Codex tier override to the Messages route

Koichi Shiraishi643b1153e01c
diff --git a/README.md b/README.md
index c8993e0..0752ca3 100644
--- a/README.md
+++ b/README.md
@@ -89,7 +89,7 @@ The opt-in Images API returns base64 image data and consumes the signed-in accou
| Provider | Account | Model selection |
| ------------ | ------------------------------ | ----------------------------------------------- |
-| Codex | ChatGPT Plus or Pro | Registered `gpt-*` models and `-fast` variants |
+| Codex | ChatGPT Plus or Pro | Registered `gpt-*` models, `-fast`/`-ultrafast` |
| Kimi | kimi.com with Kimi Code access | `kimi-for-coding` and aliases |
| Grok | grok.com | Registered Grok models |
| OpenCode Go | OpenCode Go subscription | Non-conflicting IDs and `opencode-go/<model-id>` |
diff --git a/docs/src/content/docs/providers/codex.md b/docs/src/content/docs/providers/codex.md
index d1dc7a9..d446a21 100644
--- a/docs/src/content/docs/providers/codex.md
+++ b/docs/src/content/docs/providers/codex.md
@@ -34,7 +34,7 @@ Append `-fast` to any registered Codex model to request `service_tier: "priority
Append `-ultrafast` to a model that offers the ultrafast tier to request `service_tier: "ultrafast"`. Only `gpt-6-astra` offers it today, so `gpt-6-astra-ultrafast` is the one ultrafast ID.
-`CCP_CODEX_SERVICE_TIER` or `codex.serviceTier` takes precedence over either suffix. A forced `ultrafast` applies to models that offer it, and the proxy requests `priority` for the others.
+On `/v1/messages`, `CCP_CODEX_SERVICE_TIER` or `codex.serviceTier` takes precedence over either suffix. A forced `ultrafast` applies to models that offer it, and the proxy requests `priority` for the others. The OpenAI-compatible routes use only the suffix or, on `/v1/responses`, the request's own `service_tier`.
## Reasoning
diff --git a/docs/src/content/docs/reference/configuration.md b/docs/src/content/docs/reference/configuration.md
index 9b96c72..84a3c64 100644
--- a/docs/src/content/docs/reference/configuration.md
+++ b/docs/src/content/docs/reference/configuration.md
@@ -106,7 +106,7 @@ Proxy URLs may use `http`, `https`, `socks4`, `socks4a`, `socks5`, or `socks5h`.
| `CCP_CODEX_EFFORT` | `codex.effort` | unset | Forces `none`, `low`, `medium`, `high`, `xhigh`, or `max`. |
| `CCP_COMPACT_EFFORT` | none | `low` | Caps Codex reasoning effort for Claude Code summary compaction requests. `off` disables the cap and `none` removes reasoning. |
| `CCP_CODEX_REASONING_SUMMARY` | `codex.reasoningSummary` | unset | Overrides summary mode. `off` and `none` suppress summaries. |
-| `CCP_CODEX_SERVICE_TIER` | `codex.serviceTier` | unset | Forces `fast` or `priority`, `ultrafast`, or `flex`. Fast is sent as `priority`. Ultrafast is sent as `priority` to models that do not offer it. |
+| `CCP_CODEX_SERVICE_TIER` | `codex.serviceTier` | unset | Forces `fast`, `priority`, `ultrafast`, or `flex` on `/v1/messages` requests. Fast is sent as `priority`. Ultrafast is sent as `priority` to models that do not offer it. |
| `CCP_CODEX_BASE_URL` | `codex.baseUrl` | ChatGPT Codex Responses URL | Changes the Codex endpoint. |
| `CCP_CODEX_TRANSPORT` | `codex.transport` | `websocket` | Selects `websocket`, `http`, or `auto`. |
| `CCP_CODEX_HEADER_TIMEOUT_MS` | `codex.headerTimeoutMs` | `300000` | Sets how long an HTTP-transport request waits for the Codex response headers. Values below `1000` are ignored. |
diff --git a/docs/src/content/docs/using/models-and-routing.md b/docs/src/content/docs/using/models-and-routing.md
index 6ca4950..80f9069 100644
--- a/docs/src/content/docs/using/models-and-routing.md
+++ b/docs/src/content/docs/using/models-and-routing.md
@@ -41,7 +41,7 @@ Every registered Codex model also has a local `-fast` form. The proxy removes `-
Models that offer the ultrafast tier also have a local `-ultrafast` form, which requests the ultrafast service tier. Today that is `gpt-6-astra-ultrafast` only. An `-ultrafast` name on any other model is not a registered ID.
-A configured `codex.serviceTier` or `CCP_CODEX_SERVICE_TIER` override wins over both suffixes. When the forced tier is `ultrafast` and the model does not offer it, the proxy requests priority instead.
+For Claude Code requests on `/v1/messages`, a configured `codex.serviceTier` or `CCP_CODEX_SERVICE_TIER` override wins over both suffixes. When the forced tier is `ultrafast` and the model does not offer it, the proxy requests priority instead.
## The `[1m]` hint