Skip to content

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

Rust

docs: describe the Codex ultrafast tier and where it applies

Koichi Shiraishi8a6a70c347ca
diff --git a/docs/src/content/docs/providers/choosing-a-provider.md b/docs/src/content/docs/providers/choosing-a-provider.md
index 401dbac..4ba64de 100644
--- a/docs/src/content/docs/providers/choosing-a-provider.md
+++ b/docs/src/content/docs/providers/choosing-a-provider.md
@@ -7,7 +7,7 @@ One `serve` process supports every provider. Choose based on the account you hav
| Provider | Account | Upstream protocol | Model selection | Notable capabilities |
| --- | --- | --- | --- | --- |
-| [Codex](/providers/codex/) | ChatGPT Plus or Pro | OpenAI Responses over WebSocket or HTTP SSE | Named Codex catalog, `-fast` variants | Function tools, image input, hosted web search, reasoning summaries, optional native Responses route |
+| [Codex](/providers/codex/) | ChatGPT Plus or Pro | OpenAI Responses over WebSocket or HTTP SSE | Named Codex catalog, `-fast` and `-ultrafast` variants | Function tools, image input, hosted web search, reasoning summaries, optional native Responses route |
| [Kimi](/providers/kimi/) | kimi.com with Kimi Code access | OpenAI-style chat completions | `kimi-for-coding` and aliases | Function tools, reasoning, image and video input |
| [Grok](/providers/grok/) | grok.com | Responses API | `grok-composer-2.5-fast`, `grok-4.5`, `grok-4.6` | Function tools, reasoning, web search, X search, citations |
| [OpenCode Go](/providers/opencode-go/) | OpenCode Go subscription | OpenAI-compatible Chat Completions, OpenAI Responses, or Anthropic-compatible Messages | Non-conflicting bare IDs and `opencode-go/<model-id>` forms | Curated models tested and benchmarked for coding-agent use |
diff --git a/docs/src/content/docs/providers/codex.md b/docs/src/content/docs/providers/codex.md
index e43f8ce..d1dc7a9 100644
--- a/docs/src/content/docs/providers/codex.md
+++ b/docs/src/content/docs/providers/codex.md
@@ -30,7 +30,11 @@ Use `claude-code-proxy models` as the current catalog. Model access depends on y
Claude-style aliases map to Codex models: `haiku` and `claude-haiku-*` to `gpt-6-luna`, `sonnet` and `claude-sonnet-*` to `gpt-5.6-terra`, and `opus`, `fable`, `claude-opus-*` (including `claude-opus-5-5`), and `claude-fable-*` to `gpt-6-sol`.
-Append `-fast` to any registered Codex model to request `service_tier: "priority"`. For example, `gpt-6-sol-fast` selects `gpt-6-sol` with fast service. `CCP_CODEX_SERVICE_TIER` or `codex.serviceTier` takes precedence.
+Append `-fast` to any registered Codex model to request `service_tier: "priority"`. For example, `gpt-6-sol-fast` selects `gpt-6-sol` with fast service.
+
+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.
## Reasoning
diff --git a/docs/src/content/docs/reference/configuration.md b/docs/src/content/docs/reference/configuration.md
index 28a2ec4..9b96c72 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`, or `flex`. Fast is sent as `priority`. |
+| `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_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 77c4ce6..6ca4950 100644
--- a/docs/src/content/docs/using/models-and-routing.md
+++ b/docs/src/content/docs/using/models-and-routing.md
@@ -9,7 +9,7 @@ The model ID in each request selects its provider. One proxy listener can serve
| Pattern | Provider |
| --- | --- |
-| Registered `gpt-*` IDs and their `-fast` forms | Codex |
+| Registered `gpt-*` IDs and their `-fast` and `-ultrafast` forms | Codex |
| `kimi-for-coding`, `kimi-k2.6`, `k2.6` | Kimi |
| `grok-composer-2.5-fast`, `grok-4.5`, `grok-4.6` | Grok |
| Non-conflicting registered OpenCode Go IDs and every `opencode-go/<model-id>` | OpenCode Go |
@@ -37,7 +37,11 @@ curl http://127.0.0.1:18765/v1/models
## Codex fast mode
-Every registered Codex model also has a local `-fast` form. The proxy removes `-fast` from the upstream model and requests the priority service tier. A configured `codex.serviceTier` or `CCP_CODEX_SERVICE_TIER` override wins.
+Every registered Codex model also has a local `-fast` form. The proxy removes `-fast` from the upstream model and requests the priority service tier.
+
+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.
## The `[1m]` hint