fylorn · Oct 10, 2026 · Oct 10, 2026 · Oct 10, 2026 · Oct 10, 2026 · Oct 10, 2026
diff --git a/src/content/docs-lite/en/claude-code-other-models.md b/src/content/docs-lite/en/claude-code-other-models.md
@@ -10,13 +10,13 @@ ThinkWatch Lite connects Claude Code to a gateway on the same computer, which fo
 
 ## Steps
 
-1. On the Upstreams page, choose **New upstream**. The first step, **Service**, lists the services that can be connected, account sign-ins first and API access after them, with a search box; picking one goes straight to **Connection**:
+1. On the Upstreams page, choose **New upstream**. The first step, **Service**, lists the services in three groups, with a search box; picking one goes straight to **Connection**, which asks only for what that service needs:
    - **DeepSeek** fills in `https://api.deepseek.com/anthropic` and the protocol. Enter the **API key**.
-   - GLM with a key: **Custom**, with `https://open.bigmodel.cn/api/anthropic` or `https://api.z.ai/api/anthropic` as the **Base URL**, **Protocol** set to **Anthropic Messages**, and the **API key**. GLM's OpenAI-compatible address also works from ThinkWatch Lite 2026.10.5, with **Protocol** set to **OpenAI Chat Completions**: `https://api.z.ai/api/paas/v4` or `https://open.bigmodel.cn/api/paas/v4`, and `…/api/coding/paas/v4` on a GLM Coding Plan. Claude Code's requests are then converted, so the Anthropic address is the more direct choice.
-   - GLM with an account: **Z.ai / BigModel account**. Select the **Account service**, tick **Acknowledge the notes above and continue signing in**, choose **Sign in** and authorize in the browser. The app creates an API key named `thinkwatch` on the account and saves the upstream.
+   - GLM with a key: **Z.ai / BigModel**. Choose the **Site**, **Z.ai (international)** or **BigModel (mainland China)**, which sets the Anthropic-compatible address, and enter the **API key**. GLM's OpenAI-compatible address also works from ThinkWatch Lite 2026.10.5, with **Custom** and **Protocol** set to **OpenAI Chat Completions**: `https://api.z.ai/api/paas/v4` or `https://open.bigmodel.cn/api/paas/v4`, and `…/api/coding/paas/v4` on a GLM Coding Plan. Claude Code's requests are then converted, so the Anthropic address is the more direct choice.
+   - GLM with an account: **Z.ai / BigModel**, with **Authentication** set to **Account sign-in**. Choose the **Site**, tick **Acknowledge the notes above**, choose **Sign in with the browser** and authorize; to sign in from a browser other than the default one, choose **Copy sign-in link** instead. The app creates an API key named `thinkwatch` on the account and saves the upstream.
    - Kimi: **Custom**, with the Anthropic-compatible base URL from Kimi's documentation and **Protocol** set to **Anthropic Messages**. For Kimi For Coding, also turn on **Forward client identity**.
 
-   **Check connection** verifies the address and key and fetches the model list at no cost. Choose **Next** twice, then **Create**.
+   With a key, **Check connection** verifies the address and key and fetches the model list at no cost; choose **Next** twice, then **Create**. After an account sign-in the upstream is already saved; choose **Next** twice, then **Done**.
 2. On the Clients page, choose **Connect…** on the Claude Code row. The dialog lists the fields that change in `~/.claude/settings.json`: `env.ANTHROPIC_BASE_URL`, `env.ANTHROPIC_AUTH_TOKEN` (a new key named `claude-code`) and `env.CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY`. Choose **Connect**.
 3. Choose how the model is selected:
    - **By name.** In Claude Code, `/model <model ID>` switches to the model, and `claude --model <model ID>` starts with it. To map Claude Code's model aliases to it, add these to the `env` block of `~/.claude/settings.json`; the Haiku one also runs background tasks.
@@ -35,6 +35,7 @@ ThinkWatch Lite connects Claude Code to a gateway on the same computer, which fo
 - **Format conversion.** Claude Code sends Anthropic Messages; with that protocol the request goes out unchanged, apart from identity fields such as `metadata.user_id`, which the gateway removes. Only an upstream in another format, such as an OpenAI-compatible address set to OpenAI Chat Completions, gets a converted request: Traffic marks it **Converted** and its details list any dropped fields. Web search, a server-side tool, cannot be converted and is not sent to such an upstream. **Auto-detect** does not recognize these addresses and forwards requests in the client's own format, which suits Claude Code but not Codex.
 - **Forward client identity** is off by default, so upstreams see ThinkWatch's User-Agent and no client identity. Kimi For Coding, Bailian Coding Plan and similar upstreams accept only certain clients; with the switch on, they receive Claude Code's own User-Agent, identity headers such as `x-app` and the identity fields in the body, unaltered.
 - **GLM Coding Plan.** An upstream on `api.z.ai` or `open.bigmodel.cn`, signed in or added with a key, shows its 5-hour and weekly limits, and the credits left on a plan billed in credits, in the Quota / billing column and in the menu bar or tray menu.
+- **Balance.** A DeepSeek upstream, and a Kimi upstream on `api.moonshot.cn` or `api.moonshot.ai`, shows the account balance in the Quota / billing column.
 - **The /model list** shows gateway models only when their names contain `claude` or `anthropic`. Other models are typed by name, or added as one entry with `ANTHROPIC_CUSTOM_MODEL_OPTION`.
 - **Cost.** A rewritten request is priced as the model actually sent.
 - **Restore…** puts back only the fields the app wrote; model variables added by hand stay in `settings.json`.

diff --git a/src/content/docs-lite/en/codex-other-models.md b/src/content/docs-lite/en/codex-other-models.md
@@ -10,7 +10,7 @@ ThinkWatch Lite connects Codex to a gateway on the same computer that accepts th
 
 ## Steps
 
-1. On the Upstreams page, choose **New upstream** and pick the service on the first step, **Service**, which goes straight to **Connection**: **Anthropic** for Claude, or **Google Gemini**; each fills in the address and protocol. For a relay, choose **Custom**, enter its **Base URL** without an endpoint path such as `/chat/completions`, and set **Protocol** to **OpenAI Chat Completions**; for GLM, for example, `https://api.z.ai/api/paas/v4`, or `…/api/coding/paas/v4` on a GLM Coding Plan. A base URL that ends with its own version, such as `/v4` or Volcengine Ark's `/api/v3`, is used as written from ThinkWatch Lite 2026.10.5. Enter the **API key**, choose **Check connection**, then **Next**. If the relay lists no models, or leaves some out, type each missing model ID in the box at the end of **Models** and press Enter. Choose **Next**, then **Create**.
+1. On the Upstreams page, choose **New upstream** and pick the service on the first step, **Service**, which goes straight to **Connection**: **Anthropic** for Claude, or **Google Gemini**; each fills in the address and protocol. For a relay, choose its service under **Platforms and relays**, or **Custom** for any other. **OpenRouter** fills in its address and protocol. For **Sub2API**, **New API / One API** and **Custom**, enter the relay's **Base URL** without an endpoint path such as `/chat/completions`, and set **Protocol** to **OpenAI Chat Completions**; for GLM, for example, choose **Custom** with `https://api.z.ai/api/paas/v4`, or `…/api/coding/paas/v4` on a GLM Coding Plan. A base URL that ends with its own version, such as `/v4` or Volcengine Ark's `/api/v3`, is used as written from ThinkWatch Lite 2026.10.5. Enter the **API key**, choose **Check connection**, then **Next**. If the relay lists no models, or leaves some out, type each missing model ID in the box at the end of **Models** and press Enter. Choose **Next**, then **Create**.
 2. On the Clients page, choose **Connect…** on the Codex row. The dialog shows the change to `~/.codex/config.toml`:
 
    | Field | Value |

diff --git a/src/content/docs-lite/en/compare-cc-switch.md b/src/content/docs-lite/en/compare-cc-switch.md
@@ -17,12 +17,12 @@ A dash means the feature is not described in that product's documentation.
 | | CC Switch | ThinkWatch Lite |
 |---|---|---|
 | Clients | Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes Agent, Pi, MiniMax Code | In one step: Claude Code, Claude Desktop, Codex (also in the ChatGPT desktop app), opencode, Pi, oh-my-pi, Grok Build, Qwen Code, Hermes Agent, Zed, Aider, DeepSeek Harness. With instructions: Cursor, Continue, Antigravity CLI |
-| Adding providers | More than 50 presets; `ccswitch://` links import providers, MCP servers, prompts and skills | A new upstream starts from the service: a ChatGPT or Z.ai / BigModel account sign-in, API access to Anthropic, OpenAI, Google Gemini, Amazon Bedrock, DeepSeek or Ollama, or any compatible endpoint; `thinkwatch://import` links from a relay or vendor pre-fill one upstream |
+| Adding providers | More than 50 presets; `ccswitch://` links import providers, MCP servers, prompts and skills | A new upstream starts from the service, in three groups: model vendors (Anthropic, OpenAI, Google Gemini, DeepSeek, Z.ai / BigModel), platforms and relays (Amazon Bedrock, OpenRouter, ThinkWatch Enterprise, Sub2API, New API / One API), and Ollama or any compatible endpoint; ChatGPT and Z.ai / BigModel accounts sign in inside the dialog; `thinkwatch://import` links from a relay or vendor pre-fill one upstream |
 | Routing | In proxy mode, each client's requests go to its current provider; models can be mapped per provider | Ordered rules per key by model, API format, input tokens, tools, images, extended thinking and more; rules can rewrite the model |
 | Failover | Queue in priority order with a circuit breaker (proxy mode) | Next upstream in the group when an attempt fails before the answer begins; a session stays on one upstream |
 | Load balancing | — | Group strategies: in order, manual, round robin, lowest latency, lowest cost |
 | API format conversion | Proxy mode: Claude Code to OpenAI Chat Completions or Responses; Codex to Chat Completions or Anthropic Messages | Among Anthropic Messages, OpenAI Chat Completions, OpenAI Responses and Gemini |
-| Usage and cost | Requests, tokens, cache hit rate and estimated cost, from proxy logs or the clients' session logs; custom prices, optional sync from models.dev; quota and balance display | Tokens, cost and requests by period, model and upstream; LiteLLM prices refreshed daily, or custom price sheets; estimates marked, unpriced requests counted separately |
+| Usage and cost | Requests, tokens, cache hit rate and estimated cost, from proxy logs or the clients' session logs; custom prices, optional sync from models.dev; quota and balance display | Tokens, cost and requests by period, model and upstream; LiteLLM prices refreshed daily, or custom price sheets; estimates marked, unpriced requests counted separately; the balances and quotas that upstreams report |
 | Request details | Provider, model, tokens, cost, timing and status; parameters, a response summary and errors | Matched rule, each attempt with its status, request and response bodies, cost; full-text search; replay against another upstream |
 | Outbound redaction and tool-call inspection | — | API keys, private keys, ID and bank card numbers replaced before a request leaves; tool calls that download and run code or send out credentials cut off. Both start by only recording |
 | MCP and skills | One MCP server list synced to the selected clients; skills installed from GitHub or ZIP files | MCP servers of 13 clients side by side, copied or removed for 4; skills and hooks listed; all scanned for hidden characters, prompt injection, dangerous commands and overly broad permissions |

diff --git a/src/content/docs-lite/en/failover-and-load-balancing.md b/src/content/docs-lite/en/failover-and-load-balancing.md
@@ -9,7 +9,7 @@ ThinkWatch Lite turns each relay key into an upstream and puts several upstreams
 
 ## Steps
 
-1. On the Upstreams page, choose **New upstream** and pick the service under **Service** (**Custom** for a relay). Under **Connection**, enter a **Name**, the **Base URL** and one **API key**, choose **Check connection**, then **Next** until **Create**. Repeat for each key: an upstream holds one key, and failover and pauses work per upstream.
+1. On the Upstreams page, choose **New upstream** and pick the service under **Service** (for a relay, its service under **Platforms and relays**, or **Custom**). Under **Connection**, enter a **Name**, the **Base URL** where it is asked for and one **API key**, choose **Check connection**, then **Next** until **Create**. Repeat for each key: an upstream holds one key, and failover and pauses work per upstream.
 2. On the Routing page, choose **New group** under **Groups**. Enter a **Name**, choose a **Strategy**, tick the upstreams under **Members**, drag them into order and choose **Create**. For **Round robin**, also enter each member's **Weight** and choose **Distribute by**.
 3. Under **Routes**, open the route, choose **Edit…** on the rule that should use the group (usually **All requests (catch-all)**), select the group in **Forward to** and choose **Save** in both dialogs.
 4. **Dry run** checks the result without sending anything. On the Traffic page, a request's **Routing** tab lists the upstreams it tried under **Attempts**.

diff --git a/src/content/docs-lite/en/faq.md b/src/content/docs-lite/en/faq.md
@@ -30,7 +30,7 @@ Through the gateway, Claude Code can use an Anthropic API key, Amazon Bedrock, a
 
 ## Can ThinkWatch Lite use relays and Chinese models such as GLM, Kimi, Qwen or DeepSeek?
 
-Yes. Any service with an Anthropic, OpenAI or Gemini API can be an upstream: on the Upstreams page, choose **New upstream**, set **Service** to **Custom**, and enter the **Base URL** and **API key**. DeepSeek is in the Service list, and a Z.ai or BigModel account can be signed in directly, with its GLM Coding Plan quota shown in the app.
+Yes. Any service with an Anthropic, OpenAI or Gemini API can be an upstream: on the Upstreams page, choose **New upstream**, set **Service** to **Custom**, and enter the **Base URL** and **API key**. DeepSeek, OpenRouter, Sub2API and New API / One API are in the Service list, and a Z.ai or BigModel account can be signed in directly, with its GLM Coding Plan quota shown in the app.
 
 Upstreams that accept only particular clients, such as Kimi For Coding or Bailian Coding Plan, need **Forward client identity** turned on in the upstream's connection settings; otherwise requests identify themselves as ThinkWatch. A custom price sheet covers a relay whose prices differ from the official ones, and a routing rule can rewrite the model name, in which case the request is priced by the name it was sent with.