Skip to content

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

Python

Update README

Alishahryar12ea24e2510a8
diff --git a/README.md b/README.md
index 71699980..79bfcdb4 100644
--- a/README.md
+++ b/README.md
@@ -261,18 +261,12 @@ Restart the IDE after changing the file.
### 4. Model Picker
-Claude Code 2.1.126 or later can populate `/model` from this proxy's Gateway `/v1/models` response when `ANTHROPIC_BASE_URL` points here. In **2.1.126–2.1.128** that discovery was automatic; **newer releases** require **`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1`** in the same environment as `ANTHROPIC_*`. Omit the flag if you only set models via proxy config and never use `/model` discovery.
-
-Start Claude Code with that variable set (see [Run Claude Code](#7-run-claude-code)), run `/model`, and choose any discovered provider model.
+To use Claude Code's `/model` picker, start Claude Code with `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1`, run `/model`, and choose any listed provider model.
<div align="center">
<img src="assets/cc-model-picker.png" alt="Claude Code model picker showing gateway models" width="700">
</div>
-The proxy lists models for configured provider keys and referenced local providers. Picker-safe IDs are routed back to the real provider/model automatically, so no `.env` edit is needed after startup.
-
-Each provider model also has a `(no thinking)` picker variant. Use it when a model does not support Claude Code thinking or fails with adaptive-thinking requests. It routes to the same upstream model while asking Claude Code to send a non-thinking request.
-
## Optional Integrations
### 1. Discord And Telegram Bots