diff --git a/README.md b/README.md
index 71fbd6451..102637744 100644
--- a/README.md
+++ b/README.md
@@ -181,8 +181,9 @@ you can prototype with the LLM and ship the output to production without a
 model at runtime.
 
 It supports Anthropic, OpenAI, Gemini, Google Vertex AI, Mistral, Hugging
-Face, the [Vercel AI Gateway](https://vercel.com/ai-gateway) (one key for
-hundreds of models from every major lab), any OpenAI-compatible endpoint via
+Face, the multi-lab gateways [Vercel AI Gateway](https://vercel.com/ai-gateway),
+[OpenRouter](https://openrouter.ai) and [OrcaRouter](https://orcarouter.ai)
+(one key for hundreds of models), any OpenAI-compatible endpoint via
 `OPENAI_BASE_URL`, and local models via Ollama or llama.cpp. You can also run
 without an LLM using `--no-llm`, which drops you into the REPL. See the
 [agent documentation](https://lightpanda.io/docs/usage/agent) for the full
@@ -199,6 +200,7 @@ cat session.js | ./lightpanda run -                   # ...or pipe one in via st
 VERTEX_API_KEY=... ./lightpanda agent --provider vertex             # Vertex AI, express mode
 GOOGLE_CLOUD_PROJECT=my-proj ./lightpanda agent --provider vertex   # Vertex AI, token via gcloud auth
 AI_GATEWAY_API_KEY=... ./lightpanda agent --provider vercel --model moonshotai/kimi-k2   # any model behind Vercel AI Gateway
+OPENROUTER_API_KEY=... ./lightpanda agent --provider openrouter --model anthropic/claude-sonnet-5   # any model behind OpenRouter
 OPENAI_BASE_URL=https://my-gateway/v1 OPENAI_API_KEY=... ./lightpanda agent            # any OpenAI-compatible server
 ```
 
diff --git a/src/agent/settings.zig b/src/agent/settings.zig
index 4962ef9cb..031335ed1 100644
--- a/src/agent/settings.zig
+++ b/src/agent/settings.zig
@@ -31,7 +31,7 @@ const string = @import("../string.zig");
 const auth = @import("auth/auth.zig");
 const Candidate = zenai.provider.Candidate;
 
-pub const api_keys_hint = "ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY, or MISTRAL_API_KEY (Vertex AI: VERTEX_API_KEY, or GOOGLE_CLOUD_PROJECT via gcloud; Codex: a ChatGPT subscription via /provider codex)";
+pub const api_keys_hint = "ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY, MISTRAL_API_KEY, OPENROUTER_API_KEY, or ORCAROUTER_API_KEY (Vertex AI: VERTEX_API_KEY, or GOOGLE_CLOUD_PROJECT via gcloud; Codex: a ChatGPT subscription via /provider codex)";
 
 /// Determine which provider to use and read its env key. Returns null
 /// only when no `--provider` was given AND no env key exists (the caller
diff --git a/src/help.zon b/src/help.zon
index d0d361ab4..c6aba3f2a 100644
--- a/src/help.zon
+++ b/src/help.zon
@@ -202,6 +202,7 @@
     \\  {0s} agent                                (auto-detects API key from env)
     \\  {0s} agent --provider anthropic --model claude-sonnet-4-6
     \\  {0s} agent --provider huggingface         (HF serverless router, HF_TOKEN)
+    \\  {0s} agent --provider openrouter --model anthropic/claude-sonnet-5
     \\  {0s} agent --provider ollama --model qwen3.5:latest
     \\  {0s} agent --no-llm                       (basic slash-command-only REPL)
     \\  {0s} run script.js                        (replay a saved script; see `run`)
@@ -255,7 +256,8 @@
     \\          The AI provider. When omitted, lightpanda auto-detects an API
     \\          key from your environment (ANTHROPIC_API_KEY, OPENAI_API_KEY,
     \\          GOOGLE_API_KEY/GEMINI_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY,
-    \\          MISTRAL_API_KEY, VERTEX_API_KEY). With exactly one key set:
+    \\          MISTRAL_API_KEY, OPENROUTER_API_KEY, ORCAROUTER_API_KEY,
+    \\          VERTEX_API_KEY). With exactly one key set:
     \\          that provider is used. With multiple keys on a TTY: you'll be
     \\          prompted to pick; in non-interactive contexts, pass --provider
     \\          explicitly. With no keys set: falls back to the basic REPL
@@ -272,11 +274,13 @@
     \\
     \\          Local servers (ollama, llama_cpp) are never auto-detected (they
     \\          need no key); select them explicitly with --provider ollama /
-    \\          --provider llama_cpp.
+    \\          --provider llama_cpp. Same for codex, which uses a ChatGPT
+    \\          subscription (OAuth) instead of an API key.
     \\
     \\          Allowed values: "anthropic", "openai", "gemini", "huggingface",
-    \\                          "vercel", "mistral", "ollama", "llama_cpp",
-    \\                          "vertex", "codex", "openai_compatible".
+    \\                          "vercel", "mistral", "openrouter", "orcarouter",
+    \\                          "ollama", "llama_cpp", "vertex", "codex",
+    \\                          "openai_compatible".
     \\          In the REPL, use /provider to list and change providers.
     \\  --save <PATH>
     \\          Synthesize a replayable .js script from the --task run and write