v0.4.0: account commands restored (key auth) + catalog refresh

README.md

@@ -1,6 +1,6 @@
 # QuickSilver Pro CLI
 
-`qsp` — a command-line client for [QuickSilver Pro](https://quicksilverpro.io), one OpenAI-compatible API for frontier and open-source LLMs (Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, Muse) **and** FLUX text-to-image — all billed to a single balance. Open-source chat models run up to 20% below OpenRouter.
+`qsp` — a command-line client for [QuickSilver Pro](https://quicksilverpro.io), one OpenAI-compatible API for frontier and open-source LLMs (Claude, GPT, Gemini, Grok, GLM, DeepSeek, Qwen, Kimi, Muse) **and** FLUX text-to-image — all billed to a single balance. Open-source chat models run up to 20% below OpenRouter.
 
 Designed to be **AI-agent friendly**: data commands accept `--json` for structured output, exit codes are reliable, and the API surface is intentionally small.
 

pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "hatchling.build"
 
 [project]
 name = "quicksilverpro"
-version = "0.3.0"
-description = "CLI for QuickSilver Pro — one OpenAI-compatible API for Claude, GPT, Gemini, DeepSeek, Qwen, Kimi and Muse chat plus FLUX image generation, on a single balance."
+version = "0.4.0"
+description = "CLI for QuickSilver Pro — one OpenAI-compatible API for Claude, GPT, Gemini, Grok, GLM, DeepSeek, Qwen, Kimi and Muse chat plus FLUX image generation, on a single balance."
 readme = "README.md"
 requires-python = ">=3.9"
 license = { text = "MIT" }
@@ -14,7 +14,7 @@ keywords = [
   "openai", "claude", "anthropic", "gpt", "gemini", "deepseek", "qwen",
   "kimi", "muse", "flux", "llm", "inference", "api", "chatgpt", "ai", "cli",
   "coding-agent", "image-generation", "text-to-image",
-  "openrouter-alternative", "quicksilverpro",
+  "openrouter-alternative", "quicksilverpro", "grok", "glm", "nemotron",
 ]
 classifiers = [
   "Development Status :: 4 - Beta",

src/quicksilverpro/__init__.py

@@ -3,4 +3,4 @@
 See https://quicksilverpro.io for docs. `qsp --help` for quick reference.
 """
 
-__version__ = "0.3.0"
+__version__ = "0.4.0"

src/quicksilverpro/cli.py

@@ -280,9 +280,9 @@ def balance(as_json: bool) -> None:
 
 # Hardcoded so `qsp models` works before the user has signed in. A curated,
 # hot-first view of the lineup — once signed in, `qsp models` shows the full
-# live catalog (30+ models incl. every Qwen/Kimi/Gemini/Claude variant). Keep
+# live catalog (40 models incl. every Qwen/Kimi/Gemini/Claude variant). Keep
 # prices in sync with the backend; CI smoke-tests this path. Prices verified
-# 2026-08-08 against qsp.gateway_model_pricing.
+# 2026-08-25 against the live /v1/models endpoint.
 _MODELS_FALLBACK: list[dict] = [
     {"id": "claude-opus-5", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1000000,
@@ -296,6 +296,14 @@ def balance(as_json: bool) -> None:
      "context_length": 1048576,
      "pricing": {"prompt": "0.0000040000", "completion": "0.0000240000"},
      "best_for": "OpenAI GPT-5.6 Sol · frontier reasoning + tool use"},
+    {"id": "grok-4.6", "object": "model", "owned_by": "quicksilverpro",
+     "context_length": 500000,
+     "pricing": {"prompt": "0.0000020000", "completion": "0.0000060000"},
+     "best_for": "xAI Grok 4.6 · frontier reasoning + real-time knowledge"},
+    {"id": "glm-5.3", "object": "model", "owned_by": "quicksilverpro",
+     "context_length": 1048576,
+     "pricing": {"prompt": "0.0000011200", "completion": "0.0000035200"},
+     "best_for": "Z.ai GLM 5.3 · reasoning flagship for software engineering"},
     {"id": "qwen3.8-max", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1048576,
      "pricing": {"prompt": "0.0000020000", "completion": "0.0000060000"},
@@ -304,21 +312,29 @@ def balance(as_json: bool) -> None:
      "context_length": 1048576,
      "pricing": {"prompt": "0.0000024000", "completion": "0.0000120000"},
      "best_for": "Moonshot Kimi K3 · agentic coding + tool use · 1M context"},
+    {"id": "kimi-k2.7-code", "object": "model", "owned_by": "quicksilverpro",
+     "context_length": 256000,
+     "pricing": {"prompt": "0.0000005840", "completion": "0.0000028000"},
+     "best_for": "Kimi K2.7 Code · purpose-built coding agent"},
     {"id": "muse-spark-1.2", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1048576,
      "pricing": {"prompt": "0.0000010000", "completion": "0.0000034000"},
      "best_for": "Meta Muse Spark · long-context coding agent"},
     {"id": "deepseek-v4-pro", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1048576,
-     "pricing": {"prompt": "0.0000003480", "completion": "0.0000006960"},
+     "pricing": {"prompt": "0.0000004350", "completion": "0.0000008700"},
      "best_for": "frontier reasoning + coding · 1M context"},
     {"id": "deepseek-v4-flash", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1048576,
      "pricing": {"prompt": "0.0000001120", "completion": "0.0000002240"},
      "best_for": "official 0731 agent model · lowest cost · 1M context"},
-    {"id": "gemini-3.6-flash", "object": "model", "owned_by": "quicksilverpro",
+    {"id": "nemotron-3.5-lightning", "object": "model", "owned_by": "quicksilverpro",
+     "context_length": 262144,
+     "pricing": {"prompt": "0.0000000800", "completion": "0.0000002000"},
+     "best_for": "NVIDIA Nemotron · fastest + cheapest agent loops"},
+    {"id": "gemini-3.7-flash", "object": "model", "owned_by": "quicksilverpro",
      "context_length": 1048576,
-     "pricing": {"prompt": "0.0000012750", "completion": "0.0000063750"},
+     "pricing": {"prompt": "0.0000006375", "completion": "0.0000031875"},
      "best_for": "Google Gemini · fast multimodal · 1M context"},
     {"id": "flux.2-pro", "object": "model", "owned_by": "quicksilverpro",
      "price_per_image": 0.027,