feat: add 2026 Q2 flagship models (#76)

Add latest flagships released in April 2026 that registry missed:
- deepseek: V4-Pro, V4-Flash (2026-04-24, 1M context)
- qwen: qwen3.6-max-preview (2026-04-20, 256K context)
- moonshot: kimi-k2.6 (2026-04-20, 256K context)
- zhipu: glm-5.1 (2026-04-08), glm-4.7-flash (free tier)

Update default aliases: deepseek -> v4-pro, kimi -> k2.6, glm -> 5.1.

providers/qwen.toml

@@ -1,5 +1,5 @@
 # Qwen / Alibaba — https://dashscope.aliyuncs.com
-# Models: 9
+# Models: 10
 # Regions: china (default), intl (Singapore), us (Virginia)
 
 [provider]
@@ -15,6 +15,20 @@ base_url = "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
 [provider.regions.us]
 base_url = "https://dashscope-us.aliyuncs.com/compatible-mode/v1"
 
+[[models]]
+id = "qwen3.6-max-preview"
+display_name = "Qwen3.6 Max Preview"
+tier = "frontier"
+context_window = 262144
+max_output_tokens = 32768
+input_cost_per_m = 1.30
+output_cost_per_m = 7.80
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+supports_thinking = true
+aliases = ["qwen3.6-max", "qwen-3.6-max"]
+
 [[models]]
 id = "qwen-max"
 display_name = "Qwen Max"