fix: clean up OpenRouter-generated provider configs (#37)

- Merge unique models from duplicate providers into their hand-written
  counterparts and remove the duplicates:
  - alibaba (tongyi-deepresearch) → qwen
  - amazon (nova-2-lite, nova-micro, nova-premier) → bedrock
  - bytedance (ui-tars) → volcengine
  - nvidia (nemotron-3-nano, nemotron-3-super, etc.) → nvidia-nim
  - rekaai (reka-flash-3) → reka
- Set correct official API base_url for providers with public APIs:
  arcee-ai, inception, morph, reka, upstage
- Set key_required=false for 20 providers only accessible through
  hosting platforms (no public API)
- Update sync-pricing.py with SKIP_DUPLICATES, PROVIDER_API mapping,
  and default key_required=false for future auto-generated providers

providers/bedrock.toml

@@ -111,3 +111,33 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
+
+[[models]]
+id = "bedrock/amazon.nova-2-lite-v1:0"
+display_name = "Amazon: Nova 2 Lite"
+tier = "fast"
+context_window = 1000000
+max_output_tokens = 65535
+input_cost_per_m = 0.3
+output_cost_per_m = 2.5
+supports_streaming = true
+
+[[models]]
+id = "bedrock/amazon.nova-micro-v1:0"
+display_name = "Amazon: Nova Micro 1.0"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 5120
+input_cost_per_m = 0.035
+output_cost_per_m = 0.14
+supports_streaming = true
+
+[[models]]
+id = "bedrock/amazon.nova-premier-v1:0"
+display_name = "Amazon: Nova Premier 1.0"
+tier = "frontier"
+context_window = 1000000
+max_output_tokens = 65535
+input_cost_per_m = 2.5
+output_cost_per_m = 12.5
+supports_streaming = true