Update default models with pricing documentation

- Add pricing comments (USD per 1M tokens input/output)
- Update to cost-optimized models for weekly CI runs:
  - openai: gpt-4o-mini ($0.15 / $0.60)
  - gemini: gemini-2.5-flash-lite ($0.10 / $0.40)
  - anthropic: claude-haiku-4-5 ($1.00 / $5.00)
- Use model aliases that auto-update to latest snapshots
- Note: Anthropic is ~10x more expensive than Gemini
- Update docs and Copilot instructions with new defaults

Author: Marius1311

.github/copilot-instructions.md

@@ -109,7 +109,8 @@ cell_ann = CellAnnotator(
 ### LLM Provider Selection
 - Providers: `"openai"` (default), `"gemini"`, `"anthropic"`
 - API keys via environment variables or `.env` file (loaded with python-dotenv)
-- Models: `gpt-4o-mini` (default), `gpt-4o`, `gemini-2.0-flash-exp`, `claude-3-5-sonnet-20241022`
+- Models: `gpt-4o-mini`, `gemini-2.5-flash-lite`, `claude-haiku-4-5` (defaults)
+- Anthropic is most expensive ($1/$5 per 1M tokens), minimize usage in tests
 
 ### Structured Outputs with Pydantic
 - `CellTypeListOutput`: List of expected cell types

src/cell_annotator/_constants.py

@@ -10,10 +10,15 @@ class PackageConstants:
     min_markers: int = 15
     use_raw: bool = False
     default_min_color_distance: float = 4.0  # Delta E threshold for color distinguishability
+    # Default models optimized for cost-effectiveness in CI runs
+    # Pricing in USD per 1M tokens (input / output):
+    # - openai (gpt-4o-mini): $0.15 / $0.60
+    # - gemini (gemini-2.5-flash-lite): $0.10 / $0.40
+    # - anthropic (claude-haiku-4-5): $1.00 / $5.00
     default_models: dict[str, str] = {
         "openai": "gpt-4o-mini",
         "gemini": "gemini-2.5-flash-lite",
-        "anthropic": "claude-3-5-haiku-20241022",
+        "anthropic": "claude-haiku-4-5",
     }
     # Supported LLM providers
     supported_providers: list[str] = ["openai", "gemini", "anthropic"]

src/cell_annotator/_docs.py

@@ -43,7 +43,7 @@
 _model = """\
 model
     Model name. If None, uses the default model for the selected or auto-detected provider.
-    Examples: 'gpt-4o-mini', 'gemini-2.5-flash', 'claude-3-haiku'."""
+    Examples: 'gpt-4o-mini', 'gemini-2.5-flash-lite', 'claude-haiku-4-5'."""
 
 _max_completion_tokens = """\
 max_completion_tokens