Update default anthropic model to Claude Haiku 4.5

patrickfleith · patrickfleith · commit c495b753e3ed · 2025-10-15T23:16:56.000+02:00
diff --git a/README.md b/README.md
@@ -104,7 +104,7 @@ config = ClassificationDatasetConfig(
 # Create LLM providers
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     GeminiProvider(model_id="gemini-2.0-flash")
 ]
 ```
diff --git a/datafast/examples/classification_trail_conditions_example.py b/datafast/examples/classification_trail_conditions_example.py
@@ -59,7 +59,7 @@
 # Set up providers
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929")
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001")
 ]
 
 # Generate dataset
diff --git a/datafast/examples/generic_pipeline_example.py b/datafast/examples/generic_pipeline_example.py
@@ -42,7 +42,7 @@ def main():
             model_id="gpt-5-mini-2025-08-07",
             temperature=1
             ),
-        # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
         # GeminiProvider(model_id="gemini-2.5-flash-lite", rpm_limit=15),
         # OllamaProvider(model_id="gemma3:4b"),
     ]
diff --git a/datafast/examples/inspect_dataset_example.py b/datafast/examples/inspect_dataset_example.py
@@ -48,7 +48,7 @@
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     # Uncomment to use additional providers
-    # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     # GeminiProvider(model_id="gemini-2.0-flash"),
 ]
 
diff --git a/datafast/examples/mcq_example.py b/datafast/examples/mcq_example.py
@@ -26,7 +26,7 @@ def main():
     # 2. Initialize LLM providers
     providers = [
         OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-        # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
         # GeminiProvider(model_id="gemini-2.0-flash"),
     ]
 
diff --git a/datafast/examples/quickstart_example.py b/datafast/examples/quickstart_example.py
@@ -35,7 +35,7 @@
 
 providers = [
     OpenAIProvider(model_id="gpt-5-nano-2025-08-07"),
-    # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     # GeminiProvider(model_id="gemini-2.0-flash"),
     # OllamaProvider(model_id="gemma3:12b")
 ]
diff --git a/datafast/examples/raw_text_space_engineering_example.py b/datafast/examples/raw_text_space_engineering_example.py
@@ -43,7 +43,7 @@ def main():
     # 2. Create LLM providers with specific models
     providers = [
         OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models
-        AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     ]
 
     # 3. Generate the dataset
diff --git a/datafast/examples/show_dataset_examples.py b/datafast/examples/show_dataset_examples.py
@@ -46,7 +46,7 @@
 classification_row2 = TextClassificationRow(
     text="The trail is well maintained and easy to follow.",
     label="positive_conditions",
-    model_id="claude-sonnet-4-5-20250929",
+    model_id="claude-haiku-4-5-20251001",
     language="en",
 )
 classification_dataset.data_rows = [classification_row, classification_row2]
@@ -85,7 +85,7 @@
     question="What was the main goal of the Mars 2020 mission?",
     chosen_response="To search for signs of ancient life and collect samples.",
     rejected_response="To launch a satellite.",
-    chosen_model_id="claude-sonnet-4-5-20250929",
+    chosen_model_id="claude-haiku-4-5-20251001",
     rejected_model_id="gpt-4.1-nano",
     chosen_response_score=9,
     rejected_response_score=3,
diff --git a/datafast/examples/ultrachat_materials_science.py b/datafast/examples/ultrachat_materials_science.py
@@ -25,7 +25,7 @@ def main():
 
     # 2. Initialize LLM providers - using just one for simplicity
     providers = [
-        AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     ]
 
     # 3. Get expected number of rows
diff --git a/datafast/llms.py b/datafast/llms.py
@@ -282,7 +282,7 @@ def env_key_name(self) -> str:
 
     def __init__(
         self,
-        model_id: str = "claude-sonnet-4-5-20250929",
+        model_id: str = "claude-haiku-4-5-20251001",
         api_key: str | None = None,
         temperature: float | None = None,
         max_completion_tokens: int | None = None,
@@ -292,7 +292,7 @@ def __init__(
         """Initialize the Anthropic provider.
 
         Args:
-            model_id: The model ID (defaults to claude-sonnet-4-5-20250929)
+            model_id: The model ID (defaults to claude-haiku-4-5-20251001)
             api_key: API key (if None, will get from environment)
             temperature: Temperature for generation (0.0 to 1.0)
             max_completion_tokens: Maximum tokens to generate
diff --git a/docs/guides/generating_mcq_datasets.md b/docs/guides/generating_mcq_datasets.md
@@ -184,7 +184,7 @@ Configure one or more LLM providers to generate your dataset:
 ```python
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     GeminiProvider(model_id="gemini-2.0-flash")
 ]
 ```
@@ -274,7 +274,7 @@ def main():
     providers = [
         OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
         # Add more providers as needed
-        # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
         # GeminiProvider(model_id="gemini-2.0-flash"),
     ]
 
diff --git a/docs/guides/generating_text_classification_datasets.md b/docs/guides/generating_text_classification_datasets.md
@@ -167,7 +167,7 @@ Configure one or more LLM providers to generate your dataset:
 ```python
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929")
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001")
 ]
 ```
 
@@ -294,7 +294,7 @@ config = ClassificationDatasetConfig(
 # Set up providers
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929")
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001")
 ]
 
 # Generate dataset
diff --git a/docs/guides/generating_text_datasets.md b/docs/guides/generating_text_datasets.md
@@ -157,7 +157,7 @@ Configure one or more LLM providers to generate your dataset:
 ```python
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
 ]
 ```
 
@@ -281,7 +281,7 @@ def main():
     # 2. Create LLM providers with specific models
     providers = [
         OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models
-        AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     ]
 
     # 3. Generate the dataset
diff --git a/docs/guides/generating_ultrachat_datasets.md b/docs/guides/generating_ultrachat_datasets.md
@@ -153,7 +153,7 @@ Configure one or more LLM providers to generate your dataset:
 
 ```python
 providers = [
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
 ]
 ```
 
@@ -259,7 +259,7 @@ def main():
 
     # 2. Initialize LLM providers - using just one for simplicity
     providers = [
-        AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+        AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     ]
 
     # 3. Get expected number of rows
diff --git a/docs/index.md b/docs/index.md
@@ -94,7 +94,7 @@ config = ClassificationDatasetConfig(
 # Create LLM providers
 providers = [
     OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
-    AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     GeminiProvider(model_id="gemini-2.5-flash"),
     OpenRouterProvider(model_id="z-ai/glm-4.6")
 ]
diff --git a/docs/llms.md b/docs/llms.md
@@ -24,7 +24,7 @@ Each provider can be instantiated with default parameters:
 # OpenAI (default: gpt-5-mini-2025-08-07)
 openai_llm = OpenAIProvider()
 
-# Anthropic (default:claude-sonnet-4-5-20250929)
+# Anthropic (default:claude-haiku-4-5-20251001)
 anthropic_llm = AnthropicProvider()
 
 # Gemini (default: gemini-2.0-flash)
diff --git a/tests/test_llms.py b/tests/test_llms.py
@@ -327,7 +327,7 @@ def test_gemini_messages_with_structured_output():
 def test_anthropic_with_all_parameters():
     """Test Anthropic provider with all optional parameters specified."""
     provider = AnthropicProvider(
-        model_id="claude-sonnet-4-5-20250929",
+        model_id="claude-haiku-4-5-20251001",
         temperature=0.3,
         max_completion_tokens=200,
         top_p=0.95,
@@ -999,7 +999,7 @@ def test_openai_batch_with_all_parameters():
 def test_anthropic_batch_with_all_parameters():
     """Test Anthropic provider with batch processing and all optional parameters."""
     provider = AnthropicProvider(
-        model_id="claude-sonnet-4-5-20250929",
+        model_id="claude-haiku-4-5-20251001",
         temperature=0.1,
         max_completion_tokens=50,
         top_p=0.9

Original file line number	Diff line number	Diff line change
`@@ -104,7 +104,7 @@ config = ClassificationDatasetConfig(`
`104`	`104`	`# Create LLM providers`
`105`	`105`	`providers = [`
`106`	`106`	`OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),`
`107`		`- AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`107`	`+ AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`108`	`108`	`GeminiProvider(model_id="gemini-2.0-flash")`
`109`	`109`	`]`
`110`	`110`	```
Original file line number	Diff line number	Diff line change
`@@ -59,7 +59,7 @@`
`59`	`59`	`# Set up providers`
`60`	`60`	`providers = [`
`61`	`61`	`OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),`
`62`		`- AnthropicProvider(model_id="claude-sonnet-4-5-20250929")`
	`62`	`+ AnthropicProvider(model_id="claude-haiku-4-5-20251001")`
`63`	`63`	`]`
`64`	`64`
`65`	`65`	`# Generate dataset`
Original file line number	Diff line number	Diff line change
`@@ -42,7 +42,7 @@ def main():`
`42`	`42`	`model_id="gpt-5-mini-2025-08-07",`
`43`	`43`	`temperature=1`
`44`	`44`	`),`
`45`		`- # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`45`	`+ # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`46`	`46`	`# GeminiProvider(model_id="gemini-2.5-flash-lite", rpm_limit=15),`
`47`	`47`	`# OllamaProvider(model_id="gemma3:4b"),`
`48`	`48`	`]`
Original file line number	Diff line number	Diff line change
`@@ -48,7 +48,7 @@`
`48`	`48`	`providers = [`
`49`	`49`	`OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),`
`50`	`50`	`# Uncomment to use additional providers`
`51`		`- # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`51`	`+ # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`52`	`52`	`# GeminiProvider(model_id="gemini-2.0-flash"),`
`53`	`53`	`]`
`54`	`54`
Original file line number	Diff line number	Diff line change
`@@ -26,7 +26,7 @@ def main():`
`26`	`26`	`# 2. Initialize LLM providers`
`27`	`27`	`providers = [`
`28`	`28`	`OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),`
`29`		`- # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`29`	`+ # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`30`	`30`	`# GeminiProvider(model_id="gemini-2.0-flash"),`
`31`	`31`	`]`
`32`	`32`
Original file line number	Diff line number	Diff line change
`@@ -35,7 +35,7 @@`
`35`	`35`
`36`	`36`	`providers = [`
`37`	`37`	`OpenAIProvider(model_id="gpt-5-nano-2025-08-07"),`
`38`		`- # AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`38`	`+ # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`39`	`39`	`# GeminiProvider(model_id="gemini-2.0-flash"),`
`40`	`40`	`# OllamaProvider(model_id="gemma3:12b")`
`41`	`41`	`]`
Original file line number	Diff line number	Diff line change
`@@ -43,7 +43,7 @@ def main():`
`43`	`43`	`# 2. Create LLM providers with specific models`
`44`	`44`	`providers = [`
`45`	`45`	`OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models`
`46`		`- AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`46`	`+ AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`47`	`47`	`]`
`48`	`48`
`49`	`49`	`# 3. Generate the dataset`
Original file line number	Diff line number	Diff line change
`@@ -25,7 +25,7 @@ def main():`
`25`	`25`
`26`	`26`	`# 2. Initialize LLM providers - using just one for simplicity`
`27`	`27`	`providers = [`
`28`		`- AnthropicProvider(model_id="claude-sonnet-4-5-20250929"),`
	`28`	`+ AnthropicProvider(model_id="claude-haiku-4-5-20251001"),`
`29`	`29`	`]`
`30`	`30`
`31`	`31`	`# 3. Get expected number of rows`