retab 0.0.38__py3-none-any.whl → 0.0.40__py3-none-any.whl

retab/types/ai_models.py

@@ -1,24 +1,32 @@
 import datetime
 from typing import List, Literal, Optional
+from pydantic import BaseModel, Field, computed_field
+from retab.types.inference_settings import InferenceSettings
 
-from pydantic import BaseModel, Field
 
-from .inference_settings import InferenceSettings
-
-AIProvider = Literal["OpenAI", "Gemini", "xAI", "Retab"]  # , "Anthropic", "xAI"]
-OpenAICompatibleProvider = Literal["OpenAI", "xAI"]  # , "xAI"]
+AIProvider = Literal["OpenAI", "Anthropic", "Gemini", "xAI", "Retab"]
+OpenAICompatibleProvider = Literal["OpenAI", "xAI"]
 GeminiModel = Literal[
+    "gemini-2.5-pro",
+    "gemini-2.5-flash",
     "gemini-2.5-pro-preview-06-05",
     "gemini-2.5-pro-preview-05-06",
+    "gemini-2.5-pro-preview-03-25",
     "gemini-2.5-flash-preview-05-20",
     "gemini-2.5-flash-preview-04-17",
+    "gemini-2.5-flash-lite-preview-06-17",
     "gemini-2.5-pro-exp-03-25",
     "gemini-2.0-flash-lite",
     "gemini-2.0-flash",
 ]
 
 AnthropicModel = Literal[
-    "claude-3-5-sonnet-latest", "claude-3-5-sonnet-20241022", "claude-3-5-haiku-20241022", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307"
+    "claude-3-5-sonnet-latest",
+    "claude-3-5-sonnet-20241022",
+    # "claude-3-5-haiku-20241022",
+    "claude-3-opus-20240229",
+    "claude-3-sonnet-20240229",
+    "claude-3-haiku-20240307",
 ]
 OpenAIModel = Literal[
     "gpt-4o",
@@ -26,24 +34,25 @@ OpenAIModel = Literal[
     "chatgpt-4o-latest",
     "gpt-4.1",
     "gpt-4.1-mini",
+    "gpt-4.1-mini-2025-04-14",
+    "gpt-4.1-2025-04-14",
     "gpt-4.1-nano",
+    "gpt-4.1-nano-2025-04-14",
     "gpt-4o-2024-11-20",
     "gpt-4o-2024-08-06",
     "gpt-4o-2024-05-13",
     "gpt-4o-mini-2024-07-18",
-    "o3-mini",
-    "o3-mini-2025-01-31",
+    # "o3-mini",
+    # "o3-mini-2025-01-31",
     "o1",
     "o1-2024-12-17",
-    "o1-preview-2024-09-12",
-    "o1-mini",
-    "o1-mini-2024-09-12",
+    # "o1-preview-2024-09-12",
+    # "o1-mini",
+    # "o1-mini-2024-09-12",
     "o3",
     "o3-2025-04-16",
     "o4-mini",
     "o4-mini-2025-04-16",
-    "gpt-4.5-preview",
-    "gpt-4.5-preview-2025-02-27",
     "gpt-4o-audio-preview-2024-12-17",
     "gpt-4o-audio-preview-2024-10-01",
     "gpt-4o-realtime-preview-2024-12-17",
@@ -51,9 +60,10 @@ OpenAIModel = Literal[
     "gpt-4o-mini-audio-preview-2024-12-17",
     "gpt-4o-mini-realtime-preview-2024-12-17",
 ]
-xAI_Model = Literal["grok-3-beta", "grok-3-mini-beta"]
-RetabModel = Literal["auto", "auto-small"]
-LLMModel = Literal[OpenAIModel, "human", AnthropicModel, xAI_Model, GeminiModel, RetabModel]
+xAI_Model = Literal["grok-3", "grok-3-mini"]
+RetabModel = Literal["auto-large", "auto-small", "auto-micro"]
+PureLLMModel = Literal[OpenAIModel, AnthropicModel, xAI_Model, GeminiModel, RetabModel]
+LLMModel = Literal[PureLLMModel, "human"]
 
 
 class FinetunedModel(BaseModel):
@@ -88,7 +98,7 @@ class TokenPrice(BaseModel):
 
     prompt: float  # Price per 1M prompt tokens.
     completion: float  # Price per 1M completion tokens.
-    cached_discount: float = 0.5  # Price discount for cached tokens.
+    cached_discount: float = 1.0  # Price discount for cached tokens. (1.0 means no discount or tokens are not cached)
 
 
 class Pricing(BaseModel):
@@ -124,7 +134,7 @@ EndpointType = Literal[
 ]
 
 # Define supported features
-FeatureType = Literal["streaming", "function_calling", "structured_outputs", "distillation", "fine_tuning", "predicted_outputs"]
+FeatureType = Literal["streaming", "function_calling", "structured_outputs", "distillation", "fine_tuning", "predicted_outputs", "schema_generation"]
 
 
 class ModelCapabilities(BaseModel):
@@ -138,6 +148,11 @@ class ModelCapabilities(BaseModel):
     features: List[FeatureType]
 
 
+class ModelCardPermissions(BaseModel):
+    show_in_free_picker: bool = False
+    show_in_paid_picker: bool = False
+
+
 class ModelCard(BaseModel):
     """
     Model card that includes pricing and capabilities.
@@ -148,498 +163,11 @@ class ModelCard(BaseModel):
     capabilities: ModelCapabilities
     temperature_support: bool = True
     reasoning_effort_support: bool = False
-
-
-# List of model cards with pricing and capabilities
-openai_model_cards = [
-    ########################
-    ########################
-    # ----------------------
-    # Reasoning models
-    # ----------------------
-    ########################
-    ########################
-    # ----------------------
-    # o1 family
-    # ----------------------
-    ModelCard(
-        model="o1",
-        pricing=Pricing(text=TokenPrice(prompt=15.00, cached_discount=0.5, completion=60.00), audio=None),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o1-2024-12-17",
-        pricing=Pricing(text=TokenPrice(prompt=15.00, cached_discount=0.5, completion=60.00), audio=None),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o1-preview-2024-09-12",
-        pricing=Pricing(text=TokenPrice(prompt=15.00, cached_discount=0.5, completion=60.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling"]),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    # ----------------------
-    # o1-mini family
-    # ----------------------
-    ModelCard(
-        model="o1-mini",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.5, completion=4.40), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions", "responses", "assistants"], features=["streaming"]),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o1-mini-2024-09-12",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.5, completion=4.40), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions", "responses", "assistants"], features=["streaming"]),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    # ----------------------
-    # o3 family
-    # ----------------------
-    ModelCard(
-        model="o3",
-        pricing=Pricing(text=TokenPrice(prompt=10.0, cached_discount=2.5 / 10.0, completion=40.0), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o3-2025-04-16",
-        pricing=Pricing(text=TokenPrice(prompt=10.0, cached_discount=2.5 / 10.0, completion=40.0), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    # ----------------------
-    # o3-mini family
-    # ----------------------
-    ModelCard(
-        model="o3-mini-2025-01-31",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.5, completion=4.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o3-mini",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.5, completion=4.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    # ----------------------
-    # o4-mini family
-    # ----------------------
-    ModelCard(
-        model="o4-mini",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.275 / 1.1, completion=4.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ModelCard(
-        model="o4-mini-2025-04-16",
-        pricing=Pricing(text=TokenPrice(prompt=1.10, cached_discount=0.275 / 1.1, completion=4.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=False,
-        reasoning_effort_support=True,
-    ),
-    ########################
-    ########################
-    # ----------------------
-    # Chat models
-    # ----------------------
-    ########################
-    ########################
-    # ----------------------
-    # gpt-4.1 family
-    # ----------------------
-    ModelCard(
-        model="gpt-4.1",
-        pricing=Pricing(text=TokenPrice(prompt=2.00, cached_discount=0.25, completion=8.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    ModelCard(
-        model="gpt-4.1-2025-04-14",
-        pricing=Pricing(text=TokenPrice(prompt=2.00, cached_discount=0.25, completion=8.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    ModelCard(
-        model="gpt-4.1-mini",
-        pricing=Pricing(text=TokenPrice(prompt=0.40, cached_discount=0.25, completion=1.60), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    ModelCard(
-        model="gpt-4.1-mini-2025-04-14",
-        pricing=Pricing(text=TokenPrice(prompt=0.40, cached_discount=0.25, completion=1.60), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    ModelCard(
-        model="gpt-4.1-nano",
-        pricing=Pricing(text=TokenPrice(prompt=0.10, cached_discount=0.25, completion=0.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    ModelCard(
-        model="gpt-4.1-nano-2025-04-14",
-        pricing=Pricing(text=TokenPrice(prompt=0.10, cached_discount=0.25, completion=0.40), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"], endpoints=["chat_completions", "responses", "assistants", "batch"], features=["streaming", "function_calling", "structured_outputs"]
-        ),
-        temperature_support=True,
-        reasoning_effort_support=False,
-    ),
-    # ----------------------
-    # gpt-4.5 family
-    # ----------------------
-    # ModelCard(
-    #     model="gpt-4.5-preview",
-    #     pricing=Pricing(
-    #         text=TokenPrice(prompt=75, cached_discount=0.5, completion=150.00),
-    #         audio=None,
-    #         ft_price_hike=1.5
-    #     ),
-    #     capabilities=ModelCapabilities(
-    #         modalities=["text", "image"],
-    #         endpoints=["chat_completions", "responses", "assistants", "batch"],
-    #         features=["streaming", "function_calling", "structured_outputs"]
-    #     ),
-    #     logprobs_support=False,
-    # ),
-    # ModelCard(
-    #     model="gpt-4.5-preview-2025-02-27",
-    #     pricing=Pricing(
-    #         text=TokenPrice(prompt=75, cached_discount=0.5, completion=150.00),
-    #         audio=None,
-    #         ft_price_hike=1.5
-    #     ),
-    #     capabilities=ModelCapabilities(
-    #         modalities=["text", "image"],
-    #         endpoints=["chat_completions", "responses", "assistants", "batch"],
-    #         features=["streaming", "function_calling", "structured_outputs"]
-    #     ),
-    #     logprobs_support=False,
-    # ),
-    # ----------------------
-    # gpt-4o family
-    # ----------------------
-    ModelCard(
-        model="chatgpt-4o-latest",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning", "distillation", "predicted_outputs"],
-        ),
-    ),
-    ModelCard(
-        model="gpt-4o",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning", "distillation", "predicted_outputs"],
-        ),
-    ),
-    ModelCard(
-        model="gpt-4o-2024-08-06",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning", "distillation", "predicted_outputs"],
-        ),
-    ),
-    ModelCard(
-        model="gpt-4o-2024-11-20",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning", "distillation", "predicted_outputs"],
-        ),
-    ),
-    ModelCard(
-        model="gpt-4o-2024-05-13",
-        pricing=Pricing(text=TokenPrice(prompt=5.00, cached_discount=0.5, completion=15.00), audio=None, ft_price_hike=1.5),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning", "distillation", "predicted_outputs"],
-        ),
-    ),
-    # ----------------------
-    # gpt-4o-audio family
-    # ----------------------
-    ModelCard(
-        model="gpt-4o-audio-preview-2024-12-17",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=TokenPrice(prompt=40.00, cached_discount=0.2, completion=80.00)),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="gpt-4o-audio-preview-2024-10-01",
-        pricing=Pricing(text=TokenPrice(prompt=2.50, cached_discount=0.5, completion=10.00), audio=TokenPrice(prompt=100.00, cached_discount=0.2, completion=200.00)),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="gpt-4o-realtime-preview-2024-12-17",
-        pricing=Pricing(text=TokenPrice(prompt=5.00, cached_discount=0.5, completion=20.00), audio=TokenPrice(prompt=40.00, cached_discount=0.2, completion=80.00)),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="gpt-4o-realtime-preview-2024-10-01",
-        pricing=Pricing(text=TokenPrice(prompt=5.00, cached_discount=0.5, completion=20.00), audio=TokenPrice(prompt=100.00, cached_discount=0.2, completion=200.00)),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    # ----------------------
-    # gpt-4o-mini family
-    # ----------------------
-    ModelCard(
-        model="gpt-4o-mini",
-        pricing=Pricing(text=TokenPrice(prompt=0.15, cached_discount=0.5, completion=0.60), audio=None, ft_price_hike=2.0),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning"],
-        ),
-    ),
-    ModelCard(
-        model="gpt-4o-mini-2024-07-18",
-        pricing=Pricing(text=TokenPrice(prompt=0.15, cached_discount=0.5, completion=0.60), audio=None, ft_price_hike=2.0),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image"],
-            endpoints=["chat_completions", "responses", "assistants", "batch", "fine_tuning"],
-            features=["streaming", "function_calling", "structured_outputs", "fine_tuning"],
-        ),
-    ),
-    # ----------------------
-    # gpt-4o-mini-audio family
-    # ----------------------
-    ModelCard(
-        model="gpt-4o-mini-audio-preview-2024-12-17",
-        pricing=Pricing(
-            text=TokenPrice(prompt=0.15, cached_discount=0.5, completion=0.60), audio=TokenPrice(prompt=10.00, cached_discount=0.2, completion=20.00), ft_price_hike=2.0
-        ),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="gpt-4o-mini-realtime-preview-2024-12-17",
-        pricing=Pricing(
-            text=TokenPrice(prompt=0.60, cached_discount=0.5, completion=2.40), audio=TokenPrice(prompt=10.00, cached_discount=0.2, completion=20.00), ft_price_hike=2.0
-        ),
-        capabilities=ModelCapabilities(modalities=["text", "audio"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-]
-
-# Anthropic Model Cards
-anthropic_model_cards = [
-    ModelCard(
-        model="claude-3-5-sonnet-20241022",
-        pricing=Pricing(text=TokenPrice(prompt=3.00, cached_discount=0.5, completion=15.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="claude-3-5-haiku-20241022",
-        pricing=Pricing(text=TokenPrice(prompt=0.80, cached_discount=0.5, completion=4.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="claude-3-opus-20240229",
-        pricing=Pricing(text=TokenPrice(prompt=15.00, cached_discount=0.5, completion=75.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="claude-3-sonnet-20240229",
-        pricing=Pricing(text=TokenPrice(prompt=3.00, cached_discount=0.5, completion=15.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="claude-3-haiku-20240307",
-        pricing=Pricing(text=TokenPrice(prompt=0.25, cached_discount=0.5, completion=1.25), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-]
-
-# xAI model cards
-xai_model_cards = [
-    ModelCard(
-        model="grok-2-vision-1212",
-        pricing=Pricing(text=TokenPrice(prompt=2.00, cached_discount=0.5, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="grok-2-1212",
-        pricing=Pricing(text=TokenPrice(prompt=2.00, cached_discount=0.5, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="grok-3-beta",
-        pricing=Pricing(text=TokenPrice(prompt=3.00, cached_discount=0.5, completion=15.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-    ModelCard(
-        model="grok-3-mini-beta",
-        pricing=Pricing(text=TokenPrice(prompt=0.30, cached_discount=0.5, completion=0.50), audio=None),
-        capabilities=ModelCapabilities(modalities=["text"], endpoints=["chat_completions"], features=["streaming", "function_calling"]),
-    ),
-]
-
-# Add Gemini model cards
-gemini_model_cards = [
-    # ----------------------
-    # gemini-2.5-pro-exp-03-25 family
-    # ----------------------
-    ModelCard(
-        model="gemini-2.5-pro-exp-03-25",
-        pricing=Pricing(text=TokenPrice(prompt=1.25, cached_discount=0.25, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-        temperature_support=True,
-    ),
-    ModelCard(
-        model="gemini-2.5-pro-preview-06-05",
-        pricing=Pricing(text=TokenPrice(prompt=1.25, cached_discount=0.25, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-    ),
-    ModelCard(
-        model="gemini-2.5-pro-preview-05-06",
-        pricing=Pricing(text=TokenPrice(prompt=1.25, cached_discount=0.25, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-    ),
-    ModelCard(
-        model="gemini-2.5-pro-preview-03-25",
-        pricing=Pricing(text=TokenPrice(prompt=1.25, cached_discount=0.25, completion=10.00), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-        temperature_support=True,
-    ),
-    ModelCard(
-        model="gemini-2.5-flash-preview-04-17",
-        pricing=Pricing(text=TokenPrice(prompt=0.15, cached_discount=0.25, completion=0.60), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-        temperature_support=True,
-    ),
-    ModelCard(
-        model="gemini-2.5-flash-preview-05-20",
-        pricing=Pricing(text=TokenPrice(prompt=0.15, cached_discount=0.25, completion=0.60), audio=None),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-        temperature_support=True,
-    ),
-    # ----------------------
-    # gemini-2.0-flash family
-    # ----------------------
-    ModelCard(
-        model="gemini-2.0-flash",
-        pricing=Pricing(text=TokenPrice(prompt=0.1, cached_discount=0.025 / 0.1, completion=0.40), audio=TokenPrice(prompt=0.7, cached_discount=0.175 / 0.7, completion=1000)),
-        capabilities=ModelCapabilities(modalities=["text", "image"], endpoints=["chat_completions"], features=["streaming", "function_calling", "structured_outputs"]),
-        temperature_support=True,
-    ),
-    ModelCard(
-        model="gemini-2.0-flash-lite",
-        pricing=Pricing(text=TokenPrice(prompt=0.075, cached_discount=1.0, completion=0.30), audio=TokenPrice(prompt=0.075, cached_discount=1.0, completion=1000)),
-        capabilities=ModelCapabilities(
-            modalities=["text", "image", "audio"],
-            endpoints=["chat_completions"],
-            features=["streaming", "structured_outputs"],
-        ),
-        temperature_support=True,
-    ),
-]
-
-
-model_cards = openai_model_cards + gemini_model_cards + xai_model_cards
-xAI_model_cards = [
-    # ----------------------
-    # grok3-family
-    # ----------------------
-    ModelCard(
-        model="grok-3-beta",
-        pricing=Pricing(text=TokenPrice(prompt=3, cached_discount=1.0, completion=15), audio=None),
-        capabilities=ModelCapabilities(
-            modalities=["text"],
-            endpoints=["chat_completions"],
-            features=["streaming", "structured_outputs"],
-        ),
-        temperature_support=True,
-    ),
-    ModelCard(
-        model="grok-3-mini-beta",
-        pricing=Pricing(text=TokenPrice(prompt=0.3, cached_discount=1.0, completion=0.5), audio=None),
-        capabilities=ModelCapabilities(
-            modalities=["text"],
-            endpoints=["chat_completions"],
-            features=["streaming", "structured_outputs"],
-        ),
-        temperature_support=True,
-    ),
-]
-
-
-model_cards = openai_model_cards + gemini_model_cards + xAI_model_cards
-
-
-def get_model_card(model: str) -> ModelCard:
-    """
-    Get the model card for a specific model.
-
-    Args:
-        model: The model name to look up
-
-    Returns:
-        The ModelCard for the specified model
-
-    Raises:
-        ValueError: If no model card is found for the specified model
-    """
-    # Extract base model name for fine-tuned models like "ft:gpt-4o:retab:4389573"
-    if model.startswith("ft:"):
-        # Split by colon and take the second part (index 1) which contains the base model
-        parts = model.split(":")
-        if len(parts) > 1:
-            model = parts[1]
-
-    for card in model_cards:
-        if card.model == model:
-            return card
-
-    raise ValueError(f"No model card found for model: {model}")
+    permissions: ModelCardPermissions = ModelCardPermissions()
+
+    @computed_field
+    @property
+    def is_finetuned(self) -> bool:
+        if "ft:" in self.model:
+            return True
+        return False

retab/types/automations/webhooks.py

@@ -2,20 +2,20 @@ from typing import Any, Optional
 
 from pydantic import BaseModel, EmailStr
 
-from retab.types.documents.extractions import UiParsedChatCompletion
+from retab.types.documents.extractions import RetabParsedChatCompletion
 
 from ..mime import BaseMIMEData, MIMEData
 
 
 class WebhookRequest(BaseModel):
-    completion: UiParsedChatCompletion
+    completion: RetabParsedChatCompletion
     user: Optional[EmailStr] = None
     file_payload: MIMEData
     metadata: Optional[dict[str, Any]] = None
 
 
 class BaseWebhookRequest(BaseModel):
-    completion: UiParsedChatCompletion
+    completion: RetabParsedChatCompletion
     user: Optional[EmailStr] = None
     file_payload: BaseMIMEData
     metadata: Optional[dict[str, Any]] = None