weave-python 0.27.0__py3-none-any.whl → 0.28.1__py3-none-any.whl

weave/weaveapi/llmx/v1/model_pb2_grpc.py

@@ -0,0 +1,2 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""

weave/weaveapi/llmx/v1/model_pb2_grpc.pyi

@@ -0,0 +1,20 @@
+"""
+@generated by mypy-protobuf.  Do not edit manually!
+isort:skip_file
+"""
+
+import abc
+import collections.abc
+import grpc
+import grpc.aio
+import typing
+
+_T = typing.TypeVar("_T")
+
+class _MaybeAsyncIterator(
+    collections.abc.AsyncIterator[_T],
+    collections.abc.Iterator[_T],
+    metaclass=abc.ABCMeta,
+): ...
+class _ServicerContext(grpc.ServicerContext, grpc.aio.ServicerContext):  # type: ignore[misc, type-arg]
+    ...

weave/weaveapi/llmx/v1/pricing_pb2.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# NO CHECKED-IN PROTOBUF GENCODE
+# source: weaveapi/llmx/v1/pricing.proto
+# Protobuf Python Version: 6.32.0
+"""Generated protocol buffer code."""
+
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import runtime_version as _runtime_version
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+
+_runtime_version.ValidateProtobufRuntimeVersion(
+    _runtime_version.Domain.PUBLIC, 6, 32, 0, "", "weaveapi/llmx/v1/pricing.proto"
+)
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(
+    b'\n\x1eweaveapi/llmx/v1/pricing.proto\x12\x10weaveapi.llmx.v1"\xdc\x01\n\x07Pricing\x12\x1a\n\x08\x63urrency\x18\x01 \x01(\tR\x08\x63urrency\x12\x33\n\x05items\x18\x02 \x03(\x0b\x32\x1d.weaveapi.llmx.v1.PricingItemR\x05items\x12\x43\n\x08metadata\x18\x03 \x03(\x0b\x32\'.weaveapi.llmx.v1.Pricing.MetadataEntryR\x08metadata\x1a;\n\rMetadataEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"c\n\tTokenBand\x12*\n\x11min_prompt_tokens\x18\x01 \x01(\x03R\x0fminPromptTokens\x12*\n\x11max_prompt_tokens\x18\x02 \x01(\x03R\x0fmaxPromptTokens"\x83\x04\n\x0bPricingItem\x12=\n\x08\x63\x61tegory\x18\x01 \x01(\x0e\x32!.weaveapi.llmx.v1.PricingCategoryR\x08\x63\x61tegory\x12\x31\n\x04tier\x18\x02 \x01(\x0e\x32\x1d.weaveapi.llmx.v1.PricingTierR\x04tier\x12\x39\n\toperation\x18\x03 \x01(\x0e\x32\x1b.weaveapi.llmx.v1.OperationR\toperation\x12\x14\n\x05price\x18\x04 \x01(\x01R\x05price\x12/\n\x04unit\x18\x05 \x01(\x0e\x32\x1b.weaveapi.llmx.v1.PriceUnitR\x04unit\x12\x18\n\x07quality\x18\x06 \x01(\tR\x07quality\x12\x1e\n\nresolution\x18\x07 \x01(\tR\nresolution\x12:\n\ntoken_band\x18\x08 \x01(\x0b\x32\x1b.weaveapi.llmx.v1.TokenBandR\ttokenBand\x12\x38\n\x18includes_thinking_tokens\x18\t \x01(\x08R\x16includesThinkingTokens\x12\x1b\n\ttool_name\x18\n \x01(\tR\x08toolName\x12\x1d\n\ntoken_type\x18\x0b \x01(\tR\ttokenType\x12\x14\n\x05notes\x18\x0c \x01(\tR\x05notes*\xc0\x02\n\x0fPricingCategory\x12 \n\x1cPRICING_CATEGORY_UNSPECIFIED\x10\x00\x12\x19\n\x15PRICING_CATEGORY_TEXT\x10\x01\x12\x1a\n\x16PRICING_CATEGORY_IMAGE\x10\x02\x12\x1a\n\x16PRICING_CATEGORY_AUDIO\x10\x03\x12\x1e\n\x1aPRICING_CATEGORY_EMBEDDING\x10\x04\x12 \n\x1cPRICING_CATEGORY_FINE_TUNING\x10\x05\x12\x19\n\x15PRICING_CATEGORY_TOOL\x10\x06\x12\x1d\n\x19PRICING_CATEGORY_REALTIME\x10\x07\x12\x1f\n\x1bPRICING_CATEGORY_MODERATION\x10\x08\x12\x1b\n\x17PRICING_CATEGORY_LEGACY\x10\t*\xc4\x01\n\x0bPricingTier\x12\x1c\n\x18PRICING_TIER_UNSPECIFIED\x10\x00\x12\x15\n\x11PRICING_TIER_FREE\x10\x01\x12\x16\n\x12PRICING_TIER_BATCH\x10\x02\x12\x15\n\x11PRICING_TIER_FLEX\x10\x03\x12\x19\n\x15PRICING_TIER_STANDARD\x10\x04\x12\x19\n\x15PRICING_TIER_PRIORITY\x10\x05\x12\x1b\n\x17PRICING_TIER_ENTERPRISE\x10\x06*\xab\x02\n\tOperation\x12\x19\n\x15OPERATION_UNSPECIFIED\x10\x00\x12\x13\n\x0fOPERATION_INPUT\x10\x01\x12\x14\n\x10OPERATION_OUTPUT\x10\x02\x12\x1a\n\x16OPERATION_CACHED_INPUT\x10\x03\x12\x18\n\x14OPERATION_CACHE_READ\x10\x04\x12\x19\n\x15OPERATION_CACHE_WRITE\x10\x05\x12\x16\n\x12OPERATION_TRAINING\x10\x06\x12\x15\n\x11OPERATION_STORAGE\x10\x07\x12#\n\x1fOPERATION_CONTEXT_CACHE_STORAGE\x10\x08\x12\x16\n\x12OPERATION_PER_CALL\x10\t\x12\x1b\n\x17OPERATION_PER_CONTAINER\x10\n*\x86\x02\n\tPriceUnit\x12\x1a\n\x16PRICE_UNIT_UNSPECIFIED\x10\x00\x12\x1c\n\x18PRICE_UNIT_PER_1M_TOKENS\x10\x01\x12\x18\n\x14PRICE_UNIT_PER_IMAGE\x10\x02\x12\x19\n\x15PRICE_UNIT_PER_MINUTE\x10\x03\x12 \n\x1cPRICE_UNIT_PER_1M_CHARACTERS\x10\x04\x12\x17\n\x13PRICE_UNIT_PER_CALL\x10\x05\x12\x19\n\x15PRICE_UNIT_PER_GB_DAY\x10\x06\x12\x17\n\x13PRICE_UNIT_PER_HOUR\x10\x07\x12\x1b\n\x17PRICE_UNIT_PER_1K_CALLS\x10\x08\x42\xbc\x01\n\x14\x63om.weaveapi.llmx.v1B\x0cPricingProtoP\x01Z4github.com/weave-labs/weave-go/weaveapi/llmx/v1;llmx\xa2\x02\x03WLX\xaa\x02\x10Weaveapi.Llmx.V1\xca\x02\x10Weaveapi\\Llmx\\V1\xe2\x02\x1cWeaveapi\\Llmx\\V1\\GPBMetadata\xea\x02\x12Weaveapi::Llmx::V1b\x06proto3'
+)
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(
+    DESCRIPTOR, "weaveapi.llmx.v1.pricing_pb2", _globals
+)
+if not _descriptor._USE_C_DESCRIPTORS:
+    _globals["DESCRIPTOR"]._loaded_options = None
+    _globals[
+        "DESCRIPTOR"
+    ]._serialized_options = b"\n\024com.weaveapi.llmx.v1B\014PricingProtoP\001Z4github.com/weave-labs/weave-go/weaveapi/llmx/v1;llmx\242\002\003WLX\252\002\020Weaveapi.Llmx.V1\312\002\020Weaveapi\\Llmx\\V1\342\002\034Weaveapi\\Llmx\\V1\\GPBMetadata\352\002\022Weaveapi::Llmx::V1"
+    _globals["_PRICING_METADATAENTRY"]._loaded_options = None
+    _globals["_PRICING_METADATAENTRY"]._serialized_options = b"8\001"
+    _globals["_PRICINGCATEGORY"]._serialized_start = 895
+    _globals["_PRICINGCATEGORY"]._serialized_end = 1215
+    _globals["_PRICINGTIER"]._serialized_start = 1218
+    _globals["_PRICINGTIER"]._serialized_end = 1414
+    _globals["_OPERATION"]._serialized_start = 1417
+    _globals["_OPERATION"]._serialized_end = 1716
+    _globals["_PRICEUNIT"]._serialized_start = 1719
+    _globals["_PRICEUNIT"]._serialized_end = 1981
+    _globals["_PRICING"]._serialized_start = 53
+    _globals["_PRICING"]._serialized_end = 273
+    _globals["_PRICING_METADATAENTRY"]._serialized_start = 214
+    _globals["_PRICING_METADATAENTRY"]._serialized_end = 273
+    _globals["_TOKENBAND"]._serialized_start = 275
+    _globals["_TOKENBAND"]._serialized_end = 374
+    _globals["_PRICINGITEM"]._serialized_start = 377
+    _globals["_PRICINGITEM"]._serialized_end = 892
+# @@protoc_insertion_point(module_scope)

weave/weaveapi/llmx/v1/pricing_pb2.pyi

@@ -0,0 +1,597 @@
+"""
+@generated by mypy-protobuf.  Do not edit manually!
+isort:skip_file
+"""
+
+import builtins
+import collections.abc
+import google.protobuf.descriptor
+import google.protobuf.internal.containers
+import google.protobuf.internal.enum_type_wrapper
+import google.protobuf.message
+import sys
+import typing
+
+if sys.version_info >= (3, 10):
+    import typing as typing_extensions
+else:
+    import typing_extensions
+
+DESCRIPTOR: google.protobuf.descriptor.FileDescriptor
+
+class _PricingCategory:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _PricingCategoryEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[
+        _PricingCategory.ValueType
+    ],
+    builtins.type,
+):
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    PRICING_CATEGORY_UNSPECIFIED: _PricingCategory.ValueType  # 0
+    """Default/unknown category"""
+    PRICING_CATEGORY_TEXT: _PricingCategory.ValueType  # 1
+    """Text generation models (GPT-4, Claude, etc.)
+    Example: GPT-4o, GPT-4o-mini for chat/completion
+    """
+    PRICING_CATEGORY_IMAGE: _PricingCategory.ValueType  # 2
+    """Image understanding/analysis models
+    Example: GPT-4-vision analyzing uploaded images
+    """
+    PRICING_CATEGORY_AUDIO: _PricingCategory.ValueType  # 3
+    """Audio models for speech-to-text and text-to-speech
+    Example: Whisper for transcription, TTS models for voice synthesis
+    """
+    PRICING_CATEGORY_EMBEDDING: _PricingCategory.ValueType  # 4
+    """Embedding/vector models
+    Example: text-embedding-3-large for semantic search
+    """
+    PRICING_CATEGORY_FINE_TUNING: _PricingCategory.ValueType  # 5
+    """Fine-tuning costs for training custom models
+    Example: Training GPT-4o-mini-2024-07-18 on custom data
+    """
+    PRICING_CATEGORY_TOOL: _PricingCategory.ValueType  # 6
+    """Built-in or add-on tools and capabilities
+    Example: Web Search ($2/1k calls), Code Interpreter ($0.03/container)
+    """
+    PRICING_CATEGORY_REALTIME: _PricingCategory.ValueType  # 7
+    """Realtime/streaming API pricing
+    Example: WebSocket-based continuous interaction models
+    """
+    PRICING_CATEGORY_MODERATION: _PricingCategory.ValueType  # 8
+    """Content moderation models
+    Example: OpenAI moderation endpoint for content filtering
+    """
+    PRICING_CATEGORY_LEGACY: _PricingCategory.ValueType  # 9
+    """Deprecated/legacy models with special pricing
+    Example: GPT-3.5-turbo-0301 (older version)
+    """
+
+class PricingCategory(_PricingCategory, metaclass=_PricingCategoryEnumTypeWrapper):
+    """PricingCategory defines the type of AI capability being priced."""
+
+PRICING_CATEGORY_UNSPECIFIED: PricingCategory.ValueType  # 0
+"""Default/unknown category"""
+PRICING_CATEGORY_TEXT: PricingCategory.ValueType  # 1
+"""Text generation models (GPT-4, Claude, etc.)
+Example: GPT-4o, GPT-4o-mini for chat/completion
+"""
+PRICING_CATEGORY_IMAGE: PricingCategory.ValueType  # 2
+"""Image understanding/analysis models
+Example: GPT-4-vision analyzing uploaded images
+"""
+PRICING_CATEGORY_AUDIO: PricingCategory.ValueType  # 3
+"""Audio models for speech-to-text and text-to-speech
+Example: Whisper for transcription, TTS models for voice synthesis
+"""
+PRICING_CATEGORY_EMBEDDING: PricingCategory.ValueType  # 4
+"""Embedding/vector models
+Example: text-embedding-3-large for semantic search
+"""
+PRICING_CATEGORY_FINE_TUNING: PricingCategory.ValueType  # 5
+"""Fine-tuning costs for training custom models
+Example: Training GPT-4o-mini-2024-07-18 on custom data
+"""
+PRICING_CATEGORY_TOOL: PricingCategory.ValueType  # 6
+"""Built-in or add-on tools and capabilities
+Example: Web Search ($2/1k calls), Code Interpreter ($0.03/container)
+"""
+PRICING_CATEGORY_REALTIME: PricingCategory.ValueType  # 7
+"""Realtime/streaming API pricing
+Example: WebSocket-based continuous interaction models
+"""
+PRICING_CATEGORY_MODERATION: PricingCategory.ValueType  # 8
+"""Content moderation models
+Example: OpenAI moderation endpoint for content filtering
+"""
+PRICING_CATEGORY_LEGACY: PricingCategory.ValueType  # 9
+"""Deprecated/legacy models with special pricing
+Example: GPT-3.5-turbo-0301 (older version)
+"""
+global___PricingCategory = PricingCategory
+
+class _PricingTier:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _PricingTierEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_PricingTier.ValueType],
+    builtins.type,
+):
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    PRICING_TIER_UNSPECIFIED: _PricingTier.ValueType  # 0
+    """Default/unknown tier"""
+    PRICING_TIER_FREE: _PricingTier.ValueType  # 1
+    """Free tier with usage limits
+    Example: Free API credits for new users
+    """
+    PRICING_TIER_BATCH: _PricingTier.ValueType  # 2
+    """Batch processing with 50% discount, 24-hour turnaround
+    Example: GPT-4o batch API at $1.25/1M input tokens (vs $2.50 standard)
+    """
+    PRICING_TIER_FLEX: _PricingTier.ValueType  # 3
+    """Flexible/on-demand tier (between batch and standard)
+    Example: Variable pricing based on system load
+    """
+    PRICING_TIER_STANDARD: _PricingTier.ValueType  # 4
+    """Standard/regular pricing tier
+    Example: GPT-4o at $2.50/1M input tokens for real-time API
+    """
+    PRICING_TIER_PRIORITY: _PricingTier.ValueType  # 5
+    """Priority access with higher costs but guaranteed availability
+    Example: Reserved capacity with SLA guarantees
+    """
+    PRICING_TIER_ENTERPRISE: _PricingTier.ValueType  # 6
+    """Enterprise/custom pricing with negotiated rates
+    Example: Volume discounts for large organizations
+    """
+
+class PricingTier(_PricingTier, metaclass=_PricingTierEnumTypeWrapper):
+    """PricingTier represents different service levels with varying costs and SLAs."""
+
+PRICING_TIER_UNSPECIFIED: PricingTier.ValueType  # 0
+"""Default/unknown tier"""
+PRICING_TIER_FREE: PricingTier.ValueType  # 1
+"""Free tier with usage limits
+Example: Free API credits for new users
+"""
+PRICING_TIER_BATCH: PricingTier.ValueType  # 2
+"""Batch processing with 50% discount, 24-hour turnaround
+Example: GPT-4o batch API at $1.25/1M input tokens (vs $2.50 standard)
+"""
+PRICING_TIER_FLEX: PricingTier.ValueType  # 3
+"""Flexible/on-demand tier (between batch and standard)
+Example: Variable pricing based on system load
+"""
+PRICING_TIER_STANDARD: PricingTier.ValueType  # 4
+"""Standard/regular pricing tier
+Example: GPT-4o at $2.50/1M input tokens for real-time API
+"""
+PRICING_TIER_PRIORITY: PricingTier.ValueType  # 5
+"""Priority access with higher costs but guaranteed availability
+Example: Reserved capacity with SLA guarantees
+"""
+PRICING_TIER_ENTERPRISE: PricingTier.ValueType  # 6
+"""Enterprise/custom pricing with negotiated rates
+Example: Volume discounts for large organizations
+"""
+global___PricingTier = PricingTier
+
+class _Operation:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _OperationEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_Operation.ValueType],
+    builtins.type,
+):
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    OPERATION_UNSPECIFIED: _Operation.ValueType  # 0
+    """Default/unknown operation"""
+    OPERATION_INPUT: _Operation.ValueType  # 1
+    """Input/prompt tokens sent to the model
+    Example: User message in chat, $2.50/1M tokens for GPT-4o
+    """
+    OPERATION_OUTPUT: _Operation.ValueType  # 2
+    """Output/completion tokens generated by the model
+    Example: Model response, $10.00/1M tokens for GPT-4o
+    """
+    OPERATION_CACHED_INPUT: _Operation.ValueType  # 3
+    """Cached input tokens (discounted rate for repeated context)
+    Example: $1.25/1M tokens for GPT-4o cached prompt (50% discount)
+    """
+    OPERATION_CACHE_READ: _Operation.ValueType  # 4
+    """Reading from cache (if priced separately from cached input)
+    Example: Anthropic Claude cache read operations
+    """
+    OPERATION_CACHE_WRITE: _Operation.ValueType  # 5
+    """Writing to cache (creating cached context)
+    Example: Anthropic Claude cache creation fee
+    """
+    OPERATION_TRAINING: _Operation.ValueType  # 6
+    """Fine-tuning training cost (per token or per hour)
+    Example: $25.00/1M tokens or $3.00/hour for GPT-4o-mini training
+    """
+    OPERATION_STORAGE: _Operation.ValueType  # 7
+    """General storage costs
+    Example: Vector database storage for embeddings
+    """
+    OPERATION_CONTEXT_CACHE_STORAGE: _Operation.ValueType  # 8
+    """Context cache storage charged per time unit
+    Example: $0.10/GB/hour for maintaining cached contexts
+    """
+    OPERATION_PER_CALL: _Operation.ValueType  # 9
+    """Fixed price per API call regardless of tokens
+    Example: $0.00255/call for file search tool
+    """
+    OPERATION_PER_CONTAINER: _Operation.ValueType  # 10
+    """Per container/session pricing for isolated environments
+    Example: $0.03/container for Code Interpreter execution
+    """
+
+class Operation(_Operation, metaclass=_OperationEnumTypeWrapper):
+    """Operation defines the specific type of usage being priced."""
+
+OPERATION_UNSPECIFIED: Operation.ValueType  # 0
+"""Default/unknown operation"""
+OPERATION_INPUT: Operation.ValueType  # 1
+"""Input/prompt tokens sent to the model
+Example: User message in chat, $2.50/1M tokens for GPT-4o
+"""
+OPERATION_OUTPUT: Operation.ValueType  # 2
+"""Output/completion tokens generated by the model
+Example: Model response, $10.00/1M tokens for GPT-4o
+"""
+OPERATION_CACHED_INPUT: Operation.ValueType  # 3
+"""Cached input tokens (discounted rate for repeated context)
+Example: $1.25/1M tokens for GPT-4o cached prompt (50% discount)
+"""
+OPERATION_CACHE_READ: Operation.ValueType  # 4
+"""Reading from cache (if priced separately from cached input)
+Example: Anthropic Claude cache read operations
+"""
+OPERATION_CACHE_WRITE: Operation.ValueType  # 5
+"""Writing to cache (creating cached context)
+Example: Anthropic Claude cache creation fee
+"""
+OPERATION_TRAINING: Operation.ValueType  # 6
+"""Fine-tuning training cost (per token or per hour)
+Example: $25.00/1M tokens or $3.00/hour for GPT-4o-mini training
+"""
+OPERATION_STORAGE: Operation.ValueType  # 7
+"""General storage costs
+Example: Vector database storage for embeddings
+"""
+OPERATION_CONTEXT_CACHE_STORAGE: Operation.ValueType  # 8
+"""Context cache storage charged per time unit
+Example: $0.10/GB/hour for maintaining cached contexts
+"""
+OPERATION_PER_CALL: Operation.ValueType  # 9
+"""Fixed price per API call regardless of tokens
+Example: $0.00255/call for file search tool
+"""
+OPERATION_PER_CONTAINER: Operation.ValueType  # 10
+"""Per container/session pricing for isolated environments
+Example: $0.03/container for Code Interpreter execution
+"""
+global___Operation = Operation
+
+class _PriceUnit:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _PriceUnitEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_PriceUnit.ValueType],
+    builtins.type,
+):
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    PRICE_UNIT_UNSPECIFIED: _PriceUnit.ValueType  # 0
+    """Default/unknown unit"""
+    PRICE_UNIT_PER_1M_TOKENS: _PriceUnit.ValueType  # 1
+    """Price per million tokens (most common for LLMs)
+    Example: $2.50 per 1M input tokens
+    """
+    PRICE_UNIT_PER_IMAGE: _PriceUnit.ValueType  # 2
+    """Price per generated image
+    Example: DALL-E 3 at $0.040 per 1024x1024 image
+    """
+    PRICE_UNIT_PER_MINUTE: _PriceUnit.ValueType  # 3
+    """Price per minute of processing
+    Example: Whisper at $0.006 per minute of audio
+    """
+    PRICE_UNIT_PER_1M_CHARACTERS: _PriceUnit.ValueType  # 4
+    """Price per million characters (for text not tokenized)
+    Example: Some translation APIs charge per character
+    """
+    PRICE_UNIT_PER_CALL: _PriceUnit.ValueType  # 5
+    """Fixed price per API call
+    Example: Moderation at $0.001 per call
+    """
+    PRICE_UNIT_PER_GB_DAY: _PriceUnit.ValueType  # 6
+    """Storage price per GB per day
+    Example: File search storage at $0.20/GB/day
+    """
+    PRICE_UNIT_PER_HOUR: _PriceUnit.ValueType  # 7
+    """Price per hour (training or runtime)
+    Example: Fine-tuning at $3.00/hour for small models
+    """
+    PRICE_UNIT_PER_1K_CALLS: _PriceUnit.ValueType  # 8
+    """Price per thousand API calls
+    Example: Web search at $2.00 per 1k searches
+    """
+
+class PriceUnit(_PriceUnit, metaclass=_PriceUnitEnumTypeWrapper):
+    """PriceUnit specifies how the price is measured/charged."""
+
+PRICE_UNIT_UNSPECIFIED: PriceUnit.ValueType  # 0
+"""Default/unknown unit"""
+PRICE_UNIT_PER_1M_TOKENS: PriceUnit.ValueType  # 1
+"""Price per million tokens (most common for LLMs)
+Example: $2.50 per 1M input tokens
+"""
+PRICE_UNIT_PER_IMAGE: PriceUnit.ValueType  # 2
+"""Price per generated image
+Example: DALL-E 3 at $0.040 per 1024x1024 image
+"""
+PRICE_UNIT_PER_MINUTE: PriceUnit.ValueType  # 3
+"""Price per minute of processing
+Example: Whisper at $0.006 per minute of audio
+"""
+PRICE_UNIT_PER_1M_CHARACTERS: PriceUnit.ValueType  # 4
+"""Price per million characters (for text not tokenized)
+Example: Some translation APIs charge per character
+"""
+PRICE_UNIT_PER_CALL: PriceUnit.ValueType  # 5
+"""Fixed price per API call
+Example: Moderation at $0.001 per call
+"""
+PRICE_UNIT_PER_GB_DAY: PriceUnit.ValueType  # 6
+"""Storage price per GB per day
+Example: File search storage at $0.20/GB/day
+"""
+PRICE_UNIT_PER_HOUR: PriceUnit.ValueType  # 7
+"""Price per hour (training or runtime)
+Example: Fine-tuning at $3.00/hour for small models
+"""
+PRICE_UNIT_PER_1K_CALLS: PriceUnit.ValueType  # 8
+"""Price per thousand API calls
+Example: Web search at $2.00 per 1k searches
+"""
+global___PriceUnit = PriceUnit
+
+@typing.final
+class Pricing(google.protobuf.message.Message):
+    """Pricing represents the complete pricing structure for a model or service.
+    A single model may have multiple pricing items for different operations,
+    tiers, and use cases.
+    """
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    @typing.final
+    class MetadataEntry(google.protobuf.message.Message):
+        DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+        KEY_FIELD_NUMBER: builtins.int
+        VALUE_FIELD_NUMBER: builtins.int
+        key: builtins.str
+        value: builtins.str
+        def __init__(
+            self,
+            *,
+            key: builtins.str = ...,
+            value: builtins.str = ...,
+        ) -> None: ...
+        def ClearField(
+            self, field_name: typing.Literal["key", b"key", "value", b"value"]
+        ) -> None: ...
+
+    CURRENCY_FIELD_NUMBER: builtins.int
+    ITEMS_FIELD_NUMBER: builtins.int
+    METADATA_FIELD_NUMBER: builtins.int
+    currency: builtins.str
+    """Currency code for all prices in this message.
+    Examples: "USD", "EUR", "GBP"
+    """
+    @property
+    def items(
+        self,
+    ) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[
+        global___PricingItem
+    ]:
+        """List of all pricing entries for this model.
+        Each item represents a specific price point for a particular
+        operation/tier combination.
+        Example: One item for standard input tokens, another for batch input tokens
+        """
+
+    @property
+    def metadata(
+        self,
+    ) -> google.protobuf.internal.containers.ScalarMap[builtins.str, builtins.str]:
+        """Additional metadata as key-value pairs.
+        Common keys:
+        - "footnote": Additional pricing notes (e.g., "[1] Limited availability")
+        - "estimated_cost": Estimated costs for transcription models
+        - "source_url": URL where pricing was sourced from
+        - "last_updated": ISO 8601 timestamp of last update
+        """
+
+    def __init__(
+        self,
+        *,
+        currency: builtins.str = ...,
+        items: collections.abc.Iterable[global___PricingItem] | None = ...,
+        metadata: collections.abc.Mapping[builtins.str, builtins.str] | None = ...,
+    ) -> None: ...
+    def ClearField(
+        self,
+        field_name: typing.Literal[
+            "currency", b"currency", "items", b"items", "metadata", b"metadata"
+        ],
+    ) -> None: ...
+
+global___Pricing = Pricing
+
+@typing.final
+class TokenBand(google.protobuf.message.Message):
+    """TokenBand represents tiered pricing based on token count thresholds.
+    Some models have different rates based on cumulative token usage.
+    """
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    MIN_PROMPT_TOKENS_FIELD_NUMBER: builtins.int
+    MAX_PROMPT_TOKENS_FIELD_NUMBER: builtins.int
+    min_prompt_tokens: builtins.int
+    """Minimum number of prompt tokens for this pricing tier (inclusive).
+    Example: 0 for the first tier, 200001 for the "over 200k" tier
+    Set to 0 if not applicable or for the lowest tier
+    """
+    max_prompt_tokens: builtins.int
+    """Maximum number of prompt tokens for this pricing tier (inclusive).
+    Example: 200000 for "up to 200k tokens" tier
+    Set to 0 if unlimited or not applicable
+    """
+    def __init__(
+        self,
+        *,
+        min_prompt_tokens: builtins.int = ...,
+        max_prompt_tokens: builtins.int = ...,
+    ) -> None: ...
+    def ClearField(
+        self,
+        field_name: typing.Literal[
+            "max_prompt_tokens",
+            b"max_prompt_tokens",
+            "min_prompt_tokens",
+            b"min_prompt_tokens",
+        ],
+    ) -> None: ...
+
+global___TokenBand = TokenBand
+
+@typing.final
+class PricingItem(google.protobuf.message.Message):
+    """PricingItem represents a specific price point for a model/service.
+    Each item captures one pricing scenario with all relevant qualifiers.
+    """
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    CATEGORY_FIELD_NUMBER: builtins.int
+    TIER_FIELD_NUMBER: builtins.int
+    OPERATION_FIELD_NUMBER: builtins.int
+    PRICE_FIELD_NUMBER: builtins.int
+    UNIT_FIELD_NUMBER: builtins.int
+    QUALITY_FIELD_NUMBER: builtins.int
+    RESOLUTION_FIELD_NUMBER: builtins.int
+    TOKEN_BAND_FIELD_NUMBER: builtins.int
+    INCLUDES_THINKING_TOKENS_FIELD_NUMBER: builtins.int
+    TOOL_NAME_FIELD_NUMBER: builtins.int
+    TOKEN_TYPE_FIELD_NUMBER: builtins.int
+    NOTES_FIELD_NUMBER: builtins.int
+    category: global___PricingCategory.ValueType
+    """The type of AI capability this price applies to.
+    Example: PRICING_CATEGORY_TEXT for GPT-4o chat completion
+    """
+    tier: global___PricingTier.ValueType
+    """Service tier affecting price and SLA.
+    Example: PRICING_TIER_BATCH for 50% discounted async processing
+    """
+    operation: global___Operation.ValueType
+    """The specific operation being charged for.
+    Example: OPERATION_INPUT for prompt tokens, OPERATION_OUTPUT for completions
+    """
+    price: builtins.float
+    """The numeric cost amount.
+    Example: 2.50 for "$2.50 per 1M tokens"
+    """
+    unit: global___PriceUnit.ValueType
+    """The unit that the price applies to.
+    Example: PRICE_UNIT_PER_1M_TOKENS for token-based pricing
+    """
+    quality: builtins.str
+    """Optional qualifiers to disambiguate pricing variants:
+
+    Quality level for image generation.
+    Examples: "standard", "hd" for DALL-E, "low", "medium", "high" for others
+    """
+    resolution: builtins.str
+    """Image resolution for image generation pricing.
+    Examples: "1024x1024", "1792x1024", "1024x1792"
+    """
+    includes_thinking_tokens: builtins.bool
+    """Whether output pricing includes hidden reasoning tokens.
+    Example: true for o1-preview which charges for internal thinking
+    """
+    tool_name: builtins.str
+    """Name of the tool for PRICING_CATEGORY_TOOL items.
+    Examples: "Web Search", "File Search", "Code Interpreter"
+    """
+    token_type: builtins.str
+    """Token type for multi-modal pricing.
+    Examples: "text" vs "audio" for Whisper transcription models
+    """
+    notes: builtins.str
+    """Additional human-readable notes about this pricing.
+    Example: "Discounted pricing with data sharing enabled"
+    """
+    @property
+    def token_band(self) -> global___TokenBand:
+        """Token count thresholds for tiered pricing.
+        Example: Different rates for prompts over 200k tokens
+        """
+
+    def __init__(
+        self,
+        *,
+        category: global___PricingCategory.ValueType = ...,
+        tier: global___PricingTier.ValueType = ...,
+        operation: global___Operation.ValueType = ...,
+        price: builtins.float = ...,
+        unit: global___PriceUnit.ValueType = ...,
+        quality: builtins.str = ...,
+        resolution: builtins.str = ...,
+        token_band: global___TokenBand | None = ...,
+        includes_thinking_tokens: builtins.bool = ...,
+        tool_name: builtins.str = ...,
+        token_type: builtins.str = ...,
+        notes: builtins.str = ...,
+    ) -> None: ...
+    def HasField(
+        self, field_name: typing.Literal["token_band", b"token_band"]
+    ) -> builtins.bool: ...
+    def ClearField(
+        self,
+        field_name: typing.Literal[
+            "category",
+            b"category",
+            "includes_thinking_tokens",
+            b"includes_thinking_tokens",
+            "notes",
+            b"notes",
+            "operation",
+            b"operation",
+            "price",
+            b"price",
+            "quality",
+            b"quality",
+            "resolution",
+            b"resolution",
+            "tier",
+            b"tier",
+            "token_band",
+            b"token_band",
+            "token_type",
+            b"token_type",
+            "tool_name",
+            b"tool_name",
+            "unit",
+            b"unit",
+        ],
+    ) -> None: ...
+
+global___PricingItem = PricingItem

weave/weaveapi/llmx/v1/pricing_pb2_grpc.py

@@ -0,0 +1,2 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""