fix install litellm

This commit is contained in:
Ishaan Jaffer 2025-11-21 16:15:09 -08:00
parent 0abfb07ab8
commit 4205b7caeb
2 changed files with 185 additions and 3 deletions

View file

@ -51,7 +51,11 @@ from litellm.types.llms.openai import (
ChatCompletionToolCallFunctionChunk,
ChatCompletionUsageBlock,
)
from litellm.types.utils import ChatCompletionMessageToolCall, Choices, Delta
from litellm.types.utils import (
ChatCompletionMessageToolCall,
Choices,
Delta,
)
from litellm.types.utils import GenericStreamingChunk as GChunk
from litellm.types.utils import (
ModelResponse,
@ -1260,7 +1264,7 @@ class AWSEventStreamDecoder:
def _handle_converse_start_event(
self,
start_obj: ContentBlockStartEvent,
) -> tuple[
) -> Tuple[
Optional[ChatCompletionToolCallChunk],
dict,
Optional[
@ -1320,7 +1324,7 @@ class AWSEventStreamDecoder:
self,
delta_obj: ContentBlockDeltaEvent,
index: int,
) -> tuple[
) -> Tuple[
str,
Optional[ChatCompletionToolCallChunk],
dict,

View file

@ -11367,6 +11367,39 @@
"supports_web_search": true,
"tpm": 8000000
},
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 65536,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true
},
"gemini-2.5-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,
@ -13071,6 +13104,39 @@
"supports_web_search": true,
"tpm": 8000000
},
"gemini/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 65536,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true
},
"gemini/gemini-2.5-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,
@ -24557,6 +24623,20 @@
"output_cost_per_image": 0.039,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image"
},
"vertex_ai/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 65536,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
},
"vertex_ai/imagegeneration@006": {
"litellm_provider": "vertex_ai-image-models",
"mode": "image_generation",
@ -26099,6 +26179,104 @@
"supports_tool_choice": true,
"supports_web_search": true
},
"xai/grok-4-1-fast": {
"cache_read_input_token_cost": 0.05e-06,
"input_cost_per_token": 0.2e-06,
"input_cost_per_token_above_128k_tokens": 0.4e-06,
"litellm_provider": "xai",
"max_input_tokens": 2e6,
"max_output_tokens": 2e6,
"max_tokens": 2e6,
"mode": "chat",
"output_cost_per_token": 0.5e-06,
"output_cost_per_token_above_128k_tokens": 1e-06,
"source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4-1-fast-reasoning": {
"cache_read_input_token_cost": 0.05e-06,
"input_cost_per_token": 0.2e-06,
"input_cost_per_token_above_128k_tokens": 0.4e-06,
"litellm_provider": "xai",
"max_input_tokens": 2e6,
"max_output_tokens": 2e6,
"max_tokens": 2e6,
"mode": "chat",
"output_cost_per_token": 0.5e-06,
"output_cost_per_token_above_128k_tokens": 1e-06,
"source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4-1-fast-reasoning-latest": {
"cache_read_input_token_cost": 0.05e-06,
"input_cost_per_token": 0.2e-06,
"input_cost_per_token_above_128k_tokens": 0.4e-06,
"litellm_provider": "xai",
"max_input_tokens": 2e6,
"max_output_tokens": 2e6,
"max_tokens": 2e6,
"mode": "chat",
"output_cost_per_token": 0.5e-06,
"output_cost_per_token_above_128k_tokens": 1e-06,
"source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4-1-fast-non-reasoning": {
"cache_read_input_token_cost": 0.05e-06,
"input_cost_per_token": 0.2e-06,
"input_cost_per_token_above_128k_tokens": 0.4e-06,
"litellm_provider": "xai",
"max_input_tokens": 2e6,
"max_output_tokens": 2e6,
"max_tokens": 2e6,
"mode": "chat",
"output_cost_per_token": 0.5e-06,
"output_cost_per_token_above_128k_tokens": 1e-06,
"source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4-1-fast-non-reasoning-latest": {
"cache_read_input_token_cost": 0.05e-06,
"input_cost_per_token": 0.2e-06,
"input_cost_per_token_above_128k_tokens": 0.4e-06,
"litellm_provider": "xai",
"max_input_tokens": 2e6,
"max_output_tokens": 2e6,
"max_tokens": 2e6,
"mode": "chat",
"output_cost_per_token": 0.5e-06,
"output_cost_per_token_above_128k_tokens": 1e-06,
"source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-beta": {
"input_cost_per_token": 5e-06,
"litellm_provider": "xai",