LLM-Bridge 2.2.0__tar.gz → 2.2.2__tar.gz

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: LLM-Bridge
-Version: 2.2.0
+Version: 2.2.2
 Summary: A library that wraps multiple LLM providers into a consistent API while using each provider's native SDK internally, supporting multimodal I/O, file processing, and stream output.
 Author-email: windsnow1025 <windsnow1025@gmail.com>
 License-Expression: MIT

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/llm_bridge/client/implementations/claude/non_stream_claude_client.py

@@ -21,6 +21,7 @@ class NonStreamClaudeClient(ClaudeClient):
                 tools=self.tools,
                 cache_control=self.cache_control,
                 thinking=self.thinking,
+                speed=self.speed,
                 output_config=self.output_config,
             )
 

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/llm_bridge/client/implementations/claude/stream_claude_client.py

@@ -41,6 +41,7 @@ class StreamClaudeClient(ClaudeClient):
                 tools=self.tools,
                 cache_control=self.cache_control,
                 thinking=self.thinking,
+                speed=self.speed,
                 output_config=self.output_config,
                 stream=True,
             )

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/llm_bridge/client/model_client/claude_client.py

@@ -1,4 +1,5 @@
 from collections.abc import AsyncGenerator
+from typing import Literal
 
 import anthropic
 from anthropic import Omit
@@ -23,6 +24,7 @@ class ClaudeClient(ChatClient):
             tools: list[BetaToolUnionParam],
             cache_control: BetaCacheControlEphemeralParam,
             thinking: BetaThinkingConfigParam | Omit,
+            speed: Literal["standard", "fast"] | Omit,
             output_config: BetaOutputConfigParam | Omit,
     ):
         self.model = model
@@ -34,6 +36,7 @@ class ClaudeClient(ChatClient):
         self.tools = tools
         self.cache_control = cache_control
         self.thinking = thinking
+        self.speed = speed
         self.output_config = output_config
 
     async def generate_non_stream_response(self) -> ChatResponse:

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/llm_bridge/logic/chat_generate/model_client_factory/claude_client_factory.py

@@ -1,4 +1,4 @@
-from typing import Any
+from typing import Any, Literal
 
 import anthropic
 from anthropic import Omit, transform_schema
@@ -62,6 +62,10 @@ async def create_claude_client(
         thinking = BetaThinkingConfigAdaptiveParam(type="adaptive", display="summarized")
 
     betas: list[AnthropicBetaParam] | Omit = omit
+    speed: Literal["standard", "fast"] | Omit = omit
+    if model in ["claude-opus-5-5"]:
+        betas = ["fast-mode-2026-02-01"]
+        speed = "fast"
 
     tools: list[BetaToolUnionParam] = []
     if web_search:
@@ -103,6 +107,7 @@ async def create_claude_client(
             tools=tools,
             cache_control=cache_control,
             thinking=thinking,
+            speed=speed,
             output_config=output_config,
         )
     else:
@@ -116,5 +121,6 @@ async def create_claude_client(
             tools=tools,
             cache_control=cache_control,
             thinking=thinking,
+            speed=speed,
             output_config=output_config,
         )

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/llm_bridge/resources/model_prices.json

@@ -1,4 +1,58 @@
 [
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-4-argon",
+    "input": 7.2,
+    "output": 36
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3.1-pro-preview",
+    "input": 7.2,
+    "output": 32.4
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-omni-flash-preview",
+    "input": 1.5,
+    "output": 17.5
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3.8-flash",
+    "input": 2.7,
+    "output": 13.5
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3.6-flash",
+    "input": 2.7,
+    "output": 13.5
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3-flash-preview",
+    "input": 1.8,
+    "output": 5.4
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3-pro-image",
+    "input": 3.6,
+    "output": 216
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-3.1-flash-image",
+    "input": 0.9,
+    "output": 108
+  },
+  {
+    "apiType": "Google AI Studio",
+    "model": "gemini-flash-latest",
+    "input": 1,
+    "output": 2.5
+  },
   {
     "apiType": "Grok",
     "model": "grok-4.7",
@@ -68,8 +122,8 @@
   {
     "apiType": "Claude",
     "model": "claude-opus-5-5",
-    "input": 4,
-    "output": 20
+    "input": 8,
+    "output": 40
   },
   {
     "apiType": "Claude",
@@ -89,6 +143,12 @@
     "input": 0.5,
     "output": 2.5
   },
+  {
+    "apiType": "Vertex AI",
+    "model": "gemini-4-argon",
+    "input": 7.2,
+    "output": 36
+  },
   {
     "apiType": "Vertex AI",
     "model": "gemini-3.1-pro-preview",
@@ -131,54 +191,6 @@
     "input": 0.9,
     "output": 108
   },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3.1-pro-preview",
-    "input": 7.2,
-    "output": 32.4
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-omni-flash-preview",
-    "input": 1.5,
-    "output": 17.5
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3.8-flash",
-    "input": 2.7,
-    "output": 13.5
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3.6-flash",
-    "input": 2.7,
-    "output": 13.5
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3-flash-preview",
-    "input": 1.8,
-    "output": 5.4
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3-pro-image",
-    "input": 3.6,
-    "output": 216
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-3.1-flash-image",
-    "input": 0.9,
-    "output": 108
-  },
-  {
-    "apiType": "Google AI Studio",
-    "model": "gemini-flash-latest",
-    "input": 1,
-    "output": 2.5
-  },
   {
     "apiType": "Google AI Studio Free Tier",
     "model": "gemini-3.8-flash",

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "LLM-Bridge"
-version = "2.2.0"
+version = "2.2.2"
 dependencies = [
     "fastapi",
     "httpx",

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/usage/single/config.py

@@ -161,10 +161,11 @@ messages = [
 ]
 
 # See /llm_bridge/resources/model_prices.json for available models
-model = "gpt-6-astra"
+# model = "gpt-6-astra"
 # model = "gpt-5.6-luna"
 # model = "gpt-4.1"
 # model = "gpt-audio-1.5"
+model = "gemini-4-argon"
 # model = "gemini-3.1-pro-preview"
 # model = "gemini-3-pro-image"
 # model = "gemini-3.1-flash-image"
@@ -175,8 +176,8 @@ model = "gpt-6-astra"
 
 # api_type = "Vertex AI"
 # api_type = "Google AI Studio Free Tier"
-# api_type = "Google AI Studio"
-api_type = "OpenAI"
+api_type = "Google AI Studio"
+# api_type = "OpenAI"
 # api_type = "OpenAI-Azure"
 # api_type = "Claude"
 # api_type = "Grok"

{llm_bridge-2.2.0 → llm_bridge-2.2.2}/uv.lock

@@ -794,7 +794,7 @@ wheels = [
 
 [[package]]
 name = "llm-bridge"
-version = "2.2.0"
+version = "2.2.2"
 source = { editable = "." }
 dependencies = [
     { name = "anthropic" },