tokenbee-sdk 0.1.0__tar.gz → 0.2.1__tar.gz

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: tokenbee-sdk
-Version: 0.1.0
+Version: 0.2.1
 Summary: Official Python SDK for TokenBee LLM inference gateway and observability.
 Author: TokenBee Inc.
-Author-email: "TokenBee Inc." <hello@tokenbee.dev>
+Author-email: "TokenBee Inc." <founders@tokenbee.io>
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -35,9 +35,11 @@ pip install tokenbee-sdk
 ```python
 from tokenbee import TokenBee, TokenBeeModel, CompressionRate
 
-# Initialize the client
+# Initialize the client with your TokenBee API key 
+# AND your LLM provider key (Bring Your Own Key - BYOK)
 client = TokenBee(
-    api_key="your_api_key_here",
+    api_key="your_tokenbee_api_key",
+    llm_key="your_llm_provider_key", # e.g. OpenAI or Anthropic key
     compression="auto",
     rate=CompressionRate.MEDIUM
 )
@@ -55,6 +57,10 @@ response = client.send(
 print(response["choices"][0]["message"]["content"])
 ```
 
+## Bring Your Own Key (BYOK)
+
+TokenBee is a **stateless** gateway. We do not store your LLM provider API keys in our database. You pass your provider key (OpenAI, Anthropic, etc.) through the SDK's `llm_key` parameter. The SDK sends this in the `X-LLM-Key` header, allowing the TokenBee proxy to forward requests to the provider on your behalf while you maintain full control over your billing and security.
+
 ## Advanced Usage
 
 ### Compression Control

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/README.md

@@ -1,72 +1,78 @@
-# TokenBee Python SDK
-
-Official Python SDK for [TokenBee](https://tokenbee.dev) - The Intelligent LLM Inference Gateway with Observability, Compression, and Privacy.
-
-## Features
-
-- **Unified API**: Access multiple LLM providers (OpenAI, Anthropic, Google, Mistral, etc.) through a single interface.
-- **Intelligent Compression**: Reduce token usage and latency with context-aware compression.
-- **Privacy Guard**: Automatic PII masking and privacy-preserving inference.
-- **Built-in Observability**: Automatic tracking of latency, costs, and token usage.
-
-## Installation
-
-```bash
-pip install tokenbee-sdk
-```
-
-## Quick Start
-
-```python
-from tokenbee import TokenBee, TokenBeeModel, CompressionRate
-
-# Initialize the client
-client = TokenBee(
-    api_key="your_api_key_here",
-    compression="auto",
-    rate=CompressionRate.MEDIUM
-)
-
-# Send a request
-response = client.send(
-    model=TokenBeeModel.OPENAI_GPT_4O,
-    input={
-        "messages": [
-            {"role": "user", "content": "Explain quantum entanglement in simple terms."}
-        ]
-    }
-)
-
-print(response["choices"][0]["message"]["content"])
-```
-
-## Advanced Usage
-
-### Compression Control
-
-You can specify the compression rate and method per request:
-
-```python
-response = client.send(
-    model=TokenBeeModel.ANTHROPIC_CLAUDE_3_5_SONNET,
-    input={
-        "messages": [...],
-        "compression": "on",
-        "rate": CompressionRate.HIGH,
-        "privacy": True
-    }
-)
-```
-
-### Supported Models
-
-The SDK provides a `TokenBeeModel` enum with popular models:
-
-- `TokenBeeModel.OPENAI_GPT_4O`
-- `TokenBeeModel.ANTHROPIC_CLAUDE_3_5_SONNET`
-- `TokenBeeModel.GEMINI_2_0_FLASH`
-- ... and many others.
-
-## License
-
-MIT
+# TokenBee Python SDK
+
+Official Python SDK for [TokenBee](https://tokenbee.dev) - The Intelligent LLM Inference Gateway with Observability, Compression, and Privacy.
+
+## Features
+
+- **Unified API**: Access multiple LLM providers (OpenAI, Anthropic, Google, Mistral, etc.) through a single interface.
+- **Intelligent Compression**: Reduce token usage and latency with context-aware compression.
+- **Privacy Guard**: Automatic PII masking and privacy-preserving inference.
+- **Built-in Observability**: Automatic tracking of latency, costs, and token usage.
+
+## Installation
+
+```bash
+pip install tokenbee-sdk
+```
+
+## Quick Start
+
+```python
+from tokenbee import TokenBee, TokenBeeModel, CompressionRate
+
+# Initialize the client with your TokenBee API key 
+# AND your LLM provider key (Bring Your Own Key - BYOK)
+client = TokenBee(
+    api_key="your_tokenbee_api_key",
+    llm_key="your_llm_provider_key", # e.g. OpenAI or Anthropic key
+    compression="auto",
+    rate=CompressionRate.MEDIUM
+)
+
+# Send a request
+response = client.send(
+    model=TokenBeeModel.OPENAI_GPT_4O,
+    input={
+        "messages": [
+            {"role": "user", "content": "Explain quantum entanglement in simple terms."}
+        ]
+    }
+)
+
+print(response["choices"][0]["message"]["content"])
+```
+
+## Bring Your Own Key (BYOK)
+
+TokenBee is a **stateless** gateway. We do not store your LLM provider API keys in our database. You pass your provider key (OpenAI, Anthropic, etc.) through the SDK's `llm_key` parameter. The SDK sends this in the `X-LLM-Key` header, allowing the TokenBee proxy to forward requests to the provider on your behalf while you maintain full control over your billing and security.
+
+## Advanced Usage
+
+### Compression Control
+
+You can specify the compression rate and method per request:
+
+```python
+response = client.send(
+    model=TokenBeeModel.ANTHROPIC_CLAUDE_3_5_SONNET,
+    input={
+        "messages": [...],
+        "compression": "on",
+        "rate": CompressionRate.HIGH,
+        "privacy": True
+    }
+)
+```
+
+### Supported Models
+
+The SDK provides a `TokenBeeModel` enum with popular models:
+
+- `TokenBeeModel.OPENAI_GPT_4O`
+- `TokenBeeModel.ANTHROPIC_CLAUDE_3_5_SONNET`
+- `TokenBeeModel.GEMINI_2_0_FLASH`
+- ... and many others.
+
+## License
+
+MIT

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/pyproject.toml

@@ -1,22 +1,22 @@
-[build-system]
-requires = ["setuptools>=61.0"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "tokenbee-sdk"
-version = "0.1.0"
-authors = [
-  { name="TokenBee Inc.", email="hello@tokenbee.dev" },
-]
-description = "Official Python SDK for TokenBee LLM inference gateway and observability."
-readme = "README.md"
-requires-python = ">=3.7"
-classifiers = [
-    "Programming Language :: Python :: 3",
-    "License :: OSI Approved :: MIT License",
-    "Operating System :: OS Independent",
-]
-dependencies = [
-    "httpx>=0.23.0",
-]
-
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tokenbee-sdk"
+version = "0.2.1"
+authors = [
+  { name="TokenBee Inc.", email="founders@tokenbee.io" },
+]
+description = "Official Python SDK for TokenBee LLM inference gateway and observability."
+readme = "README.md"
+requires-python = ">=3.7"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "httpx>=0.23.0",
+]
+

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/setup.py

@@ -1,23 +1,23 @@
-from setuptools import setup, find_packages
-from pathlib import Path
-
-this_directory = Path(__file__).parent
-long_description = (this_directory / "README.md").read_text()
-
-setup(
-    name="tokenbee-sdk",
-    version="0.1.0",
-    packages=find_packages(),
-    install_requires=["httpx>=0.23.0"],
-    author="TokenBee Inc.",
-    author_email="hello@tokenbee.dev",
-    description="Official Python SDK for TokenBee LLM inference gateway and observability.",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    python_requires=">=3.7",
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "License :: OSI Approved :: MIT License",
-        "Operating System :: OS Independent",
-    ],
+from setuptools import setup, find_packages
+from pathlib import Path
+
+this_directory = Path(__file__).parent
+long_description = (this_directory / "README.md").read_text()
+
+setup(
+    name="tokenbee-sdk",
+    version="0.2.1",
+    packages=find_packages(),
+    install_requires=["httpx>=0.23.0"],
+    author="TokenBee Inc.",
+    author_email="founders@tokenbee.io",
+    description="Official Python SDK for TokenBee LLM inference gateway and observability.",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    python_requires=">=3.7",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
 )

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/tokenbee/__init__.py

@@ -1,99 +1,102 @@
-import httpx
-from enum import Enum
-
-class CompressionRate(str, Enum):
-    LOW = "0.75"
-    MEDIUM = "0.5"
-    HIGH = "0.33"
-    EXTREME = "0.2"
-
-class TokenBeeModel(str, Enum):
-    # OpenAI
-    OPENAI_GPT_4O = "openai/gpt-4o"
-    OPENAI_GPT_4O_MINI = "openai/gpt-4o-mini"
-    OPENAI_O1 = "openai/o1"
-    OPENAI_O1_MINI = "openai/o1-mini"
-    OPENAI_O3_MINI = "openai/o3-mini"
-
-    # Anthropic
-    ANTHROPIC_CLAUDE_4_6_SONNET = "anthropic/claude-4-6-sonnet-latest"
-    ANTHROPIC_CLAUDE_4_6_OPUS = "anthropic/claude-4-6-opus-latest"
-    ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic/claude-3-5-sonnet-latest"
-    ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3-5-haiku-latest"
-    ANTHROPIC_CLAUDE_3_OPUS = "anthropic/claude-3-opus-latest"
-
-    # Google
-    GEMINI_3_1_PRO = "google/gemini-3.1-pro"
-    GEMINI_3_1_FLASH = "google/gemini-3.1-flash"
-    GEMINI_2_0_FLASH = "google/gemini-2.0-flash"
-    GEMINI_2_0_PRO = "google/gemini-2.0-pro-exp"
-    GEMINI_1_5_PRO = "google/gemini-1.5-pro"
-    GEMINI_1_5_FLASH = "google/gemini-1.5-flash"
-
-    # Mistral
-    MISTRAL_LARGE = "mistral/mistral-large-latest"
-    MISTRAL_SMALL = "mistral/mistral-small-latest"
-    PIXTRAL_LARGE = "mistral/pixtral-large-latest"
-    MISTRAL_NEMO = "mistral/open-mistral-nemo"
-
-    # Perplexity
-    PERPLEXITY_SONAR = "perplexity/sonar"
-    PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro"
-    PERPLEXITY_SONAR_REASONING = "perplexity/sonar-reasoning"
-
-    # Groq
-    GROQ_LLAMA_3_3_70B = "groq/llama-3.3-70b-versatile"
-    GROQ_LLAMA_3_1_8B = "groq/llama-3.1-8b-instant"
-    GROQ_MIXTRAL_8X7B = "groq/mixtral-8x7b-32768"
-    GROQ_GEMMA2_9B = "groq/gemma2-9b-it"
-
-class TokenBee:
-    def __init__(
-        self, 
-        api_key: str, 
-        base_url: str = "https://api.tokenbee.dev/v1", 
-        compression: str = "auto", 
-        rate: str = CompressionRate.MEDIUM, 
-        model: str = "", 
-        provider: str = "",
-        privacy: bool = False
-    ):
-        self.api_key = api_key
-        self.base_url = base_url
-        self.headers = {
-            "Authorization": f"Bearer {api_key}",
-            "X-TokenBee-Compression": compression,
-            "X-TokenBee-Rate": rate,
-            "X-TokenBee-Privacy": str(privacy).lower()
-        }
-        if model:
-            self.headers["X-TokenBee-Model"] = model
-        if provider:
-            self.headers["X-TokenBee-Provider"] = provider
-
-        self.client = httpx.Client(headers=self.headers, base_url=self.base_url)
-
-    def send(self, model: str, input: dict):
-        parts = model.split("/")
-        provider = parts[0] if len(parts) > 1 else self.headers.get("X-TokenBee-Provider", "openai")
-        model_name = "/".join(parts[1:]) if len(parts) > 1 else parts[0]
-
-        headers = self.headers.copy()
-        headers["X-TokenBee-Model"] = model_name
-        headers["X-TokenBee-Provider"] = provider
-        
-        if "compression" in input:
-            headers["X-TokenBee-Compression"] = str(input["compression"])
-        if "rate" in input:
-            headers["X-TokenBee-Rate"] = str(input["rate"])
-        if "privacy" in input:
-            headers["X-TokenBee-Privacy"] = str(input["privacy"]).lower()
-
-        payload = input.copy()
-        payload.pop("compression", None)
-        payload.pop("rate", None)
-        payload.pop("privacy", None)
-
-        response = self.client.post("/chat/completions", json=payload, headers=headers)
-        response.raise_for_status()
-        return response.json()
+import httpx
+from enum import Enum
+
+class CompressionRate(str, Enum):
+    LOW = "0.75"
+    MEDIUM = "0.5"
+    HIGH = "0.33"
+    EXTREME = "0.2"
+
+class TokenBeeModel(str, Enum):
+    # OpenAI
+    OPENAI_GPT_4O = "openai/gpt-4o"
+    OPENAI_GPT_4O_MINI = "openai/gpt-4o-mini"
+    OPENAI_O1 = "openai/o1"
+    OPENAI_O1_MINI = "openai/o1-mini"
+    OPENAI_O3_MINI = "openai/o3-mini"
+
+    # Anthropic
+    ANTHROPIC_CLAUDE_4_6_SONNET = "anthropic/claude-4-6-sonnet-latest"
+    ANTHROPIC_CLAUDE_4_6_OPUS = "anthropic/claude-4-6-opus-latest"
+    ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic/claude-3-5-sonnet-latest"
+    ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3-5-haiku-latest"
+    ANTHROPIC_CLAUDE_3_OPUS = "anthropic/claude-3-opus-latest"
+
+    # Google
+    GEMINI_3_1_PRO = "google/gemini-3.1-pro"
+    GEMINI_3_1_FLASH = "google/gemini-3.1-flash"
+    GEMINI_2_0_FLASH = "google/gemini-2.0-flash"
+    GEMINI_2_0_PRO = "google/gemini-2.0-pro-exp"
+    GEMINI_1_5_PRO = "google/gemini-1.5-pro"
+    GEMINI_1_5_FLASH = "google/gemini-1.5-flash"
+
+    # Mistral
+    MISTRAL_LARGE = "mistral/mistral-large-latest"
+    MISTRAL_SMALL = "mistral/mistral-small-latest"
+    PIXTRAL_LARGE = "mistral/pixtral-large-latest"
+    MISTRAL_NEMO = "mistral/open-mistral-nemo"
+
+    # Perplexity
+    PERPLEXITY_SONAR = "perplexity/sonar"
+    PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro"
+    PERPLEXITY_SONAR_REASONING = "perplexity/sonar-reasoning"
+
+    # Groq
+    GROQ_LLAMA_3_3_70B = "groq/llama-3.3-70b-versatile"
+    GROQ_LLAMA_3_1_8B = "groq/llama-3.1-8b-instant"
+    GROQ_MIXTRAL_8X7B = "groq/mixtral-8x7b-32768"
+    GROQ_GEMMA2_9B = "groq/gemma2-9b-it"
+
+class TokenBee:
+    def __init__(
+        self, 
+        api_key: str,
+        llm_key: str,
+        base_url: str = "https://api.tokenbee.dev/v1", 
+        compression: str = "auto", 
+        rate: str = CompressionRate.MEDIUM, 
+        model: str = "", 
+        provider: str = "",
+        privacy: bool = False
+    ):
+        self.api_key = api_key
+        self.llm_key = llm_key
+        self.base_url = base_url
+        self.headers = {
+            "Authorization": f"Bearer {api_key}",
+            "X-LLM-Key": llm_key,
+            "X-TokenBee-Compression": compression,
+            "X-TokenBee-Rate": rate,
+            "X-TokenBee-Privacy": str(privacy).lower()
+        }
+        if model:
+            self.headers["X-TokenBee-Model"] = model
+        if provider:
+            self.headers["X-TokenBee-Provider"] = provider
+
+        self.client = httpx.Client(headers=self.headers, base_url=self.base_url)
+
+    def send(self, model: str, input: dict):
+        parts = model.split("/")
+        provider = parts[0] if len(parts) > 1 else self.headers.get("X-TokenBee-Provider", "openai")
+        model_name = "/".join(parts[1:]) if len(parts) > 1 else parts[0]
+
+        headers = self.headers.copy()
+        headers["X-TokenBee-Model"] = model_name
+        headers["X-TokenBee-Provider"] = provider
+        
+        if "compression" in input:
+            headers["X-TokenBee-Compression"] = str(input["compression"])
+        if "rate" in input:
+            headers["X-TokenBee-Rate"] = str(input["rate"])
+        if "privacy" in input:
+            headers["X-TokenBee-Privacy"] = str(input["privacy"]).lower()
+
+        payload = input.copy()
+        payload.pop("compression", None)
+        payload.pop("rate", None)
+        payload.pop("privacy", None)
+
+        response = self.client.post("/chat/completions", json=payload, headers=headers)
+        response.raise_for_status()
+        return response.json()

{tokenbee_sdk-0.1.0 → tokenbee_sdk-0.2.1}/tokenbee_sdk.egg-info/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: tokenbee-sdk
-Version: 0.1.0
+Version: 0.2.1
 Summary: Official Python SDK for TokenBee LLM inference gateway and observability.
 Author: TokenBee Inc.
-Author-email: "TokenBee Inc." <hello@tokenbee.dev>
+Author-email: "TokenBee Inc." <founders@tokenbee.io>
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -35,9 +35,11 @@ pip install tokenbee-sdk
 ```python
 from tokenbee import TokenBee, TokenBeeModel, CompressionRate
 
-# Initialize the client
+# Initialize the client with your TokenBee API key 
+# AND your LLM provider key (Bring Your Own Key - BYOK)
 client = TokenBee(
-    api_key="your_api_key_here",
+    api_key="your_tokenbee_api_key",
+    llm_key="your_llm_provider_key", # e.g. OpenAI or Anthropic key
     compression="auto",
     rate=CompressionRate.MEDIUM
 )
@@ -55,6 +57,10 @@ response = client.send(
 print(response["choices"][0]["message"]["content"])
 ```
 
+## Bring Your Own Key (BYOK)
+
+TokenBee is a **stateless** gateway. We do not store your LLM provider API keys in our database. You pass your provider key (OpenAI, Anthropic, etc.) through the SDK's `llm_key` parameter. The SDK sends this in the `X-LLM-Key` header, allowing the TokenBee proxy to forward requests to the provider on your behalf while you maintain full control over your billing and security.
+
 ## Advanced Usage
 
 ### Compression Control