| Name | llm-token-tracker JSON |
| Version |
0.4.0
JSON |
| download |
| home_page | None |
| Summary | A package to track LLM token usage in context |
| upload_time | 2025-10-16 11:32:21 |
| maintainer | None |
| docs_url | None |
| author | Laurin |
| requires_python | >=3.13 |
| license | None |
| keywords |
llm
token
tracker
xai
grok
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llm-token-tracker
[](https://pypi.org/project/llm-token-tracker/)
A Python package to track token usage in LLM interactions.
## Features
- Track token usage in LLM conversations
- Support for detailed token breakdowns (prompt, completion, reasoning, cached, etc.)
- Cost estimation for input and output tokens
- Configurable verbosity levels for logging
- Integration with custom loggers
- Compatibility with xAI and OpenAI models
## Installation
```bash
pip install llm-token-tracker
```
## Usage
```python
from llm_token_tracker import wrap_llm
from xai_sdk import Client
import logging
# Create and wrap a chat for token tracking
client = Client()
chat = client.chat.create(model="grok-3")
wrapped_chat = wrap_llm(chat)
response = wrapped_chat.sample("Hello, how are you?")
print(response.content)
# Console will log: Total tokens used in context: X
# For conversation context
wrapped_chat.append(system("You are Grok, a highly intelligent AI."))
wrapped_chat.append(user("What is the meaning of life?"))
response = wrapped_chat.sample()
print(response.content)
```
### OpenAI Compatibility
For OpenAI models using the responses API:
```python
from openai import OpenAI
from llm_token_tracker import wrap_llm
client = OpenAI()
wrapped_client = wrap_llm(client, provider="openai")
response = wrapped_client.responses.create(
model="gpt-4.1",
input="Tell me a three sentence bedtime story about a unicorn."
)
print(response.content)
# Console will log: Total tokens used in context: X
```
### Configuration Options
`wrap_llm` accepts several parameters to customize logging:
- `provider`: `"xai"` (default) or `"openai"` to specify the LLM provider.
- `verbosity`: `"minimum"` (default), `"detailed"`, or `"max"`
- `"minimum"`: Logs only total tokens used.
- `"detailed"`: Logs a detailed usage summary.
- `"max"`: Logs the full history of all token usages.
- `logger`: Optional `logging.Logger` instance. If provided, uses the logger instead of printing to console.
- `log_level`: Logging level (default `logging.INFO`).
- `quiet`: If `True`, disables all logging.
- `max_tokens`: Maximum tokens allowed in context (default 132000).
- `input_pricing`: Price per 1 million input tokens (default 0.2).
- `output_pricing`: Price per 1 million output tokens (default 0.5).
- `calculate_pricing`: If `True`, calculates and logs cost estimates (default `False`).
Example with custom logger:
```python
import logging
logger = logging.getLogger("my_llm_logger")
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
logger.addHandler(handler)
wrapped_chat = wrap_llm(chat, logger=logger, verbosity="detailed")
```
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-token-tracker",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.13",
"maintainer_email": null,
"keywords": "llm, token, tracker, xai, grok",
"author": "Laurin",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/01/2b/c0e74da9f0ce96ce5d3d29b0ebe57061481eca0cbd640dcbdd35b7b957aa/llm_token_tracker-0.4.0.tar.gz",
"platform": null,
"description": "# llm-token-tracker\n\n[](https://pypi.org/project/llm-token-tracker/)\n\nA Python package to track token usage in LLM interactions.\n\n## Features\n\n- Track token usage in LLM conversations\n- Support for detailed token breakdowns (prompt, completion, reasoning, cached, etc.)\n- Cost estimation for input and output tokens\n- Configurable verbosity levels for logging\n- Integration with custom loggers\n- Compatibility with xAI and OpenAI models\n\n## Installation\n\n```bash\npip install llm-token-tracker\n```\n\n## Usage\n\n```python\nfrom llm_token_tracker import wrap_llm\nfrom xai_sdk import Client\nimport logging\n\n# Create and wrap a chat for token tracking\nclient = Client()\nchat = client.chat.create(model=\"grok-3\")\nwrapped_chat = wrap_llm(chat)\n\nresponse = wrapped_chat.sample(\"Hello, how are you?\")\nprint(response.content)\n# Console will log: Total tokens used in context: X\n\n# For conversation context\nwrapped_chat.append(system(\"You are Grok, a highly intelligent AI.\"))\nwrapped_chat.append(user(\"What is the meaning of life?\"))\nresponse = wrapped_chat.sample()\nprint(response.content)\n```\n\n### OpenAI Compatibility\n\nFor OpenAI models using the responses API:\n\n```python\nfrom openai import OpenAI\nfrom llm_token_tracker import wrap_llm\n\nclient = OpenAI()\nwrapped_client = wrap_llm(client, provider=\"openai\")\n\nresponse = wrapped_client.responses.create(\n model=\"gpt-4.1\",\n input=\"Tell me a three sentence bedtime story about a unicorn.\"\n)\nprint(response.content)\n# Console will log: Total tokens used in context: X\n```\n\n### Configuration Options\n\n`wrap_llm` accepts several parameters to customize logging:\n\n- `provider`: `\"xai\"` (default) or `\"openai\"` to specify the LLM provider.\n- `verbosity`: `\"minimum\"` (default), `\"detailed\"`, or `\"max\"`\n - `\"minimum\"`: Logs only total tokens used.\n - `\"detailed\"`: Logs a detailed usage summary.\n - `\"max\"`: Logs the full history of all token usages.\n- `logger`: Optional `logging.Logger` instance. If provided, uses the logger instead of printing to console.\n- `log_level`: Logging level (default `logging.INFO`).\n- `quiet`: If `True`, disables all logging.\n- `max_tokens`: Maximum tokens allowed in context (default 132000).\n- `input_pricing`: Price per 1 million input tokens (default 0.2).\n- `output_pricing`: Price per 1 million output tokens (default 0.5).\n- `calculate_pricing`: If `True`, calculates and logs cost estimates (default `False`).\n\nExample with custom logger:\n\n```python\nimport logging\n\nlogger = logging.getLogger(\"my_llm_logger\")\nlogger.setLevel(logging.INFO)\nhandler = logging.StreamHandler()\nlogger.addHandler(handler)\n\nwrapped_chat = wrap_llm(chat, logger=logger, verbosity=\"detailed\")\n```\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
"bugtrack_url": null,
"license": null,
"summary": "A package to track LLM token usage in context",
"version": "0.4.0",
"project_urls": null,
"split_keywords": [
"llm",
" token",
" tracker",
" xai",
" grok"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "5e554327a778ce1c47078f9ebf99532a32fa754c6f484765f4643464fef9c610",
"md5": "9c572d163c2b5462dc87cc85fbcb2689",
"sha256": "56d8e34df36b232829d8cb120eee0541d413e2e5b9452ca7a0a9ce70727edf23"
},
"downloads": -1,
"filename": "llm_token_tracker-0.4.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9c572d163c2b5462dc87cc85fbcb2689",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.13",
"size": 6259,
"upload_time": "2025-10-16T11:32:20",
"upload_time_iso_8601": "2025-10-16T11:32:20.558407Z",
"url": "https://files.pythonhosted.org/packages/5e/55/4327a778ce1c47078f9ebf99532a32fa754c6f484765f4643464fef9c610/llm_token_tracker-0.4.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "012bc0e74da9f0ce96ce5d3d29b0ebe57061481eca0cbd640dcbdd35b7b957aa",
"md5": "f0289045acb5b8394d149477dfae3040",
"sha256": "8482ff780199d0c7bf468b618ee05e76373506ef247de922aba64dea2a03d779"
},
"downloads": -1,
"filename": "llm_token_tracker-0.4.0.tar.gz",
"has_sig": false,
"md5_digest": "f0289045acb5b8394d149477dfae3040",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.13",
"size": 6463,
"upload_time": "2025-10-16T11:32:21",
"upload_time_iso_8601": "2025-10-16T11:32:21.506421Z",
"url": "https://files.pythonhosted.org/packages/01/2b/c0e74da9f0ce96ce5d3d29b0ebe57061481eca0cbd640dcbdd35b7b957aa/llm_token_tracker-0.4.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-16 11:32:21",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llm-token-tracker"
}
