Petro Lingo

Warning

Large Language Models generate a “Most Probable Response” through a statistical process influenced by your data and its quality. There is no guarantee of the accuracy or veracity of the results.

Petro Lingo is a Python package designed to integrate Large Language Models with Geoscience ANALYST via geoh5py. This package encompasses a variety of applications leveraging these models to generate outputs, along with additional tools that facilitate ease of use.

Theory

• Large Language Model Principles

Applications

• Composite Text Column
• Summarize
• Relogger
• Translate
• Third-party software

Case Studies

• Relogging of the Butler Property Outcrops - Northern Ontario

Models Available

• LLM Providers
  • Google Models
  • OpenAI Models
  • Mistral Models

Several Large Language Models are available for use with Petro Lingo through OpenRouter. The following table provides a summary of the models available based on real OpenRouter pricing and performance data.

Table 6 Available Language Models

Model	Provider	Intelligence Score	Speed (tokens/s)	Value Rating	Data Retention
gpt-5	OpenAI	68/100	~250-300	Premium	30 days
gpt-5-mini	OpenAI	64/100	~400-500	Excellent	30 days
gpt-5-nano	OpenAI	51/100	~600-700	Budget	30 days
gemini-2.5-pro	Google	60/100	~150-200	Premium	Zero
gemini-2.5-flash	Google	54/100	~250-300	Excellent	Zero
mistral-small-3.2	Mistral	29/100	~400-500	Budget	Zero
custom	User-defined	Variable	Variable	Variable	Variable

Pricing Data (per million tokens):

• gpt-5: $1.25 input / $10.00 output

• gpt-5-mini: $0.25 input / $2.00 output

• gpt-5-nano: $0.05 input / $0.40 output

• gemini-2.5-pro: $1.25 input / $10.00 output

• gemini-2.5-flash: $0.30 input / $2.50 output

• mistral-small-3.2: $0.06 input / $0.18 output

Legend:

• Intelligence Score: Comprehensive AI capability rating from Artificial Analysis Intelligence Index (0-100 scale)

• Speed: Approximate output generation speed in tokens per second

• Value Rating: Premium (high cost, high performance), Excellent (balanced cost/performance), Budget (low cost, basic performance)

• Data Retention: How long your data is stored by the provider

License

Copyright 2025, Mira Geoscience Ltd.

All rights reserved.

The software and information contained herein are proprietary to, and comprise valuable trade secrets of, Mira Geoscience, which intend to preserve as trade secrets such software and information. This software is furnished pursuant to a written license agreement and may be used, copied, transmitted, and stored only in accordance with the terms of such license and with the inclusion of the above copyright notice. This software and information or any other copies thereof may not be provided or otherwise made available to any other person.

THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

Third Party Software

The petro-lingo Software may provide links to third party libraries or code (collectively “Third Party Software”) to implement various functions. Third Party Software does not comprise part of the Software. The use of Third Party Software is governed by the terms of such software license(s). Third Party Software notices and/or additional terms and conditions are located in the Third-party software file.