Provide API Endpoint for Model Pricing #2074
Description
Confirm this is a feature request for the Python library and not the underlying OpenAI API.
- This is a feature request for the Python library
Describe the feature or improvement you're requesting
Issue
Currently, OpenAI does not offer a way to dynamically retrieve model pricing through the API. Developers must hardcode pricing information and manually update their configurations when OpenAI changes pricing. This approach is outdated and impractical, as any other modern API service would provide pricing dynamically via an endpoint.
Proposed Solution
Please provide an official API endpoint that returns current model pricing, including:
• Per-token costs for input and output
• Pricing per model (GPT-4, GPT-3.5, etc.)
• Any upcoming changes (if applicable)
Why This Matters
• Prevents manual updates and errors in cost calculations
• Ensures accurate cost tracking for dynamic workloads
• Helps enterprise users avoid unexpected cost changes
• Reduces reliance on scraping OpenAI’s website
Expected Format (Example Response)
A simple JSON response like:
{
"gpt-4-1106-turbo": {
"input_cost_per_1k_tokens": 0.01,
"output_cost_per_1k_tokens": 0.03
},
"gpt-3.5-turbo": {
"input_cost_per_1k_tokens": 0.0015,
"output_cost_per_1k_tokens": 0.002
}
}
This would let developers dynamically fetch pricing without hardcoding values.
Conclusion
A pricing API would be a small but high-impact addition, aligning OpenAI’s developer experience with modern cloud services like AWS and Google Cloud.
Additional context
No response