Check Price and Token Limits in ZapGPT with OpenAI Provider
2025-06-21
379 words
2 mins read
ZapGPT is a CLI and API tool to interact with LLMs like OpenAI, Groq, Claude, Perplexity, and more. If you’re using the OpenAI provider, you can easily check the price per token for each supported model — critical info if you’re optimizing for cost or want to dynamically switch models based on available context or budget.
Also, you can use the OpeNRouter provider to check the length of context if you are using some huge context like a big file as input :).
📊 How to Check Prices and Token Limits
ZapGPT maintains a built-in reference for most LLM providers including OpenAI (this is static information and may change). For OpenRouter the API is queried for this information so this is more upto date and correct.
Step 1: List All Models
Run:
|
|
to check for openai and openrouter providers.
This will show all models available via the active provider (default is github) along with their:
Ctx Length(context limit) for OpenRouter
Example output:
|
|
To check the price for the models, you can run:
|
|
Sample output:
|
|
Step 2: Choose a Model Based on Budget/Context
Based on your budget or the size of documents you’re working with:
- Use
gpt-4ofor a good balance of cost and performance - Use
gpt-3.5-turbofor high-volume, low-cost tasks - Use
gpt-4-turboonly if you need advanced reasoning and don’t mind higher cost
You can switch models using:
|
|
🔗 Reference
- GitHub: https://github.com/raj77in/zapgpt
- Supported providers:
openai,openrouter,github
Authored By Amit Agarwal
Amit Agarwal, Linux and Photography are my hobbies.Creative Commons Attribution 4.0 International License.