Cost Tracking

Prysm automatically calculates the cost of every LLM request based on the model used and the token counts returned by the provider.

Built-in Pricing

Pricing is pre-configured for popular models including GPT-4o, GPT-4o Mini, Claude Sonnet 4, Claude Haiku, Gemini 2.5 Flash, and more. Prices are updated as providers change their rates.

Custom Model Pricing

For self-hosted models or providers not in the default list, set custom pricing in Settings → Cost Tracking. Specify the input and output cost per 1M tokens.

Usage Limits

Free tier includes 10,000 requests per month. When you hit the limit, the proxy returns a 429 Too Many Requests response. View your current usage in Settings → Usage.