Skip to main content
GET https://api.prysm1.com/v1/savings · Requires authentication
Computes an estimate of what your usage would have cost if every request had gone to a single baseline model, then returns the delta against your actual spend. The figure is a blended estimate based on per-token pricing — it is not a billing statement.

Authorization

string
required
Your secret key as a bearer token: Bearer prysm_sk_...

Query parameters

string
default:"gpt-5.2"
The model to compare against. Must be a valid model ID from GET /v1/models. Defaults to gpt-5.2.

Response

string
The model used as the comparison baseline.
integer
Total requests included in the calculation.
integer
Total tokens (input + output) across all requests.
number
Your actual spend, USD.
number
Estimated cost if every request had gone to the baseline model, USD.
number
Estimated savings: max(0, baseline_cost - actual_cost), USD.
number
Percentage saved relative to the baseline cost.
Compare against different baselines to see how your routing choices stack up. For agentic workloads, claude-opus-4.6 or gpt-5.2-pro make conservative baselines that show maximum savings.