recursive API pricing across models and providers
Shortlist models by capability and compare API prices and public performance. Use your own task results to decide whether to switch.
Find a model
More conditions
No usage needed. Find up to three matching models by your selected unit price, with both rates shown together.
Your result
Loading quotes…
Manage saved choices and save these results
Saved candidates 0/3
Saved choices stay when you run the finder. Compare their input and output prices per million tokens here.
Run the finder, then save candidates from its recommendations.
Estimate workload cost (optional)
Cost estimate
Example per call: read 500 characters, generate 300; 1 call(s) per task.
Adjust content lengths and assumptions
Include prompts, conversation history and attached context in the input. For multi-step tasks, use average content lengths per model call.
Characters per token is an adjustable planning assumption, not a measurement. Language, model and code affect it. Input and output scale together with tasks. Set extra per-request fees and reasoning usage separately in other assumptions.
Estimated monthly usage: 0.3M input, 0.18M output tokens, 600 calls.
Text-cost estimate for 600 tasks over 30 days per month.
Loading quotes…
Estimate, not a bill: token and request charges only, in the quote’s own currency. Excludes tools, storage, search, taxes and platform fees. Different models tokenize the same task differently.
Today
Your requirements and usage
Text generation · compare costs across models and providers
Other model types
Each category uses its own billing units. The cost tool only includes current quotes with verified, complete rates.
Your result
Set your requirements and usage, then run the search. We’ll offer up to three matching models, ordered by estimated cost.
View quote details and advanced filters
History · Billing and conditions
recursive API pricing across models and providers: 1 current published quote records across 1 exact API IDs and 1 providers. Compare API versions, currencies, regions and billing conditions separately; prices do not prove task quality or account access.
Latest recorded source check: 2026-11-22
Recorded changes
No changes recorded yet. The first successful check establishes a baseline; it does not count as a price drop or a newly launched endpoint.
Showing up to 100 recent events. Prices for unavailable endpoints are retained for reference. Failed source checks do not establish that a price stayed unchanged.
Open a quote’s billing details for cache reads/writes, request fees and endpoint instructions. Batch, free, promotional and off-peak tiers are selected separately. Context-tier, storage, search, tax and platform fees may be excluded.