Search models and prices
A model is a provider and one of its search modes, written provider/variant. The same request works with every model, and you pay the provider’s list price per request. Prices are loaded live from GET /v1/models.
| Model | Per 1,000 requests | Included results | Extra result | Latency |
|---|---|---|---|---|
| exa/instant Exa instant, lowest-latency neural search | $4.00 | 10 | +$1.00 / 1k | ~300 ms |
| exa/fast Exa fast | $7.00 | 10 | +$1.00 / 1k | ~500 ms |
| exa/auto Exa auto (default, best general quality) | $7.00 | 10 | +$1.00 / 1k | ~1 s |
| exa/deep Exa deep multi-query search | $12.00 | 10 | +$1.00 / 1k | ~5 s |
| parallel/turbo Parallel turbo, ~200ms | $1.00 | 10 | +$1.00 / 1k | ~200 ms |
| parallel/fast Parallel fast, <1s | $1.00 | 10 | +$1.00 / 1k | ~800 ms |
| parallel/basic Parallel basic | $5.00 | 10 | +$1.00 / 1k | ~1 s |
| parallel/advanced Parallel advanced, highest quality excerpts | $5.00 | 10 | +$1.00 / 1k | ~3 s |
| keenable/pro Keenable pro index | $4.00 | 10 | none | ~700 ms |
| keenable/realtime Keenable realtime index | $4.00 | 10 | none | ~700 ms |
Each price includes 10 results. Extra results beyond 10 cost the per-result rate shown, billed on what the provider returns. See Pricing.
Exa
Neural search built for AI applications, with several speed and depth tiers and the largest result cap (100).
Parallel
Search tuned for agents, with the lowest entry price on Mux and excerpt-style results.
Keenable
Index-based search with a flat price per request, whatever the result count, and a realtime index for fresh pages.
Not sure which to pick?
Pass an ordered list and let Mux fall back: "models": ["parallel/fast", "exa/auto", "keenable/pro"]. Failed attempts are refunded and you pay for the model that answered. Read Exa vs Parallel vs Keenable or the routing docs.