Skip to main content
Surplus Intelligence
Marketplace
MarketplacePricing

Pricing

Sellers set their own prices. The marketplace routes buyers to the cheapest available seller.

Pricing Modes

Cost Multiplier — the only mode for text models

Seller specifies a fraction of the model's reference price. "I'll undercut the market by X%."

json
{ "pricing_mode": "cost_multiplier", "cost_multiplier": 0.50 }

0.50 = buyer pays 50% of the reference price. Reference prices come from PROVIDER_PRICES in the codebase.

Per-token pricing is retired for text models. Quoting a text offer with price_input_per_1m / price_output_per_1m now returns 400 per_token_pricing_retired on create, bulk create and update. Use cost_multiplier. Media offers are exempt and still price per unit.

Cost Calculation

For each request:

base_cost    = reference_price_for_model × cost_multiplier   (applied per input/output token)
buyer_cost   = base_cost
seller_earns = base_cost
How a buyer's price is built
  1. Reference priceThe model's list price
  2. × cost_multiplierThe seller's discount
  3. Buyer paysThe seller earns it
What you pay is what the seller charges. The seller's multiplier against the model's reference price is the whole calculation.

Price Threshold

Buyers can require a minimum discount below the go-direct reference price:

bash
-H "X-Min-Discount: 30"

The same floor can be set on the API key itself (min_discount_pct in the key's scope) or expressed in the URL (/min30/v1/...). When more than one is present the strictest applies — a per-request value can tighten the key's floor but never loosen it. A request that no offer satisfies fails with minimum_discount_not_met rather than routing to a worse price.

Price ceilings are retired. max_price_per_1m and the X-Max-Price-Per-1M header capped a per-1M input rate, which ignored output and cache rates and told you nothing about whether the price was actually good. Discount is measured against the reference price you would pay going direct, which is the number that matters.

Requests skip sellers whose estimated cost exceeds this threshold.

Provider Pricing Discovery

When sellers connect their API key, the marketplace auto-detects pricing from the provider's /models endpoint. Four parsing layers handle all known provider formats:

  1. Venice format — model_spec.pricing with nested {usd, diem}
  2. OpenRouter format — pricing.prompt / pricing.completion as per-token strings
  3. Generic format — pricing.input / pricing.output as numbers ($/1M tokens)
  4. Reference fallback — static reference prices for known models when provider returns none
Previous← Health and routingNextOverview →