Fireworks AI API pricing

Billing rules Veqen applies

• Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
• Image models: per image, with each size and quality priced separately. When the API reports image tokens, those are the bill.
• Audio models: per second of audio or per character of text, or per token where the model bills tokens.
• Rerank models: per query.

Also recognized as: fireworks-ai, fireworks_ai (framework, gateway and OpenTelemetry names).

Reconcile your bill

Fireworks AI doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.

Prices come from Fireworks AI's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.