LLMPriceTracker

River API pricing

7 River models. Source: https://console.river.ai/api/public/pricing

Provider type
Inference host
Server location (where inference runs)
Global
Regions
Global
Company HQ (secondary)
US (outside EU) · Operated by River AI Inc., a Nevada corporation with business operations in San Francisco, per the River API Services Agreement and Privacy Policy. Address 455 Market St, Ste 1940, San Francisco, CA 94105, USA, per the USPTO trademark record (serial 99866194, owner River AI Inc.). Checked 2026-11-03. · legal source
EU data residency
unknown
Residency notes
DPA: River is established in the US and may process data in the US and wherever its sub-processors operate (Crusoe, Google Cloud, Oracle: 'Global'); 'residency options available where supported' but no EU region is published. Commercial tier: no training on inputs/outputs, User Content kept up to 2 days.
Residency source
https://console.river.ai/terms

Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.

7models

Tap a box to filter by it; tap it again to remove that filter. Filters combine.

Blend input:output

7 of 7 models.

ProviderModelInputOutputCached inBlended 3:1* ▲ContextEU residency
River
Inference host
Nemotron 3.5 Super VL 120B A12B (NVFP4)$0.07$0.37$0.024$0.145—unknown
River
Inference host
GLM 5.3 Flash$0.12$0.40$0.024$0.19—unknown
River
Inference host
DeepSeek V4.1 Flash$0.12$0.48$0.0024$0.21—unknown
River
Inference host
DeepSeek V4.1 Flash 1017$0.12$0.48$0.0024$0.21—unknown
River
Inference host
Qwen3.8 27B (FP8)$0.10$2.00$0.02$0.575—unknown
River
Inference host
GLM 5.3$1.12$3.52$0.208$1.72—unknown
River
Inference host
Kimi K3$3.00$15.00$0.30$6.00—unknown

Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with €, CHF or ₹: those are as published and not converted. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09); sorting still uses the published ₹ amount. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. Click a header to sort.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.