LLMDeepSeek V4.1 Flash API pricing
DeepSeek V4.1 Flash by River costs $0.12 per 1M input tokens and $0.48 per 1M output tokens (1M in + 1M out = $0.60).
- API model id
deepseek-ai/DeepSeek-V4.1-Flash- Input / 1M
- $0.12
- Output / 1M
- $0.48
- Cached input / 1M
- $0.0024
- Context window
- —
- Notes
- River Inference price (USD per 1M tokens) from the public pricing JSON behind river.ai/pricing. Training/sampling prices are separate and not listed here.
- Source
- https://console.river.ai/api/public/pricing
- Provider type
- Inference host (HQ: US)
- Regions
- Global
- EU data residency
- unknown — US company; processing on GCP, Crusoe and Oracle (locations 'Global') per the DPA.
- Last verified
- 2026-11-12
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| River | DeepSeek V4.1 Flash | $0.24 |
Uses standard list prices (no caching, batch or off-peak discounts). €, CHF and ₹ rows are priced in that currency by the provider and not converted, so compare them with care. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09).
Other River models
- GLM 5.3: $1.12 / $3.52
- Qwen3.8 27B (FP8): $0.10 / $2.00
- DeepSeek V4.1 Flash 1017: $0.12 / $0.48
- Kimi K3: $3.00 / $15.00
- Nemotron 3.5 Super VL 120B A12B (NVFP4): $0.07 / $0.37
- GLM 5.3 Flash: $0.12 / $0.40