LLMGemma 4 31B (NVFP4) API pricing variable pricing
Gemma 4 31B (NVFP4) by Sail Research costs $0.14 per 1M input tokens and $0.40 per 1M output tokens (1M in + 1M out = $0.54).
- API model id
nvidia/Gemma-4-31B-IT-NVFP4- Input / 1M
- $0.14
- Output / 1M
- $0.40
- Cached input / 1M
- $0.07
- Context window
- —
- Notes
- Sail Research API (OpenAI/Anthropic-compatible), USD per 1M tokens, Default (ASAP) completion window; inputs include a guaranteed 30-minute cache write. Usage-based from prepaid credits, $5 free credits/month with a payment method.
- Source
- https://docs.sailresearch.com/pricing
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- no — Serving countries are not published. Requests are unrestricted by country by default; 'US-only inference' (routing.allowed_countries ['US'], Pro/Enterprise plans, surcharge) is the only country restriction offered, so there is no EU residency option.
- Last verified
- 2026-11-12
Variable pricing
The effective price of this model depends on the request. Figures above are the base (short-context / peak) tier.
- Depends on completion window / service tier: Cheaper with a longer completion window: Balanced $0.11 input / $0.06 cached / $0.32 output per 1M; Flex $0.07 input / $0.04 cached / $0.2 output per 1M.
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Sail Research | Gemma 4 31B (NVFP4) | $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 Sail Research models
- Kimi K3: $1.50 / $10.00
- GLM-5.3: $0.98 / $3.08
- GLM-5.3 Flash: $0.11 / $0.35
- DeepSeek V4.1 Flash 1017: $0.09 / $0.30
- DeepSeek V4.1 Flash: $0.09 / $0.30
- DeepSeek V4 Pro 0813: $0.92 / $2.77
- DeepSeek V4 Flash 0731: $0.09 / $0.18
- Gemma 4 31B: $0.40 / $0.60