Meta-Llama-3.3-70B-Instruct API pricing
Meta-Llama-3.3-70B-Instruct by SambaNova costs $0.60 per 1M input tokens and $1.20 per 1M output tokens (1M in + 1M out = $1.80).
- API model id
Meta-Llama-3.3-70B-Instruct- Input / 1M
- $0.60
- Output / 1M
- $1.20
- Cached input / 1M
- —
- Context window
- —
- Notes
- —
- Source
- https://cloud.sambanova.ai/plans/pricing
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — No public EU data-residency commitment found on the SambaNova Cloud pricing/plans pages.
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| SambaNova | Meta-Llama-3.3-70B-Instruct | $0.90 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other SambaNova models
- gpt-oss-120b: $0.22 / $0.59
- gemma-4-31B-it: $0.38 / $1.15
- MiniMax-M3: $0.60 / $2.40
- DeepSeek-V3.1: $3.00 / $4.50
- DeepSeek-V3.2: $3.00 / $4.50