Llama 3.3 70B API pricing
Llama 3.3 70B by Venice costs $0.70 per 1M input tokens and $2.80 per 1M output tokens (1M in + 1M out = $3.50).
- API model id
llama-3.3-70b- Input / 1M
- $0.70
- Output / 1M
- $2.80
- Cached input / 1M
- —
- Context window
- —
- Notes
- Venice API, USD per 1M tokens, 'Private' tier (zero data retention, Venice-hosted open model). Context listed as 128K.
- Source
- https://docs.venice.ai/overview/pricing
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Venice docs do not publish serving regions. Privacy tiers: Private = zero data retention on Venice-hosted open models; Anonymized = proxied third-party models with identifying metadata stripped; TEE/E2EE = enclave models. OpenRouter's provider list reports HQ US, datacenters US.
- Last verified
- 2026-10-21
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Venice | Llama 3.3 70B | $1.40 |
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 Venice models
- DeepSeek V4 Flash 0731: $0.13 / $0.26
- DeepSeek V4 Pro: $1.65 / $3.30
- DeepSeek V4.1 Flash: $0.30 / $1.20
- GLM 5.2: $1.40 / $4.40
- GLM 5.3: $1.75 / $5.50
- GLM 5.3 Flash: $0.15 / $0.50
- Kimi K3: $3.75 / $18.75
- Kimi K2.6: $0.75 / $3.50