Llama-3.3-70B-Instruct-Turbo API pricing
Llama-3.3-70B-Instruct-Turbo by DeepInfra costs $0.10 per 1M input tokens and $0.32 per 1M output tokens (1M in + 1M out = $0.42).
- API model id
Llama-3.3-70B-Instruct-Turbo- Input / 1M
- $0.10
- Output / 1M
- $0.32
- Cached input / 1M
- —
- Context window
- 128K
- Notes
- —
- Source
- https://deepinfra.com/pricing
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Not stated on the pricing page.
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| DeepInfra | Llama-3.3-70B-Instruct-Turbo | $0.18 |
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 DeepInfra models
- DeepSeek-V4-Pro: $1.30 / $2.60
- DeepSeek-V4-Flash: $0.09 / $0.18
- Kimi-K3: $2.85 / $14.25
- Qwen3.8-Max: $1.65 / $4.95
- gemma-4-31B-it: $0.20 / $0.40
- claude-sonnet-5: $3.00 / $15.00
- claude-opus-5: $5.00 / $25.00
- gemini-2.5-flash: $0.30 / $2.50