Llama 3.3 70B Instruct Turbo
MetaOpen weights131K context
As of Oct 15, 2026, Llama 3.3 70B Instruct Turbo costs $0.10 per million input tokens and $0.32 per million output tokens from DeepInfra. The cheapest of 3 sellers is DeepInfra at $0.10 / $0.32.
Lowest price, from DeepInfra
Pricing pagePer million tokens
- Input
- $0.10
- Output
- $0.32
- Cached input
- —
- Batch input / output
- —
- Up to 131K output tokens per request.
Estimate your monthly cost
Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30. ¹ The price is higher for long prompts (usually over 200K tokens); the estimate uses the base price.
From DeepInfra: $1.64 a month.
Where to buy it (3)
Sorted by your monthly estimate. Prices per million tokens.
DeepInfraCheapest
- Input / output
- $0.10 / $0.32
- Context
- 131K
- Per month
- $1.64
deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo
- Input / output
- $0.20 / $0.50
- Context
- 131K
- Per month
- $3.00
inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo
- Input / output
- $1.04 / $1.04
- Context
- 131K
- Per month
- $12.48
together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo
Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling.