Loading page
Llama 3.3 70B API pricing on Hyperstack
Every Hyperstack Llama 3.3 70B rate we track, compared against 8 providers serving the same model.
Input from /1M
$0.800
Output /1M
$0.800
Price rank
#6 of 8
Last updated
September 18, 2026
The cheapest Llama 3.3 70B input price we currently track is $0.100/1M on Deep Infra.
Hyperstack Llama 3.3 70B rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.800/1M | $0.800/1M |
About Llama 3.3 70B
- Creator
- Meta
- Context
- 128K
- Modalities
- text
- Knowledge cutoff
- Mar 2024
- Tool calling
- Yes
- Open weights
- Yes
Llama 3.3 70B on other providers
About Hyperstack
Hyperstack offers on‑demand H200/H100/A100/L40 with clear per‑GPU hourly pricing and reservation discounts.
Frequently Asked Questions
How much does Llama 3.3 70B cost on Hyperstack?
Hyperstack serves Llama 3.3 70B from $0.800 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is Hyperstack the cheapest way to run Llama 3.3 70B?
Hyperstack ranks #6 of 8 providers we track serving Llama 3.3 70B. The cheapest input price right now is on Deep Infra. Price is only one factor — throughput, latency, and context limits differ between providers.
Does Hyperstack offer batch or cached pricing for Llama 3.3 70B?
We track 1 Llama 3.3 70B offering from Hyperstack. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.