Skip to content
Sovyron

Llama 3.3 70B

llama128k context128k max outputreleased Dec 6, 2024Open weightsTool calling

As of Nov 22, 2026, the cheapest Llama 3.3 70B API price is $0.53 per 1M input tokens (STACKIT) and $0.71 per 1M output tokens (CoreWeave). Llama 3.3 70B is offered by 4 providers in the llama family, open weights.

Cheapest input
$0.53
Cheapest output
$0.71
Official
—
output per 1M tokens
Providers
4
offering this model
Spread
3.9×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Llama 3.3 70B API prices by provider in USD per 1M tokens, updated Nov 22, 2026
STACKITopencortecs/Llama-3.3-70B-Instruct-FP8-DynamicCheapest$0.53$0.76——128k
CoreWeaveopenmeta-llama/Llama-3.3-70B-Instruct$0.71Cheapest$0.71$0.71—128k
Venice AIopenllama-3.3-70b$0.7$2.8——128k
NanoGPTopenTEE/llama3-3-70b$1.75$2.75$1.75—128k

Llama 3.3 70B pricing FAQ

What is the cheapest Llama 3.3 70B API?

As of Nov 22, 2026, CoreWeave has the lowest Llama 3.3 70B output price at $0.71 per 1M tokens, and STACKIT has the lowest input price at $0.53 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Llama 3.3 70B?

4 providers list Llama 3.3 70B on Sovyron; 4 of them sell it at a metered per-token price.

Is Llama 3.3 70B free?

No provider in the Sovyron catalog lists a free tier for Llama 3.3 70B.

What is the context window of Llama 3.3 70B?

Llama 3.3 70B supports a 128k-token context window and up to 128k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—