Pricing

Llama 3.3 70B Pricing

Groq • Model ID: llama-3.3-70b-versatile

Token Pricing (per 1M tokens)

$0.5900
Input tokens
$0.7900
Output tokens

Cost Calculator

$0.00
Estimated monthly cost · $0.000 per call

Monthly Cost Estimates

Usage LevelCalls/MonthMonthly Cost
Hobby 1,000 $0.79
Startup 10,000 $7.88
Growth 100,000 $78.80
Scale 500,000 $394.00
Enterprise 2,000,000 $1,576.00

Assumes 800 input + 400 output tokens per call.

Compare with Alternatives

ModelProviderInput/1MOutput/1Mvs Llama 3.3 70B
Llama 3.3 70B Groq $0.5900 $0.7900
Gemini 1.0 Pro Google Gemini $0.5000 $1.5000 +45% more
Mistral Large Mistral AI $0.5000 $1.5000 +45% more
GPT-3.5 Turbo OpenAI $0.5000 $1.5000 +45% more
Mixtral 8x7B Mistral AI $0.7000 $0.7000 +1% more
Mistral Medium Mistral AI $0.4000 $2.0000 +74% more

Other Groq Models

Frequently Asked Questions

How much does Llama 3.3 70B cost?

Llama 3.3 70B by Groq costs $0.59/M input tokens and $0.79/M output tokens as of June 2026.

How much does 1,000 API calls to Llama 3.3 70B cost?

At 800 input + 400 output tokens per call, 1,000 calls to Llama 3.3 70B costs approximately $0.79.

Is Llama 3.3 70B cheaper than GPT-4o?

Llama 3.3 70B input costs $0.59/M vs GPT-4o at $5.00/M. Llama 3.3 70B is 88% cheaper for input tokens.

Track your Llama 3.3 70B costs in real time

Tokonomics automatically calculates cost for every Llama 3.3 70B call. Set budget alerts and never overspend.

Start Free →