Start free

groq/llama-3.3-70b-versatile

Groq text

groq/llama-3.3-70b-versatile

Input

$0.5900

per 1M input tokens

Output

$0.7900

per 1M output tokens

Cache read

n/a

per 1M cached read tokens

Cache write

n/a

per 1M cache write tokens

Context window

131,072

Max output

32,768

Effective date

Aug 14, 2026

Estimate a workload

Enter token counts to see the cost at this model's rates.

Estimated cost: $0.00

Price history

blended $ per 1M tokens (3:1)
$0.00 $0.61 $1.22 $1.84 Jun 15, 2026: $0.64 Aug 14, 2026: $0.64 Jun 15, 2026 Aug 14, 2026
Effective Input Output Blended
Aug 14, 2026 $0.59 $0.79 $0.64
Jun 15, 2026 $0.59 $0.79 $0.64

Other Groq models

groq/meta-llama/llama-prompt-guard-2-22m · $0.0300/Mtok out groq/meta-llama/llama-prompt-guard-2-86m · $0.0400/Mtok out groq/llama-3.1-8b-instant · $0.0800/Mtok out groq/gemma-7b-it · $0.0800/Mtok out groq/openai/gpt-oss-20b · $0.3000/Mtok out groq/openai/gpt-oss-safeguard-20b · $0.3000/Mtok out

Source: litellm. Confirm against the provider's official pricing before relying on these figures.