Llama 3.3 70B Versatile

$0.59
Input / MTok
$0.79
Output / MTok

Hosted third-party inference; price is Groq's serverless rate, not Meta's own API.

API identifier llama-3.3-70b-versatile · Context 131,072 tokens · Max output 32,768 · vendor pricing page

Full price sheet

MetricUSD / million tokens
Input$0.59
Output$0.79

Price history

ObservedMetric Price
2026-08-07 19:44:55 Input $0.59
2026-08-07 19:44:55 Output $0.79

Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.

Changes affecting this model

coverage
Llama 3.3 70B Versatile added to coverage
2026-08-07

Compare with

Models at a similar price point.

ModelInputOutput
Codestral $0.3$0.9 compare →
DeepSeek V4 Pro $0.435$0.87 compare →
Gemma 4 31B Instruct (Pearl AI) $0.28$0.86 compare →
Gemma 4 31B IT $0.39$0.97 compare →
GPT-5.6 Luna $0.2$1.2 compare →
Command Light $0.3$0.6 compare →