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
| Metric | USD / million tokens |
|---|---|
| Input | $0.59 |
| Output | $0.79 |
Price history
| Observed | Metric | 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
—
2026-08-07Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| 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 → |