Llama 3.3 70B Pricing
BalancedMeta · 131K tokens context
Llama 3.3 70B from Meta costs $0.100 per 1 million input tokens and $0.320 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 131,072-token context window (approximately 98,304 words) with a 8K-token maximum output. A typical 1,000-token request costs $0.0001 in input charges; a 10,000-token request costs $0.0010.
| Input price | $0.100 / 1M tokens |
|---|---|
| Output price | $0.320 / 1M tokens |
| Output / input ratio | 3.2× |
| Context window | 131,072 tokens (~98,304 words) |
| Maximum output | 8,192 tokens |
| Cost per 1K tokens (input) | $0.0001 |
| Tier | Balanced |
| Last verified |
Llama 3.3 70B improves on Llama 3.1 70B with better instruction-following and reasoning, at the same price point. The recommended Llama 70B for new projects — same hosting cost, meaningfully better quality.
Input Price
$0.100
per 1 million tokens
Output Price
$0.320
per 1 million tokens
Context Window
131K tokens
max 8K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.000133 | $0.000128 |
| 10-page document (2,500 words) | 3,333 | $0.000333 | $0.00032 |
| 1,000 lines of code | 5,000 | $0.0005 | $0.00048 |
| 100K token document | 100,000 | $0.01 | $0.0096 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Better than 3.1 70B on most benchmarks
- ✓Same affordable hosted pricing
- ✓Open weights
Limitations
- –128K context
- –Still outclassed by frontier models on hardest tasks
Best Use Cases
Calculate Llama 3.3 70B Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Llama 3.3 70B costs — and compare across all models.
Open Calculator →Llama 3.3 70B — FAQ
Related Models
Related Guides