Llama 3.3 70B pricing
Meta · list prices as of 2026-09-29 · open-weight model: a representative hosting rate, not a first-party list price
| Input | $0.88 per 1M tokens |
|---|---|
| Output | $0.88 per 1M tokens |
| Context window | 131K tokens |
What a call costs
| Typical call | Input tokens | Output tokens | Per call | Per month at 1,000 a day |
|---|---|---|---|---|
| Chat reply | 1,000 | 300 | $0.00114 | $34.32 |
| Document summary | 6,000 | 400 | $0.00563 | $168.96 |
| Code change | 3,000 | 1,200 | $0.0037 | $110.88 |
No caching or batch discount. Your own prompt will differ: count it exactly below.
Price your own prompt on Llama 3.3 70BSimilarly priced models
- DeepSeek R1 (DeepSeek): 1.1× more
- Gemini 2.5 Flash (Google): 1.1× cheaper
- Gemini 3.5 Flash-Lite (Google): 1.1× cheaper
- GPT-3.5 Turbo (OpenAI): 1.2× cheaper
- Mistral Large 3 (Mistral): 1.2× cheaper
Questions
How much does Llama 3.3 70B cost?
Llama 3.3 70B costs $0.88 per million input tokens and $0.88 per million output tokens, as of 2026-09-29.
How much is one Llama 3.3 70B call?
A call with 1,000 input tokens and a 300-token answer costs about $0.00114, or $34.32 a month at 1,000 calls a day.
How big is the Llama 3.3 70B context window?
131,072 tokens.