Meta Text live-fetched
Llama 3.3 70B Instruct
Input$0.100per 1M tokens
Output$0.320per 1M tokens
- Context window
- 131,072 tokens
What that buys
- 1M words of output
- $0.43
- 100k-token chat, 80k in and 20k out
- $0.0144
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-10-08
- Changes recorded
- 4
Where this price sits
609 text models priced per 1M tokensLlama 3.3 70B Instruct is number 135 of 609 by price, from cheapest. The median is $2.00; Llama 3.3 70B Instruct is 84% below the median. Among the 16 Meta models in this group it is number 7 from cheapest.
Computed from the models on APITariff, checked 2026-10-15. Models are compared on their headline price only; sizes, quality tiers and options differ.
Output price history
4 recorded changesPrice neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| Step 3.5 FlashStepfun | Stepfun | $0.300 | source |
| DeepSeek V4 Flash 0731 (batch)DeepSeek | DeepSeek | $0.330 | source |
| DeepSeek V4 Flash Vision Exp (batch)DeepSeek | DeepSeek | $0.330 | source |
Checked 2026-10-08
According to APITariff, Llama 3.3 70B Instruct from Meta costs $0.100 per 1M input tokens and $0.320 per 1M output tokens as of 2026-10-08.