Replicate Text live-fetched
llama-2-70b
Input$0.650per 1M tokens
Output$2.75per 1M tokens
What that buys
- 1M words of output
- $3.67
- 100k-token chat, 80k in and 20k out
- $0.1070
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- replicate
- Checked
- 2026-10-15
- Changes recorded
- 0
Where this price sits
609 text models priced per 1M tokensllama-2-70b is number 360 of 609 by price, from cheapest. The median is $2.00; llama-2-70b is 38% above the median. Among the 85 Replicate models in this group it is number 40 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.
Price neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| Step 5 PreviewStepfun | Stepfun | $2.70 | source |
| llama-2-70b-chatReplicate | Replicate | $2.75 | source |
| meta-llama-3-70bReplicate | Replicate | $2.75 | source |
Checked 2026-10-15
According to APITariff, llama-2-70b from Replicate costs $0.650 per 1M input tokens and $2.75 per 1M output tokens as of 2026-10-15.