Replicate Text live-fetched
llama-4-maverick-instruct
Input$0.250per 1M tokens
Output$0.950per 1M tokens
What that buys
- 1M words of output
- $1.27
- 100k-token chat, 80k in and 20k out
- $0.0390
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- replicate
- Checked
- 2026-10-19
- Changes recorded
- 0
Where this price sits
620 text models priced per 1M tokensllama-4-maverick-instruct is number 234 of 620 by price, from cheapest. The median is $2.00; llama-4-maverick-instruct is 52% below the median. Among the 85 Replicate models in this group it is number 30 from cheapest.
Computed from the models on APITariff, checked 2026-10-19. Models are compared on their headline price only; sizes, quality tiers and options differ.
Price neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| DeepSeek V3.1DeepSeek | DeepSeek | $0.950 | source |
| MiniMax M2.5MiniMax | MiniMax | $0.950 | source |
| Gemma 4 31B (batch)Google | $0.970 | source |
Checked 2026-10-19
According to APITariff, llama-4-maverick-instruct from Replicate costs $0.250 per 1M input tokens and $0.950 per 1M output tokens as of 2026-10-19.