Llama API pricing
Every Llama model we track, with the cheapest price per 1M tokens across 12 providers. Collected daily.
Llama API prices by model
Standard (real-time) rates per 1M tokens, newest first. “Cheapest” is the lowest input price across every provider we track; batch and cached-input rates are on each model page.
| Model | Cheapest input | Output | Cheapest on |
|---|---|---|---|
| Llama 4 Maverick 17B128K context | $0.188 | $0.652 | OpenRouter |
| Llama 4 Scout328K context | $0.100 | $0.300 | OpenRouter |
| Llama 3.3 70B128K context | $0.100 | $0.320 | Deep Infra |
| Llama 3.2 1B128K context | $0.020 | $0.020 | Novita AI |
| Llama 3.2 3B128K context | $0.050 | $0.330 | OpenRouter |
| Llama 3.2 Instruct 11B | $0.160 | $0.160 | Amazon AWS |
| Llama 3.2 Instruct 90B | $0.720 | $0.720 | Amazon AWS |
| Llama 3.1 8B128K context | $0.020 | $0.050 | Novita AI |
| Llama 3.1 405B128K context | $3.50 | $3.50 | Together AI |
| Llama 3.1 70B128K context | $0.400 | $0.400 | OpenRouter |
| Llama 3 70B8K context | $0.880 | $0.880 | Together AI |
| Llama 3 8B8K context | $0.200 | $0.200 | Together AI |
Llama price history
Average input price per 1M tokens across the providers serving each model, last 90 days.
Frequently Asked Questions
What is the cheapest Llama API?
Of the 12 Llama models we track, Llama 3.2 1B has the lowest input price right now: $0.020 per 1M input tokens on Novita AI. Prices are collected daily from 12 providers — see the table above for every model.
Where is Llama 4 Maverick 17B cheapest?
Llama 4 Maverick 17B is served by 6 providers we track. The lowest standard input price is $0.188 per 1M tokens on OpenRouter. Throughput, latency and context limits differ between hosts, so check the model page before committing.