# Llama API prices

Llama lists 7 model(s) in the Sovyron catalog. Every price is Llama's own, in USD per 1M tokens.
Prices as of 2026-10-04.

| Model | Input $/1M | Output $/1M | Cache read $/1M | Context | Released |
| --- | --- | --- | --- | --- | --- |
| Cerebras-Llama-4-Maverick-17B-128E-Instruct | free | free | — | 128k | Apr 5, 2025 |
| Cerebras-Llama-4-Scout-17B-16E-Instruct | free | free | — | 128k | Apr 5, 2025 |
| Groq-Llama-4-Maverick-17B-128E-Instruct | free | free | — | 128k | Apr 5, 2025 |
| Llama 4 Maverick 17B 128E Instruct FP8 | free | free | — | 128k | Apr 5, 2025 |
| Llama-4-Scout-17B-16E-Instruct-FP8 | free | free | — | 128k | Apr 5, 2025 |
| Llama-3.3-70B-Instruct | free | free | — | 128k | Dec 6, 2024 |
| Llama-3.3-8B-Instruct | free | free | — | 128k | Dec 6, 2024 |

HTML page: https://sovyron.com/providers/llama/
Full dataset: https://sovyron.com/data/catalog.json