Hong Life CalculatorsHow it works
Cost per request = (uncached input tokens × input price + cached input tokens × cached-input price + output tokens × output price) ÷ 1,000,000, with prices in US$ per 1 million tokens. No batch discount could be confirmed on the official page, so none is applied. Day = request cost × requests per day; month = day × days per month; year = month × 12. “Saved” compares with the same traffic at the plain input and output price. Meta Model API, Standard mode. Meta does not publish a first-party per-token price for Llama models; Llama is open-weight and is self-hosted or run by cloud partners. Taxes, tools (web search, code execution), image or audio tokens, long-context surcharges and cache-write fees are not included.
Meta API prices (US$ per 1M tokens, checked 10 Nov 2026)
| AI model | Input price | Cached-input price | Output price |
|---|---|---|---|
| Muse Wonder 1.0 | 4 | 0.2 | 20 |
| Muse Spark 1.3/1.2/1.1 | 1.25 | 0.15 | 4.25 |
⚠ Estimates for information only — not financial advice.
FAQ
Is there an official price for Llama?
No. Meta’s Model API price list covers its Muse models. Llama models are open-weight: you run them on your own GPUs or through a cloud partner, whose price list applies. Use the LLM GPU memory and GPU cloud-vs-buy calculators for self-hosting.
Does Meta charge more for long prompts?
Meta states there is no long-context premium: the same per-token rate applies whether the context window is nearly empty or nearly full.
Checked 10 Nov 2026. Meta official API pricing page (https://dev.meta.ai/docs/pricing-rate-limits), read on 10 Nov 2026. No batch discount listed.