Llama 4 Scout pricing & price history
Llama 4 Scout by Meta Llama costs $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 1.3M token context window. The cheapest provider currently charges $0.08 input / $0.24 output.
Price history
| Date | Input | Output |
|---|---|---|
| 2026-10-16 | $0.18 → $0.10 -44% | $0.59 → $0.30 -49% |
| 2026-10-12 | $0.10 → $0.18 +80% | $0.30 → $0.59 +97% |
No real-traffic data for Meta Llama's own API on this model (it may not be served directly); the table below covers third-party hosts and says nothing about the official API.
Which platform runs Llama 4 Scout most reliably
2 platformsBy 30-day real-traffic success rate, DeepInfra is the most stable and also the cheapest.
| Platform | Last 30 days | Stability | 24 h | 30 min | |
|---|---|---|---|---|---|
| DeepInfra most stable | Often unstable (14 d)avg 93.37% | 100% | 100% | ||
| Collecting data | — | — |
Success rates come from real API traffic routed to each platform (public OpenRouter data), not our probes; each daily bar is the average of that day's samples. Green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %. Updated 28m ago.
Cost calculator
Cheaper alternatives to Llama 4 Scout
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
 GLM 5.3 Flash Z.ai (Zhipu) | $0.0399 | $0.0784 | 1M | 27.8 | compare |
 DeepSeek V4.1 Flash DeepSeek | $0.022 | $0.40 | 1M | — | compare |
DeepSeek V4.1 Flash 1017 DeepSeek | $0.098 | $0.29 | 1M | 28.6 | compare |
Using a relay or third-party API?
Check for free whether it really serves Llama 4 Scout: output fingerprint, tokenizer and billing evidence, results in 1–3 minutes.
About Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
FAQ
How much does Llama 4 Scout cost?
Llama 4 Scout by Meta Llama costs $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 1.3M token context window. The cheapest provider currently charges $0.08 input / $0.24 output. A typical request with 2,000 input and 500 output tokens costs about $0.0003.
What is the context window of Llama 4 Scout?
Llama 4 Scout supports up to 1,310,720 tokens of context and up to 16,384 output tokens per request.
Has Llama 4 Scout’s price changed?
Yes. ModelBank recorded 2 price changes; the latest on 2026-10-16.
Is Llama 4 Scout being deprecated?
No retirement date has been announced for Llama 4 Scout as of 2026-11-12.
What are cheaper alternatives to Llama 4 Scout?
Cheaper options include GLM 5.3 Flash ($0.0399/$0.0784), DeepSeek V4.1 Flash ($0.022/$0.40), DeepSeek V4.1 Flash 1017 ($0.098/$0.29).