Llama 4 Scout pricing
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... This page tracks 2 listings in total. Highlighted lows are $0.080 per million input and $0.300 per million output (see table for which seller matches each).
Pricing across providers
Use this table to read Llama 4 Scout list prices. We show 2 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.080 | $0.300 | — | — |
VA Vercel Ai Gateway | $0.100 | $0.300 | — | — |
Input vs output · per provider
Cost calculator
Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Llama 4 Scout.
Provider
0.008000¢ / req
0.015000¢ / req
Model specifications
Quick spec sheet for Llama 4 Scout before you dive back into pricing. Reported under Meta.
- Context window
- 131,072 tokens
- Max output
- 8,192 tokens
- Vision (images)
- Yes
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Apr 2025
- Primary provider
- Meta
- Model family
- N/A
Compare Llama 4 Scout
These links open full side by side pages for Llama 4 Scout. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular Llama 4 Scout comparisons
- Llama 4 Scout vs Llama 3.1 70B
Compare pricing side by side
- Llama 4 Scout vs Llama 3.1 8B
Compare pricing side by side
- Llama 4 Scout vs GPT-4o
Compare pricing side by side
- Llama 4 Scout vs GPT-4o mini
Compare pricing side by side
- Llama 4 Scout vs Claude Sonnet 4.6
Compare pricing side by side
- Llama 4 Scout vs Gemini 2.0 Flash
Compare pricing side by side
Frequently asked questions
Quick frequently asked items for Llama 4 Scout pricing and limits. The short model note from our index: 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...
Also from Meta
Other models by Meta with live pricing in our catalog.