open-source
Llama 4 Maverick 17b 128e Instruct vs Llama 4 Scout 17b 16e Instruct
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Llama 4 Maverick 17b 128e Instruct | Llama 4 Scout 17b 16e Instruct |
|---|---|---|
| Provider | groq | groq |
| Model ID | groq/meta-llama/llama-4-maverick-17b-128e-instruct | groq/meta-llama/llama-4-scout-17b-16e-instruct |
| Input / 1M tokens | $0.20 | $0.11 (45% cheaper) |
| Output / 1M tokens | $0.60 | $0.34 (43% cheaper) |
| Cached input / 1M | — | — |
| Context window | 131kk tokens | 131kk tokens |
| Max output | 8kk tokens | 8kk tokens |
| Vision | ✅ | ✅ |
| Function calling | ✅ | ✅ |
| Prompt caching | ⬜ | ⬜ |
| Web search | ⬜ | ⬜ |
| JSON schema | ✅ | ✅ |
Monthly cost comparison
No cache discount applied — pure token costs at three usage scales.
| Scale | Llama 4 Maverick 17b 128e Instruct | Llama 4 Scout 17b 16e Instruct | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $0.32 | $0.18 | Llama 4 Scout 17b 16e Instruct saves 44% |
| Medium 10M in / 2M out | $3.20 | $1.78 | Llama 4 Scout 17b 16e Instruct saves 44% |
| Large 100M in / 20M out | $32.00 | $17.80 | Llama 4 Scout 17b 16e Instruct saves 44% |
Category winners
Cheapest input
Llama 4 Scout 17b 16e Instruct
$0.11/M
· 45% less than the other
Cheapest output
Llama 4 Scout 17b 16e Instruct
$0.34/M
· 43% less than the other
Larger context
Llama 4 Maverick 17b 128e Instruct
131kk tokens
More features
Llama 4 Maverick 17b 128e Instruct
3 / 5 capabilities
(tied)
Better for…
Short interactions & high-throughput APIs
$0.34/M output — 43% cheaper on output at scale
Llama 4 Scout 17b 16e Instruct
Cost-sensitive production at scale
$17.80/month at 100M-token scale — 44% cheaper than the alternative
Llama 4 Scout 17b 16e Instruct
Deep-dive on each model
Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.