Llama 4 Scout 17B 16E Instruct
Provider: wandb ·
wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $17.0k |
| Output | $66.0k |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$30.2k
per month
Medium
10M in / 2000k out
$302.0k
per month
Large
100M in / 20000k out
$3020.0k
per month
Context
- Input window
- 64,000 tokens
- Max output
- 64,000 tokens
Capabilities
- ⬜ Vision (image input)
- ⬜ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Llama 4 Scout 17B 16E Instruct with similar models
Llama 3.1 8B Instruct
wandb
$22.0k in
/ $22.0k out
Gpt Oss 120b
wandb
$15.0k in
/ $60.0k out
Qwen3 235B A22B Instruct 2507
wandb
$10.0k in
/ $10.0k out
Qwen3 235B A22B Thinking 2507
wandb
$10.0k in
/ $10.0k out
DeepSeek V3.1
wandb
$55.0k in
/ $165.0k out
Phi 4 Mini Instruct
wandb
$8000 in
/ $35.0k out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.