Llama 4 Scout vs Llama Nemotron Ultra 253B
Side-by-side API pricing comparison · Meta vs NVIDIA
🏆
Llama 4 Scout is 833.3% cheaper on blended cost ($0.225 vs $2.10/Mtok)
Llama 4 Scout
by Meta
Current open weights Open weightsInput
$0.110/Mtok
Output
$0.340/Mtok
✓ Cheaper
| Blended avg | $0.225/Mtok |
|---|---|
| Context | 10M tokens |
| Modality | text, image |
| Parameters | 17B (16 experts) |
| Released | Apr 6, 2025 |
Llama Nemotron Ultra 253B
by NVIDIA
Current open weights Open weightsInput
$0.600/Mtok
Output
$3.60/Mtok
| Blended avg | $2.10/Mtok |
|---|---|
| Context | 128K tokens |
| Modality | text |
| Parameters | 253B |
| Released | Jan 1, 2025 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Llama 4 Scout | Llama Nemotron Ultra 253B | Savings |
|---|---|---|---|
| 1M tokens | $0.23 | $2.1 | $1.88 (89.5%) |
| 10M tokens | $2.25 | $21 | $18.75 (89.3%) |
| 100M tokens | $22.5 | $210 | $187.5 (89.3%) |
| 1000M tokens | $225 | $2100 | $1875 (89.3%) |
Summary
Llama 4 Scout by Meta costs $0.110/Mtok input and $0.340/Mtok output, with a 10M-token context window. It supports text, image input.
Llama Nemotron Ultra 253B by NVIDIA costs $0.600/Mtok input and $3.60/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, Llama 4 Scout is 833.3% cheaper than Llama Nemotron Ultra 253B. It also has a larger context window.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.