Llama 4 Scout vs GPT-OSS 120B
Side-by-side API pricing comparison · Groq vs Groq
🏆
Llama 4 Scout is 3.6% cheaper on blended cost ($0.555 vs $0.575/Mtok)
Llama 4 Scout
by Groq
Current fast Open weightsInput
$0.110/Mtok
Output
$1.00/Mtok
✓ Cheaper
| Blended avg | $0.555/Mtok |
|---|---|
| Context | 10M tokens |
| Modality | text, image |
| Parameters | 17B (16 experts) |
| Released | Apr 6, 2025 |
GPT-OSS 120B
by Groq
Current fast Open weightsInput
$0.150/Mtok
Output
$1.00/Mtok
| Blended avg | $0.575/Mtok |
|---|---|
| Context | 128K tokens |
| Modality | text |
| Parameters | 120B |
| Released | Jan 1, 2026 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Llama 4 Scout | GPT-OSS 120B | Savings |
|---|---|---|---|
| 1M tokens | $0.56 | $0.57 | $0.02 (3.5%) |
| 10M tokens | $5.55 | $5.75 | $0.2 (3.5%) |
| 100M tokens | $55.5 | $57.5 | $2 (3.5%) |
| 1000M tokens | $555 | $575 | $20 (3.5%) |
Summary
Llama 4 Scout by Groq costs $0.110/Mtok input and $1.00/Mtok output, with a 10M-token context window. It supports text, image input.
GPT-OSS 120B by Groq costs $0.150/Mtok input and $1.00/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, Llama 4 Scout is 3.6% cheaper than GPT-OSS 120B. 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.