Llama 4 Scout (DeepInfra) vs Llama 4 Maverick
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepInfra
3 providers:
Groq $0.110/$0.340
Meta $0.110/$0.340
DeepInfra $0.100/$0.300
|
by DeepInfra
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Apr 6, 2025 | Apr 6, 2025 |
| Pricing per million tokens | ||
| Input | $0.100/Mtok | $0.200/Mtok |
| Output | $0.300/Mtok | $0.800/Mtok |
| Blended avg | $0.150/Mtok | $0.350/Mtok |
| Specifications | ||
| Context window | 10M tokens | 1M tokens |
| Parameters | 17B (16 experts) | 17B (128 experts) |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks sources: Vellum LLM Leaderboard (Jun 2026), Meta model card / Vellum LLM Leaderboard | ||
| Avg benchmark score | 46.8 | 65.1 |
| Perf / dollar | 312 | 186 |
| GPQA Diamond | 57.2 | 69.8 |
| LiveCodeBench | 32.8 | 41 |
| MMMLU | 75 | 84.6 |
| SWE-Bench Verified | 28 | — |
| Humanity's Last Exam | 12 | — |
| ARC-AGI 2 | 15 | — |
| AIME 2025 | 45 | — |
| BFCL | 58 | — |
| HumanEval | 80 | — |
| MATH 500 | 65 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 10.3 | 14.5 |
| AA Agentic Index | 1.1 | 1.2 |
| AA-Omniscience Index (−100–100) | -52.1 | -41.9 |
| Providers | ||
| Available from |
Groq — $0.110/$0.340/Mtok
Meta — $0.110/$0.340/Mtok
DeepInfra — $0.100/$0.300/Mtok
|
DeepInfra — $0.200/$0.800/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Llama 4 Scout | Llama 4 Maverick | Savings |
|---|---|---|---|
| 1M tokens | $0.15 | $0.35 | $0.2 (57.1%) |
| 10M tokens | $1.5 | $3.5 | $2 (57.1%) |
| 100M tokens | $15 | $35 | $20 (57.1%) |
| 1000M tokens | $150 | $350 | $200 (57.1%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.150/Mtok blended vs $0.350 — 57.1% less on the same 50/50 token mix
- you need the longer context: 10M tokens vs 1M (10×)
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
- raw capability matters more than price: 65.1 vs 46.8 average benchmark score
Summary
Llama 4 Scout by DeepInfra costs $0.100/Mtok input and $0.300/Mtok output, with a 10M-token context window. It supports text, image input and is available from 3 providers.
Llama 4 Maverick by DeepInfra costs $0.200/Mtok input and $0.800/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, Llama 4 Scout is 57.1% cheaper than Llama 4 Maverick.It also has a larger context window.
On benchmarks, Llama 4 Maverick scores higher (65.1 vs 46.8) on average. In terms of value, Llama 4 Scout has better performance per dollar (312 vs 186).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.