Llama 4 Scout vs Qwen2.5 72B Instruct

Price, context window & benchmark comparison

Meta Llama

Llama 4 Scout

Meta Llama
$0.10 / $0.30
Input / Output · per 1M tokens
VS
Qwen (Alibaba)

Qwen2.5 72B Instruct

Qwen (Alibaba)
$0.36 / $0.40
Input / Output · per 1M tokens
Compare different models
Meta Llama
Qwen (Alibaba)
Verdict: Llama 4 Scout is 2.5× cheaper than Qwen2.5 72B Instruct on a typical 3:1 input/output mix. Llama 4 Scout has the larger context window (1.3M vs 33K).
Llama 4 ScoutQwen2.5 72B Instruct
Input price / 1M$0.10$0.36
Output price / 1M$0.30$0.40
Blended price (3:1)$0.15$0.37
Cached input / 1M
Context window1.3M33K
Max output16K16K
Intelligence index
Coding index8.2
Providers3
Best provider uptime (30m)99.9%
Vision inputYesNo
ReasoningNoNo
Tool callingYesYes
Released2025-04-052024-09-19
Retirement

Cost calculator

FAQ

Which is cheaper, Llama 4 Scout or Qwen2.5 72B Instruct?

Llama 4 Scout is 2.5× cheaper than Qwen2.5 72B Instruct on a typical 3:1 input/output mix.

Llama 4 Scout vs Qwen2.5 72B Instruct: which has a bigger context window?

Llama 4 Scout: 1,310,720 tokens. Qwen2.5 72B Instruct: 32,768 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Llama 4 Scout ≈ $350.00, Qwen2.5 72B Instruct ≈ $920.00.

More comparisons