GPT-3.5 Turbo (older v0613) vs Llama 4 Scout

Price, context window & benchmark comparison

GPT-3.5 Turbo (older v0613)

OpenAI

$1.00 / $2.00

Input / Output · per 1M tokens

Llama 4 Scout

Meta Llama

$0.10 / $0.30

Input / Output · per 1M tokens

Compare different models

Verdict: Llama 4 Scout is 8.3× cheaper than GPT-3.5 Turbo (older v0613) on a typical 3:1 input/output mix. Llama 4 Scout has the larger context window (1.3M vs 4K).

	GPT-3.5 Turbo (older v0613)	Llama 4 Scout
Input price / 1M	$1.00	$0.10
Output price / 1M	$2.00	$0.30
Blended price (3:1)	$1.25	$0.15
Cached input / 1M	—	—
Context window	4K	1.3M
Max output	4K	16K
Intelligence index	—	—
Coding index	—	8.2
Providers	—	3
Best provider uptime (30m)	—	99.9%
Vision input	No	Yes
Reasoning	No	No
Tool calling	Yes	Yes
Released	2024-01-25	2025-04-05
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, GPT-3.5 Turbo (older v0613) or Llama 4 Scout?

Llama 4 Scout is 8.3× cheaper than GPT-3.5 Turbo (older v0613) on a typical 3:1 input/output mix.

GPT-3.5 Turbo (older v0613) vs Llama 4 Scout: which has a bigger context window?

GPT-3.5 Turbo (older v0613): 4,095 tokens. Llama 4 Scout: 1,310,720 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: GPT-3.5 Turbo (older v0613) ≈ $3,000, Llama 4 Scout ≈ $350.00.

More comparisons