GPT-3.5 Turbo Instruct vs GPT-6 Luna

Price, context window & benchmark comparison

GPT-3.5 Turbo Instruct

OpenAI

$1.50 / $2.00

Input / Output · per 1M tokens

GPT-6 Luna

OpenAI

$0.10 / $0.50

Input / Output · per 1M tokens

Compare different models

Verdict: GPT-6 Luna is 8.1× cheaper than GPT-3.5 Turbo Instruct on a typical 3:1 input/output mix. GPT-6 Luna has the larger context window (1.1M vs 4K).

	GPT-3.5 Turbo Instruct	GPT-6 Luna
Input price / 1M	$1.50	$0.10
Output price / 1M	$2.00	$0.50
Blended price (3:1)	$1.63	$0.20
Cached input / 1M	—	$0.01
Context window	4K	1.1M
Max output	4K	128K
Intelligence index	—	37.3
Coding index	—	—
Providers	—	7
Best provider uptime (30m)	—	100.0%
Vision input	No	Yes
Reasoning	No	Yes
Tool calling	No	Yes
Released	2023-09-28	2026-09-22
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, GPT-3.5 Turbo Instruct or GPT-6 Luna?

GPT-6 Luna is 8.1× cheaper than GPT-3.5 Turbo Instruct on a typical 3:1 input/output mix.

GPT-3.5 Turbo Instruct vs GPT-6 Luna: which has a bigger context window?

GPT-3.5 Turbo Instruct: 4,095 tokens. GPT-6 Luna: 1,050,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: GPT-3.5 Turbo Instruct ≈ $4,000, GPT-6 Luna ≈ $450.00.

More comparisons