GPT-6 Luna Pro vs Qwen2.5 VL 72B Instruct

Price, context window & benchmark comparison

GPT-6 Luna Pro

OpenAI

$0.10 / $0.50

Input / Output · per 1M tokens

Qwen2.5 VL 72B Instruct

Qwen (Alibaba)

$0.80 / $1.00

Input / Output · per 1M tokens

Compare different models

Verdict: GPT-6 Luna Pro is 4.3× cheaper than Qwen2.5 VL 72B Instruct on a typical 3:1 input/output mix. GPT-6 Luna Pro has the larger context window (1.1M vs 128K).

	GPT-6 Luna Pro	Qwen2.5 VL 72B Instruct
Input price / 1M	$0.10	$0.80
Output price / 1M	$0.50	$1.00
Blended price (3:1)	$0.20	$0.85
Cached input / 1M	$0.01	$0.40
Context window	1.1M	128K
Max output	128K	115K
Intelligence index	—	—
Coding index	—	—
Providers	6	—
Best provider uptime (30m)	100.0%	—
Vision input	Yes	Yes
Reasoning	Yes	No
Tool calling	Yes	No
Released	2026-09-22	2025-02-01
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, GPT-6 Luna Pro or Qwen2.5 VL 72B Instruct?

GPT-6 Luna Pro is 4.3× cheaper than Qwen2.5 VL 72B Instruct on a typical 3:1 input/output mix.

GPT-6 Luna Pro vs Qwen2.5 VL 72B Instruct: which has a bigger context window?

GPT-6 Luna Pro: 1,050,000 tokens. Qwen2.5 VL 72B Instruct: 128,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: GPT-6 Luna Pro ≈ $450.00, Qwen2.5 VL 72B Instruct ≈ $2,100.

More comparisons