GPT-3.5 Turbo (older v0613) vs Ministral 3 8B 2512

Price, context window & benchmark comparison

GPT-3.5 Turbo (older v0613)

OpenAI

$1.00 / $2.00

Input / Output · per 1M tokens

Ministral 3 8B 2512

Mistral AI

$0.15 / $0.15

Input / Output · per 1M tokens

Compare different models

Verdict: Ministral 3 8B 2512 is 8.3× cheaper than GPT-3.5 Turbo (older v0613) on a typical 3:1 input/output mix. Ministral 3 8B 2512 has the larger context window (262K vs 4K).

	GPT-3.5 Turbo (older v0613)	Ministral 3 8B 2512
Input price / 1M	$1.00	$0.15
Output price / 1M	$2.00	$0.15
Blended price (3:1)	$1.25	$0.15
Cached input / 1M	—	$0.015
Context window	4K	262K
Max output	4K	210K
Intelligence index	—	5.5
Coding index	—	9.7
Providers	—	3
Best provider uptime (30m)	—	98.8%
Vision input	No	Yes
Reasoning	No	No
Tool calling	Yes	Yes
Released	2024-01-25	2025-12-02
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, GPT-3.5 Turbo (older v0613) or Ministral 3 8B 2512?

Ministral 3 8B 2512 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 Ministral 3 8B 2512: which has a bigger context window?

GPT-3.5 Turbo (older v0613): 4,095 tokens. Ministral 3 8B 2512: 262,144 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, Ministral 3 8B 2512 ≈ $375.00.

More comparisons