Last verified 2025-09-22 (left) · 2025-09-22 (right)
Gemini 2.5 Flash vs GPT-5 mini — Pricing & Capability Comparison
Gemini 2.5 Flash charges $0.30 per million input tokens and $2.50 per million output tokens. GPT-5 mini comes in at $0.25 / $2.00. Context windows span 1M vs 200K tokens respectively.
Input price (per 1M)
Gemini 2.5 Flash
$0.30
GPT-5 mini
$0.25
GPT-5 mini leads here
Output price (per 1M)
Gemini 2.5 Flash
$2.50
GPT-5 mini
$2.00
GPT-5 mini leads here
Context window
Gemini 2.5 Flash
1,000,000 tokens
GPT-5 mini
200,000 tokens
Gemini 2.5 Flash leads here
Cached input
Gemini 2.5 Flash
Not published
GPT-5 mini
Not published
No published data
Cost comparison for 10K-token workloads
Side-by-side pricing for identical workloads (10,000 total tokens per request) across different distributions.
| Scenario | Gemini 2.5 Flash | GPT-5 mini |
|---|---|---|
Balanced conversation 50% input · 50% output | $0.0140 | $0.0112 |
Input-heavy workflow 80% input · 20% output | $0.0074 | $0.0060 |
Generation heavy 30% input · 70% output | $0.0184 | $0.0148 |
Cached system prompt 90% cached input · 10% fresh output | $0.0052 | $0.0043 |
Frequently asked questions
Which model is cheaper per million input tokens?
GPT-5 mini costs $0.25 per million input tokens versus $0.30 for Gemini 2.5 Flash.
How do output prices compare?
GPT-5 mini charges $2.00 per million output tokens, while Gemini 2.5 Flash costs $2.50 per million.
Which model supports a larger context window?
Gemini 2.5 Flash offers 1,000,000 tokens (1M) versus 200K for GPT-5 mini.