Last verified 2025-09-22 (left) · 2025-09-22 (right)
GPT-5 Chat vs o4-mini — Pricing & Capability Comparison
GPT-5 Chat charges $1.25 per million input tokens and $10.00 per million output tokens. o4-mini comes in at $1.10 / $4.40. Context windows span 200K vs 200K tokens respectively.
Input price (per 1M)
GPT-5 Chat
$1.25
o4-mini
$1.10
o4-mini leads here
Output price (per 1M)
GPT-5 Chat
$10.00
o4-mini
$4.40
o4-mini leads here
Context window
GPT-5 Chat
200,000 tokens
o4-mini
200,000 tokens
GPT-5 Chat leads here
Cached input
GPT-5 Chat
$0.125
o4-mini
Not published
GPT-5 Chat leads here
Cost comparison for 10K-token workloads
Side-by-side pricing for identical workloads (10,000 total tokens per request) across different distributions.
| Scenario | GPT-5 Chat | o4-mini | GPT-5 Chat cached |
|---|---|---|---|
Balanced conversation 50% input · 50% output | $0.0563 | $0.0275 | $0.0506 |
Input-heavy workflow 80% input · 20% output | $0.0300 | $0.0176 | $0.0210 |
Generation heavy 30% input · 70% output | $0.0738 | $0.0341 | $0.0704 |
Cached system prompt 90% cached input · 10% fresh output | $0.0212 | $0.0143 | $0.0111 |
Frequently asked questions
Which model is cheaper per million input tokens?
o4-mini costs $1.10 per million input tokens versus $1.25 for GPT-5 Chat.
How do output prices compare?
o4-mini charges $4.40 per million output tokens, while GPT-5 Chat costs $10.00 per million.
Which model supports a larger context window?
GPT-5 Chat offers 200,000 tokens (200K) versus 200K for o4-mini.