Last verified 2025-09-22 (left) · 2025-09-22 (right)
GPT-4o (fine-tuned) vs GPT-5 nano — Pricing & Capability Comparison
GPT-4o (fine-tuned) charges $3.75 per million input tokens and $15.00 per million output tokens. GPT-5 nano comes in at $0.05 / $0.40. Context windows span 128K vs 200K tokens respectively.
Input price (per 1M)
GPT-4o (fine-tuned)
$3.75
GPT-5 nano
$0.05
GPT-5 nano leads here
Output price (per 1M)
GPT-4o (fine-tuned)
$15.00
GPT-5 nano
$0.40
GPT-5 nano leads here
Context window
GPT-4o (fine-tuned)
128,000 tokens
GPT-5 nano
200,000 tokens
GPT-5 nano leads here
Cached input
GPT-4o (fine-tuned)
$1.875
GPT-5 nano
Not published
GPT-4o (fine-tuned) 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-4o (fine-tuned) | GPT-5 nano | GPT-4o (fine-tuned) cached |
|---|---|---|---|
Balanced conversation 50% input · 50% output | $0.0938 | $0.0023 | $0.0844 |
Input-heavy workflow 80% input · 20% output | $0.0600 | $0.0012 | $0.0450 |
Generation heavy 30% input · 70% output | $0.116 | $0.0030 | $0.111 |
Cached system prompt 90% cached input · 10% fresh output | $0.0487 | $0.0009 | $0.0319 |
Frequently asked questions
Which model is cheaper per million input tokens?
GPT-5 nano costs $0.05 per million input tokens versus $3.75 for GPT-4o (fine-tuned).
How do output prices compare?
GPT-5 nano charges $0.40 per million output tokens, while GPT-4o (fine-tuned) costs $15.00 per million.
Which model supports a larger context window?
GPT-5 nano offers 200,000 tokens (200K) versus 128K for GPT-4o (fine-tuned).