Side by side pricing and context for GPT-3.5 Turbo and GPT-4o mini. Rates are curated catalog values with last verified dates on each model page.
GPT-3.5 Turbo
Legacy OpenAI chat model kept for migration cost checks against Mini and Nano tiers. Prefer GPT-4.1 Mini or GPT-5 Mini for new production apps.
Input $0.500 / Output $1.50 per 1M
Context 16.4K · Exact (cl100k_base)
GPT-4o mini
Inexpensive OpenAI chat model for customer support and simple tools. Popular cheap baseline. Pair with Exact token counts when budgeting.
Input $0.150 / Output $0.600 per 1M
Context 128K · Exact (o200k_base)
Quick take
- GPT-4o mini is cheaper on input in this catalog snapshot.
- GPT-4o mini is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | GPT-3.5 Turbo | GPT-4o mini |
|---|---|---|
| Input / 1M | $0.500 | $0.150 |
| Output / 1M | $1.50 | $0.600 |
| Cached input / 1M | n/a | $0.075 |
| Context | 16.4K | 128K |
| Tokenizer | Exact (cl100k_base) | Exact (o200k_base) |