Side by side pricing and context for GPT-4 and GPT-4.1. Rates are curated catalog values with last verified dates on each model page.
GPT-4
Original GPT-4 API tier kept for legacy cost audits. Prefer GPT-4.1 or GPT-5 for new builds; use this row when older integrations still call gpt-4.
Input $30.00 / Output $60.00 per 1M
Context 8.2K · Exact (cl100k_base)
GPT-4.1
Strong all-round OpenAI model with a very large context window. Prefer for long documents, tool-heavy apps, and workloads that benefit from prompt caching.
Input $2.00 / Output $8.00 per 1M
Context 1M · Exact (o200k_base)
Quick take
- GPT-4.1 is cheaper on input in this catalog snapshot.
- GPT-4.1 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-4 | GPT-4.1 |
|---|---|---|
| Input / 1M | $30.00 | $2.00 |
| Output / 1M | $60.00 | $8.00 |
| Cached input / 1M | n/a | $0.500 |
| Context | 8.2K | 1M |
| Tokenizer | Exact (cl100k_base) | Exact (o200k_base) |