Side by side pricing and context for GPT-4 Turbo and GPT-4o. Rates are curated catalog values with last verified dates on each model page.
GPT-4 Turbo
Legacy OpenAI Turbo tier still seen in older integrations. Prefer GPT-4.1 or GPT-5 for new builds; keep this row for migration cost checks.
Input $10.00 / Output $30.00 per 1M
Context 128K · Exact (cl100k_base)
GPT-4o
Multimodal OpenAI workhorse for chat and mixed text workloads. Still widely deployed; compare against GPT-4.1 / GPT-5 in TokenCALC before locking a stack.
Input $2.50 / Output $10.00 per 1M
Context 128K · Exact (o200k_base)
Quick take
- GPT-4o is cheaper on input in this catalog snapshot.
- GPT-4o 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 Turbo | GPT-4o |
|---|---|---|
| Input / 1M | $10.00 | $2.50 |
| Output / 1M | $30.00 | $10.00 |
| Cached input / 1M | $5.00 | $1.25 |
| Context | 128K | 128K |
| Tokenizer | Exact (cl100k_base) | Exact (o200k_base) |