GPT-4 Turbo pricing and token costs
GPT-4 Turbo is a OpenAI model with a 128,000-token context window. Rates below are per million tokens, and are the ones in effect today.
Retiring. OpenAI removes this model on 2026-10-23. The named replacement is GPT-5.6 Sol.
In practice
The most expensive input rate here at $10 per million, and scheduled for retirement on 23 October 2026 with GPT-5.6 Sol named as its replacement — a model that costs half as much and accepts roughly eight times as much text. Its one favourable number is the output ratio: three to one, the lowest in this catalogue, so verbose answers are penalised less here than anywhere else. It also counts with the older cl100k_base tokenizer, so identical text produces different token totals than the o200k_base models above.
Pricing
- Input, per 1M tokens
- $10.00
- Output, per 1M tokens
- $30.00
- Context window
- 128,000 tokens
- Tokenizer
- cl100k_base
Input and output combined.
Counted exactly, in your browser.
Alternatives
Head to head
Articles that quote these figures
Common questions
- How much does GPT-4 Turbo cost per million tokens?
- $10.00 per million input tokens and $30.00 per million output tokens.
- What is the context window of GPT-4 Turbo?
- 128,000 tokens, covering input and output combined.
- Which tokenizer does GPT-4 Turbo use?
- GPT-4 Turbo uses the cl100k_base encoding. Counts are computed in your browser with the same tokenizer OpenAI publishes, so they are exact.
- Is GPT-4 Turbo being retired?
- OpenAI removes this model on 2026-10-23. The named replacement is GPT-5.6 Sol.
Figures come from OpenAI’s published list prices and are checked against every article on this site that quotes them at build time. They are still estimates of what a request costs — verify against your own billing before committing to them. See the methodology page for how these numbers are actually calculated.