OpenAI Pricing & Token Calculator
All 24 OpenAI models on one page: context windows, tokenizer behaviour and list price per 1M input and output tokens. Each row links to a dedicated calculator already preselected to that model.
OpenAI counts every request with the tiktoken Byte-Pair-Encoding tokenizer, which is why every OpenAI model on TokenCalc returns an exact count rather than an estimate.
OpenAI model pricing table
| Model | Tokenizer | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| GPT-5.5 | o200k | 1M | $5.00 | $30.00 |
| GPT-5 | o200k | 400K | $1.25 | $10.00 |
| GPT-5 mini | o200k | 400K | $0.25 | $2.00 |
| GPT-5 nano | o200k | 400K | $0.05 | $0.4 |
| GPT-4o | o200k | 128K | $2.50 | $10.00 |
| GPT-4o mini | o200k | 128K | $0.15 | $0.6 |
| GPT-4.1 | o200k | 1M | $2.00 | $8.00 |
| GPT-4.1 mini | o200k | 1M | $0.4 | $1.60 |
| GPT-4.1 nano | o200k | 1M | $0.1 | $0.4 |
| o3 | o200k | 200K | $2.00 | $8.00 |
| o4-mini | o200k | 200K | $1.10 | $4.40 |
| o3-mini | o200k | 200K | $1.10 | $4.40 |
| o1 | o200k | 200K | $15.00 | $60.00 |
| GPT-4 Turbo | cl100k | 128K | $10.00 | $30.00 |
| GPT-4 | cl100k | 8K | $30.00 | $60.00 |
| GPT-3.5 Turbo | cl100k | 16K | $0.5 | $1.50 |
| text-embedding-3-small | cl100k | – | $0.02 | — |
| text-embedding-3-large | cl100k | – | $0.13 | — |
| GPT-5.6 Sol | o200k | 1M | $4.00 | $20.00 |
| GPT-5.6 Terra | o200k | 1M | $2.00 | $12.00 |
| GPT-5.6 Luna | o200k | 1M | $0.2 | $1.20 |
| GPT-5.4 | o200k | 400K | $2.50 | $15.00 |
| GPT-5.4 mini | o200k | 400K | $0.75 | $4.50 |
| GPT-5.4 nano | o200k | 400K | $0.2 | $1.25 |
Cheapest OpenAI models per 1M input tokens
ERNIE X1 at $0.006/1M, Doubao 1.6 Flash at $0.01/1M, text-embedding-3-small at $0.02/1M, Doubao 1.6 Lite at $0.02/1M, SenseNova 5.1 (商汤) at $0.04/1M. Output rates run several times higher than input rates on most vendors, so a token-heavy workflow with long generations is priced by the output column.
Largest OpenAI context windows
Gemini 3.1 Pro (2M), Gemini 2.5 Pro (2M), GPT-5.5 (1M). Context headroom is usually the binding constraint before price is — check it first.
Count tokens for any OpenAI model
Pick the model from the dropdown, or open any row above for a page preselected to it.
OpenAI pricing FAQs
How many OpenAI models can I count tokens for?
24 on TokenCalc, each with its own page and its own preselected calculator: GPT-5.5, GPT-5, GPT-5 mini, GPT-5 nano, GPT-4o, GPT-4o mini, GPT-4.1, GPT-4.1 mini and more.
Are OpenAI token counts exact?
OpenAI counts every request with the tiktoken Byte-Pair-Encoding tokenizer, which is why every OpenAI model on TokenCalc returns an exact count rather than an estimate.
Which OpenAI model is cheapest per 1M input tokens?
Among the models tracked here: ERNIE X1 at $0.006/1M, Doubao 1.6 Flash at $0.01/1M, text-embedding-3-small at $0.02/1M, Doubao 1.6 Lite at $0.02/1M, SenseNova 5.1 (商汤) at $0.04/1M. Prices verified 2 October 2026.