GPT API cost per request, October 2026: a chat turn and a long document
Input, cached and output prices for every GPT model, OpenAI's list price next to ours, and what a chat turn and a long-document request cost on GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna.
How a GPT API request is billed
OpenAI bills API calls per token, at three rates per million tokens: input, cached input and output. Output costs more than input on every GPT model. GPT-4o and GPT-4o mini have no cached rate here, so repeated tokens bill at their input rate. A request costs its tokens times the rates of the model it named; there is no seat or plan price.
GPT per-token rates
13 GPT models. Each row shows our price and OpenAI's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| GPT-6.1 Sol | $0.60 | $0.06 | $3.00 | $2.00 | $0.10 | $10.00 |
| GPT-6 Sol | $0.60 | $0.12 | $3.00 | $2.00 | $0.20 | $10.00 |
| GPT-5.5 | $1.50 | $0.15 | $9.00 | $5.00 | $0.50 | $30.00 |
| GPT-6 Astra | $3.00 | $0.30 | $15.00 | $10.00 | $1.00 | $50.00 |
| GPT-6 Luna | $0.0625 | $0.0125 | $0.15 | $0.10 | $0.01 | $0.50 |
| GPT-5.6 Luna | $0.12 | $0.012 | $0.72 | $0.20 | $0.02 | $1.20 |
| GPT-5.6 Sol | $1.20 | $0.12 | $3.00 | $2.00 | $0.20 | $10.00 |
| GPT-5.6 Terra | $1.20 | $0.12 | $3.60 | $2.00 | $0.20 | $12.00 |
| GPT-5.4 | $1.50 | $0.15 | $9.00 | $2.50 | $0.25 | $15.00 |
| GPT-5.4 Mini | $0.45 | $0.045 | $2.70 | $0.75 | $0.075 | $4.50 |
| GPT-5.3-Codex | $1.05 | $0.105 | $8.40 | $1.75 | $0.175 | $14.00 |
| GPT-4o | $1.50 | input rate | $6.00 | $2.50 | input rate | $10.00 |
| GPT-4o mini | $0.09 | input rate | $0.36 | $0.15 | input rate | $0.60 |
USD per million tokens. Ours from the live catalog; list is the price on OpenAI's pricing page, the read date on each model page.
The lowest price here is GPT-6 Luna: $0.0625 in and $0.15 out.
GPT API cost per request, worked
A chat turn of 2,000 input and 500 output tokens, and a long-document request of 50,000 input and 2,000 output. Both sizes are assumptions; nothing is counted at the cached rate.
| Model | Chat turn, list | Chat turn, here | Long document, list | Long document, here |
|---|---|---|---|---|
| GPT-6 Astra | $0.045 | $0.0135 | $0.60 | $0.18 |
| GPT-6.1 Sol | $0.009 | $0.0027 | $0.12 | $0.036 |
| GPT-6 Luna | $0.0005 | $0.0002 | $0.006 | $0.0034 |
Input tokens times the input rate plus output tokens times the output rate, per million.
GPT-6 Astra: $3.00 in and $15.00 out here, against $10.00 and $50.00 at list, 70% under on input and 70% on output.
GPT-6.1 Sol: $0.60 in and $3.00 out here, against $2.00 and $10.00 at list, 70% under on input and 70% on output.
GPT-6 Luna: $0.0625 in and $0.15 out here, against $0.10 and $0.50 at list, 37% under on input and 70% on output.
GPT API cost per month, worked
Two monthly workloads on the same models: 1,000 chat turns a day and 100 long documents a day, each for 30 days. Every request is the size above, so a month of chat is 60 million input and 15 million output tokens, and a month of documents is 150 million input and 6 million output. The volumes are assumptions; nothing is counted at the cached rate.
| Model | Chat month, list | Chat month, here | Document month, list | Document month, here |
|---|---|---|---|---|
| GPT-6 Astra | $1,350.00 | $405.00 | $1,800.00 | $540.00 |
| GPT-6.1 Sol | $270.00 | $81.00 | $360.00 | $108.00 |
| GPT-6 Luna | $13.50 | $6.00 | $18.00 | $10.28 |
USD for 30 days: the per-request cost above times 30,000 chat turns or 3,000 documents.
GPT-6 Astra: $945.00 a month here for both workloads, against $3,150.00 at list, $2,205.00 less.
GPT-6.1 Sol: $189.00 a month here for both workloads, against $630.00 at list, $441.00 less.
GPT-6 Luna: $16.28 a month here for both workloads, against $31.50 at list, $15.22 less.
Cost scales with volume, so 10,000 chat turns a day is ten times the chat column.
What cached input does to the cost
When a request repeats a prefix the API has seen, such as a long system prompt or a document, the response reports those tokens as cached and they bill at the cached rate in the first table. A model with no cached rate bills them at its input rate.
Calling it
Point the SDK at our base URL with your key. Every GPT id in the table works with the same two values.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="gpt-6-astra",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)More in the SDK guide.
Questions
Is there a subscription? No. Credit is prepaid from $10, and each top-up locks your prices for 30 days.
Which GPT model should I use? The cheapest one that does the task. Luna for classification, extraction and other short high-volume work, Sol for most coding and writing, Astra where the harder answer is worth the price. Run the same prompt on each and compare.
Where is the full price list? On the GPT API pricing page, and every other model on the Models page. To see what your own usage would cost, re-price an export on the savings page.