Grok API cost per request, October 2026: a chat turn and a long document
Input, cached and output prices for every Grok model, xAI's list price next to ours, and what a chat turn and a long-document request cost on Grok 4.7, 4.5 and 4.3.
How a Grok API request is billed
xAI bills Grok API calls per token, at three rates per million tokens: input, cached input and output. Grok output costs two to three times input, a smaller gap than most flagship models. A request costs its tokens times the rates of the model it named; there is no seat or plan price.
Grok per-token rates
5 Grok models. Each row shows our price and xAI's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| Grok 4.6 | $0.60 | $0.15 | $1.80 | $2.00 | $0.50 | $6.00 |
| Grok 4.7 | $0.60 | $0.15 | $1.80 | $2.00 | $0.50 | $6.00 |
| Grok 4.5 | $0.60 | $0.09 | $1.80 | $2.00 | $0.30 | $6.00 |
| Grok 4.3 | $0.75 | $0.12 | $1.50 | $1.25 | $0.20 | $2.50 |
| Grok 4.20 Multi-Agent (0309) | $0.75 | $0.12 | $1.50 | $1.25 | $0.20 | $2.50 |
USD per million tokens. Ours from the live catalog; list is the price on xAI's pricing page, the read date on each model page.
The lowest price here is Grok 4.3: $0.75 in and $1.50 out.
Grok 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 |
|---|---|---|---|---|
| Grok 4.7 | $0.007 | $0.0021 | $0.112 | $0.0336 |
| Grok 4.5 | $0.007 | $0.0021 | $0.112 | $0.0336 |
| Grok 4.3 | $0.0038 | $0.0023 | $0.0675 | $0.0405 |
Input tokens times the input rate plus output tokens times the output rate, per million.
Grok 4.7: $0.60 in and $1.80 out here, against $2.00 and $6.00 at list, 70% under on input and 70% on output.
Grok 4.5: $0.60 in and $1.80 out here, against $2.00 and $6.00 at list, 70% under on input and 70% on output.
Grok 4.3: $0.75 in and $1.50 out here, against $1.25 and $2.50 at list, 40% under on input and 40% on output.
Grok 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 |
|---|---|---|---|---|
| Grok 4.7 | $210.00 | $63.00 | $336.00 | $100.80 |
| Grok 4.5 | $210.00 | $63.00 | $336.00 | $100.80 |
| Grok 4.3 | $112.50 | $67.50 | $202.50 | $121.50 |
USD for 30 days: the per-request cost above times 30,000 chat turns or 3,000 documents.
Grok 4.7: $163.80 a month here for both workloads, against $546.00 at list, $382.20 less.
Grok 4.5: $163.80 a month here for both workloads, against $546.00 at list, $382.20 less.
Grok 4.3: $189.00 a month here for both workloads, against $315.00 at list, $126.00 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 Grok 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="grok-4.7",
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 Grok model should I use? Grok 4.7 for most work; its input and output prices here match 4.5 and 4.6. Grok 4.3 has the lower output price, so it fits long answers where the newest model isn't needed. Run the same prompt on each and compare.
Where is the full price list? On the Grok 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.