GLM API pricing, October 2026: every Z.ai model per million tokens
Input, cached and output prices for every GLM model, Z.ai's list price next to ours, and what a chat turn and a long-document request cost on GLM 5.3, 5.2 and 5.3 Flash.
How the GLM API is priced
Z.ai bills GLM API calls per token, at three rates per million tokens: input, cached input and output. At list, GLM output costs three to three and a half times input. A request costs its tokens times the rates of the model it named; there is no seat or plan price.
Every GLM model
4 GLM models. Each row shows our price and Z.ai's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| GLM 5.3 | $0.3276 | $0.0608 | $1.0296 | $1.092 | $0.2028 | $3.432 |
| GLM 5.3 Flash | $0.084 | $0.009 | $0.15 | $0.15 | $0.03 | $0.50 |
| GLM 5.2 | $0.18 | $0.051 | $0.60 | $0.60 | $0.15 | $2.00 |
| GLM 5.1 | $0.5796 | $0.1076 | $1.8216 | $0.966 | $0.1794 | $3.036 |
USD per million tokens. Ours from the live catalog; list is the price on Z.ai's pricing page, the read date on each model page.
The lowest price here is GLM 5.3 Flash: $0.084 in and $0.15 out.
Two requests, 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 |
|---|---|---|---|---|
| GLM 5.3 | $0.0039 | $0.0012 | $0.0615 | $0.0184 |
| GLM 5.2 | $0.0022 | $0.0007 | $0.034 | $0.0102 |
| GLM 5.3 Flash | $0.0006 | $0.0002 | $0.0085 | $0.0045 |
Input tokens times the input rate plus output tokens times the output rate, per million.
GLM 5.3: $0.3276 in and $1.0296 out here, against $1.092 and $3.432 at list, 70% under on input and 70% on output.
GLM 5.2: $0.18 in and $0.60 out here, against $0.60 and $2.00 at list, 70% under on input and 70% on output.
GLM 5.3 Flash: $0.084 in and $0.15 out here, against $0.15 and $0.50 at list, 44% under on input and 70% on output.
Cached input
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 GLM 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="glm-5.3",
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. New accounts start with $1 free.
Which GLM model should I use? GLM 5.3 for most work; here it costs less than GLM 5.1 on input and output. GLM 5.3 Flash for high-volume chat, tagging and agent subtasks, at cents per million tokens. Run the same prompt on both and compare.
Where is the full price list? On the GLM 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.