GLM-5.3 costs LKR 424 per million input tokens and LKR 1,333 per million output tokens on Roar AI, billed in Sri Lankan rupees on one invoice. Z.ai’s open flagship for coding agents and security work.
Prices are shown in LKR to make model costs easier to estimate and manage for Sri Lankan teams, with the published US dollar rate beside each.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 2,606. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 20 November 2026. Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.
glm-5.3For security analysis and command-line agents, it is worth testing. Z.ai reports 84.5% on the CyberGym security benchmark. Its headline coding gain is on a private benchmark whose method is not published, so try it on your own code.
For simple requests, look elsewhere. Every call reasons and there is no fast mode, so simple requests are slower and dearer than they need to be. It also reads text only.
| Model | Input | Output | Choose it for |
|---|---|---|---|
| GLM-5.3 | LKR 424 | LKR 1,333 | Coding agents and security work. |
| DeepSeek-V4-Pro | LKR 519 | LKR 1,039 | General coding, with a no-thinking mode for quick answers. |
| GLM-5.3-Flash | LKR 64.94 | LKR 216 | A low-cost model that reads images and video. |
| Kimi K3 | LKR 1,234 | LKR 6,169 | Web research, images and video. |
Prices per 1M tokens.
GLM-5.3 is Z.ai’s top model, and an unusual kind of upgrade: the base model is the same as GLM-5.2, and every gain came from further training on top of it. The gains are largest where Z.ai aimed them: 66.9% on DeepSWE, up from 46.2%, and 84.5% on the CyberGym security benchmark, which Z.ai puts ahead of Claude Fable 5.
It always thinks before answering, at low, high or max effort (max is the default), and handles a million-token context. The weights are open under Z.ai’s own licence, which asks the very largest companies to pass a security review first.
Roar AI provides access to GLM-5.3 through the Roar AI gateway, with usage billed in LKR and no foreign card needed. Developers can use GLM-5.3 alongside other supported models without maintaining a separate integration for every provider.
Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Requests to GLM-5.3 are processed in Singapore, outside Sri Lanka.
Roar AI’s locally hosted model is separate and is labelled as such: if a workload has to stay in the country, Qwen 3.8 27B LK runs on our own server in Colombo.
Input is LKR 424 per 1M tokens; output is LKR 1,333 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 2,606. Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.
Yes. GLM-5.3 usage is billed in LKR on one monthly invoice with every other model you use, so there is no foreign card or separate Zhipu AI account to set up.
Its weights are open under the GLM-5.3 License licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.
GLM-5.3 can read up to 1M tokens in one request, and write an answer of up to 128K tokens.
It reads text only. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge. Scanned pages need a model that can see images.
Create a free account, get an API key and call GLM-5.3 with the OpenAI SDK, billed in Sri Lankan rupees.