GLM 5.3 API pricing
As of 2026-10-31, GLM 5.3 API costs $2.21 per 1M input and $6.95 per 1M output tokens on one-api.ai (source: Cloudflare Workers AI pricing list price, checked 2026-10-22, plus our posted margin).
Early access: billing is not open yet. Prices below are what a call will debit when it opens. Request access →
GLM 5.3 from Zhipu (Z.ai) is a strong bilingual Chinese and English model, useful for Chinese-language products and agents that need tool-style output. Model id: @cf/zai-org/glm-5.3.
Price comparison
Cloudflare's list price is what the provider charges through Cloudflare; one-api.ai is what a call debits here. one-api.ai runs GLM 5.3 on Cloudflare Workers AI, so the maker's own API price does not apply and is not shown.
Per 1M tokens
| Price | Input | Cached input | Output |
|---|---|---|---|
| Cloudflare list | $1.400 | $0.260 | $4.400 |
| hiapi | $4.40 | not posted | $15.40 |
| one-api.ai | $2.21 | $0.41 | $6.95 |
Sources: Cloudflare Workers AI pricing (page updated 2026-10-20), checked 2026-10-22; hiapi's public price page, collected 2026-10-21.
What a month costs
Three example workloads. "Monthly cost" multiplies the tokens by the one-api.ai price per 1M, and that is what billing debits: usage is metered to a millionth of a credit, with no rounding up per call. A credit is a tenth of a cent.
| Workload | Requests | Tokens in / out per request | Monthly cost | Per request |
|---|---|---|---|---|
| Support chatbot | 10,000 | 1,500 / 300 | $54.00 | 5.4 credits |
| RAG answers | 5,000 | 6,000 / 400 | $80.20 | 16.04 credits |
| Batch summaries | 1,000 | 20,000 / 1,000 | $51.15 | 51.15 credits |
Prompts that reuse a long prefix can cost less where the model has a cached-input rate, shown in the price comparison above.
Context and cache tiers
The context window is not stated on the source page, so it is not given here. There is one price tier for every prompt length. Cached input is billed at the cached rate only when the provider reports a cache hit; the cost examples above assume no cache hits. one-api.ai sets max_tokens to 4,096 when a request leaves it out and clamps it to 16,384.
Request examples
Python
import os
from openai import OpenAI
client = OpenAI(base_url="https://one-api.ai/v1/launch", api_key=os.environ["ONE_API_TOKEN"])
resp = client.chat.completions.create(
model="@cf/zai-org/glm-5.3",
messages=[{"role": "user", "content": "Summarise RDAP in one sentence."}],
max_tokens=512,
)
print(resp.choices[0].message.content)
print(resp.usage)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://one-api.ai/v1/launch", apiKey: process.env.ONE_API_TOKEN });
const resp = await client.chat.completions.create({
model: "@cf/zai-org/glm-5.3",
messages: [{ role: "user", content: "Summarise RDAP in one sentence." }],
max_tokens: 512,
});
console.log(resp.choices[0].message.content, resp.usage);curl
curl https://one-api.ai/v1/launch/chat/completions \
-H "Authorization: Bearer $ONE_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"@cf/zai-org/glm-5.3","messages":[{"role":"user","content":"Say hello in one sentence."}],"max_tokens":512}'Notes on GLM 5.3
The id is @cf/zai-org/glm-5.3 on Cloudflare Workers AI, with the same 50 requests per minute ceiling as the other Workers AI models.
GLM carries the largest margin on one-api.ai, about 50% over cost, rounded to the cent per 1M tokens. Even so, the price sits below what hiapi posts for GLM 5.3, as the comparison table shows.
Cached input is relatively expensive on this model: about a fifth of the plain input rate, against roughly a fiftieth on DeepSeek. Prompt caching saves less here, so trimming repeated context matters more.
Neither source we cite states the context window, so this page leaves it out rather than guess.
FAQ
Is this Zhipu's own GLM API?
No. It is the Cloudflare Workers AI deployment of GLM 5.3. We do not call Zhipu's or Z.ai's API directly.
Why does GLM cost more here than DeepSeek?
Cloudflare's list price for GLM 5.3 is higher, and our margin on it is larger. Both are shown in the comparison table with their sources.
Does GLM 5.3 handle Chinese prompts?
Yes, it is trained for Chinese and English. Token counts for Chinese text differ from English, so measure a few real requests before estimating a monthly bill.
Related
Last updated 2026-10-31.