LLM · Vision
GLM-5.3 Flash API, free to try
No credit card · Free credits valid for 30 days · Then top up and pay as you go, no subscription
model: "glm-5.3-flash"
reasoning_effort: "low"
system: You write release notes. Summarise the changelog in two plain sentences. No lists.
Summarise this for the customer newsletter.
v2.4.0 (2026-11-12)
- Added: CSV export on the Invoices page
- Added: SSO login with Google Workspace
- Fixed: duplicate e-mail reminders after a timezone change
- Changed: API rate limit raised from 60 to 120 requests per minute
- Removed: legacy /v1/reports endpoint (use /v2/reports)
In v2.4.0 you can now export invoices as CSV, sign in with Google Workspace via SSO, and enjoy a doubled API rate limit of 120 requests per minute. We’ve also fixed duplicate email reminders after timezone changes and removed the legacy /v1/reports endpoint, so please switch to /v2/reports.
GLM-5.3 Flash use cases
{
"invoice_number": "NS-2026-0418",
"issue_date": "2026-11-03",
"due_date": "2026-11-17",
"seller": "Nordlicht Studio GmbH",
"seller_vat_id": "DE298765431",
"net": 2250.00,
"vat": 427.50,
"total": 2677.50,
"currency": "EUR",
"iban": "DE44100100100123456789"
}
GLM-5.3 Flash API pricing
| Tokens | Price per 1M | For $5 |
|---|---|---|
| Input (text and images) | $0.165 | ≈ 30M tokens |
| Cached input (repeated prompt prefix) | $0.033 | ≈ 151M tokens |
| Output (answer and reasoning) | $0.55 | ≈ 9.0M tokens |
| Summary in the hero, one call | $0.00006 | ≈ 84,000 calls |
| Invoice example, one call | $0.00039 | ≈ 12,000 calls |
GLM-5.3 Flash vs GLM-5.3 vs Qwen3.8 Flash
| GLM-5.3 Flash | GLM-5.3 | Qwen3.8 Flash | |
|---|---|---|---|
| Input | Text, image | Text | Text, image |
| Context | 1,048,576 tokens | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 131,072 tokens | 131,072 tokens | 131,072 tokens |
reasoning_effort |
none to max, 7 values; reasons even at none | low, high, max | none to max, 7 levels |
| Price per 1M, input / output | $0.165 / $0.55 | $1.54 / $4.84 | $0.165 / $0.517 |
GLM-5.3 Flash API example
- Model ID
- Endpoint
- Input
- Context and output
- Reasoning
- Output options
curl https://oai.deapi.ai/v1/chat/completions \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "glm-5.3-flash",
"reasoning_effort": "low",
"messages": [
{"role": "system", "content": "Sort support tickets. Reply with one word: billing, bug, feature or other."},
{"role": "user", "content": "I was charged twice for the November top-up."}
]
}'
import base64, json
from openai import OpenAI
client = OpenAI(base_url="https://oai.deapi.ai/v1", api_key="YOUR_API_KEY")
with open("invoice.png", "rb") as f:
image = "data:image/png;base64," + base64.b64encode(f.read()).decode()
schema = {
"type": "object",
"additionalProperties": False,
"required": ["invoice_number", "issue_date", "due_date", "seller",
"seller_vat_id", "net", "vat", "total", "currency", "iban"],
"properties": {
"invoice_number": {"type": "string"},
"issue_date": {"type": "string"},
"due_date": {"type": "string"},
"seller": {"type": "string"},
"seller_vat_id": {"type": "string"},
"net": {"type": "number"},
"vat": {"type": "number"},
"total": {"type": "number"},
"currency": {"type": "string"},
"iban": {"type": "string"},
},
}
response = client.chat.completions.create(
model="glm-5.3-flash",
temperature=0,
messages=[
{"role": "system", "content": "Extract invoice fields. "
"Dates as YYYY-MM-DD, amounts as numbers."},
{"role": "user", "content": [
{"type": "text", "text": "Extract the fields from this invoice."},
{"type": "image_url", "image_url": {"url": image}},
]},
],
response_format={"type": "json_schema",
"json_schema": {"name": "invoice", "strict": True, "schema": schema}},
)
invoice = json.loads(response.choices[0].message.content)
print(invoice["total"], invoice["currency"]) # 2677.5 EUR
print(response.usage)
What is GLM-5.3 Flash?
-
Create a free account
-
Point your client at deAPI
-
Send the request
GLM-5.3 Flash FAQ
Send your first GLM-5.3 Flash request with $5 of free credits
Sign up with e-mail or Google. No subscription, pay as you go.