GPT 2.6, Veo 3.1, Seedance 2.5, Kling 4 in deAPI!
Web-search and web-contents are now available via API
Browse all Models
Browse all
Browse all
Browse all

LLM · Vision

GLM-5.3 Flash API, free to try

GLM-5.3 Flash is an open-weight large language model from Z.ai. It reads text and images and holds up to 1M tokens of context. deAPI serves it on an OpenAI-compatible endpoint, so the OpenAI SDK works once you change the base URL, the key and the model ID.

  • Text and images in, a 1,048,576-token context window
  • JSON schema output, tool calls and streaming
  • reasoning_effort takes seven values, none to max; reasoning stays on at none

No credit card · Free credits valid for 30 days · Then top up and pay as you go, no subscription

GLM-5.3 Flash LLM · Vision

model: "glm-5.3-flash"
reasoning_effort: "low"

system: You write release notes. Summarise the changelog in two plain sentences. No lists.

user

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)
assistant

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.

123 input + 71 output tokens (1 reasoning) · 3.2 s Cost on deAPI: $0.00006 (price as of November 2026)

GLM-5.3 Flash use cases

Four jobs where the model fits, each with the number behind it. All of them run on the same deAPI key as transcription, OCR and image generation.

  1. Summaries of changelogs, tickets and meeting notes. The changelog above went in as 123 tokens and came back as a two-sentence summary of 71 tokens. Three runs at reasoning_effort: low each named all five changes. One such call costs $0.00006.

  2. Invoices, receipts and forms. Send a photo or scan as image_url with a JSON schema. On the generated German invoice below it returned all 10 values in two runs, with dates in ISO format and amounts as numbers. The IBAN came back without spaces.

  3. Coding agents. Z.ai reports 63.4 on DeepSWE v1.1 for GLM-5.3 Flash, against 46.2 for GLM-5.2 (mini-swe-agent harness, per the model card). Coding tools that speak the OpenAI Chat Completions API can point at https://oai.deapi.ai/v1.

  4. Agents that call deAPI. Describe deAPI endpoints as tools. Asked for chapters with timestamps for a YouTube video, the model called transcribe_video with include_ts: true (one run). Your code runs that call with WhisperLargeV3Ct2 and sends the transcript back.

German invoice from Nordlicht Studio GmbH with three line items and a total of 2,677.50 EUR
Response: message.content
{
  "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"
}
Invoice example: image in, JSON out Prompt: “Extract the fields from this invoice.” System message: “Extract invoice fields. Dates as YYYY-MM-DD, amounts as numbers.” JSON schema with 10 fields, temperature 0. 1,440 input + 278 output tokens (152 reasoning), 5.9 s on the first call.

GLM-5.3 Flash API pricing

You pay per token from the same prepaid balance as every other deAPI model. Reasoning tokens are part of completion_tokens in usage. No subscription.

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

What the free account includes

  • $5 of credits once you add a payment card
  • About 12,000 calls like the invoice example
  • Credits valid for 30 days, then top up and pay as you go
Get $5 credits

Prices for glm-5.3-flash in USD, November 2026. Token counts from the hero summary and the invoice example. Context and output limits from GET https://oai.deapi.ai/v1/models.

GLM-5.3 Flash vs GLM-5.3 vs 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

Limits and input types from GET /v1/models. Accepted reasoning_effort values tested on 16 November 2026.

GLM-5.3 Flash API example

One POST to https://oai.deapi.ai/v1/chat/completions with your deAPI key as the Bearer token. In the OpenAI SDK, set base_url, your deAPI key and the model ID; the rest of a Chat Completions call stays the same. Replace YOUR_API_KEY with a key from your dashboard.

Model ID
glm-5.3-flash
Endpoint
POST https://oai.deapi.ai/v1/chat/completions
Input
Text and images as image_url parts: a base64 data URL or a public HTTPS link. PDFs and audio are rejected.
Context and output
1,048,576-token context window (prompt and answer together), up to 131,072 tokens per answer
Reasoning
reasoning_effort: none, minimal, low, medium, high, xhigh or max. Reasoning text, when the model returns it, is in reasoning_content.
Output options
response_format with json_schema (strict) or json_object, tools, stream
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?

GLM-5.3 Flash is an open-weight model that Z.ai publishes on Hugging Face under the MIT license. It has 320B parameters in total and uses 18B of them per token. Z.ai calls it the first natively multimodal model in the GLM-5 series: it reads text and images and writes text. On deAPI you call it like any OpenAI chat model and pay per token.

  1. Create a free account

    Sign up and get $5 of credits.

  2. Point your client at deAPI

    Set base_url to https://oai.deapi.ai/v1 and use your deAPI key.

  3. Send the request

    Use glm-5.3-flash as the model and read the answer from choices[0].message.content.

GLM-5.3 Flash FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID glm-5.3-flash, with the request and response format of the OpenAI Chat Completions API. In code that uses the OpenAI SDK you change three values: base_url, the API key and the model. Run your own tests before you switch traffic.
A new deAPI account gets $5 of credits once you add a payment card, enough for about 12,000 calls like the invoice example on this page. The credits are valid for 30 days. After that you top up and pay as you go, with no subscription.
$0.165 per million input tokens and $0.55 per million output tokens (November 2026). Reasoning tokens count as output, and you see them in usage.completion_tokens_details.reasoning_tokens.
Yes. Add an image_url part to the user message, as a base64 data URL or a public HTTPS link. PDFs and audio files are rejected: run PDFs through the OCR API or send pages as images, and transcribe audio first.
On deAPI the context window is 1,048,576 tokens, prompt and answer together, and one answer can be up to 131,072 tokens long. A larger max_tokens is rejected with an error.
On deAPI, glm-5.3-flash reads text and images and accepts seven reasoning_effort values and a strict json_schema. glm-5.3 reads text only and accepts low, high and max. Per million tokens, Flash costs $0.165 in and $0.55 out; GLM-5.3 costs $1.54 in and $4.84 out. Z.ai lists Flash at 320B parameters with 18B active per token.
Not fully. deAPI accepts all seven reasoning_effort values, but Z.ai’s docs say thinking cannot be disabled for this model. On the ticket request from the cURL example, none answered “billing” with 7 output tokens, 5 of them reasoning. low used 5 output tokens (3 reasoning) and max used 59 (57 reasoning). One run each.
Z.ai publishes the weights on Hugging Face under the MIT license, which allows commercial use. Calls through deAPI are also covered by the deAPI Terms of Service.

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.