Structured output
You send
Turn this customer email into JSON with intent, urgency and order_id.
customer-email.txtGLM 5
by Z.AIReleased 11 February 2026
GLM-5 reads and writes text, keeps about 200 pages in mind at once, and is the flagship of Z.ai's line, a model you can download and run yourself. It is made for building whole software systems, not single snippets: it plans the work, reasons about the back end, corrects its own mistakes and carries tasks through on its own. Z.ai says it rivals the best closed models on large programming jobs.
TakesText
GivesText
What it costs
You pay for what each request uses. No subscription, no minimum.
≈ 0,87 DA per message3 000 DA buys about 3 400 messages
One message, the ordinary use
1 000 tokens sent× 332,84 DA per 1M0,33 DA
500 tokens back× 1 065,07 DA per 1M0,53 DA
Total≈ 0,87 DA
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 332,84 DA | 1 065,07 DA |
| Cached tokens read | 66,57 DA |
per 1M tokens
Answer a quick question≈ 0,32 DA
Explain an error message and the fix≈ 0,69 DA
Write a function and its tests≈ 1,09 DA
Review a pull request of about 400 lines≈ 3,28 DA
Summarise a large file of code≈ 4,63 DA
- When you pay
- After the answer, from your balance. Nothing is held.
- Why it varies
- A longer question or a longer answer costs more.
- After each one
- The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.
Where your request runs
Eight companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
StreamLake40 % off…
↑ Sent, per 1M
↓ Back, per 1M
Cache read
Latency
…
Throughput
…
GMICloud40 % offUnited States…
↑ Sent, per 1M
↓ Back, per 1M
Cache read
Latency
…
Throughput
…
Baidu…
↑ Sent, per 1M
232,98 DA
↓ Back, per 1M
745,55 DA
Cache read
46,60 DA
Latency
…
Throughput
…
SiliconFlowUnited States…
↑ Sent, per 1M
316,19 DA
↓ Back, per 1M
848,73 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Amazon Bedrock…
↑ Sent, per 1M
332,84 DA
↓ Back, per 1M
1 065,07 DA
Cache read
none
Latency
…
Throughput
…
VeniceUnited States…
↑ Sent, per 1M
332,84 DA
↓ Back, per 1M
1 065,07 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Novita…
↑ Sent, per 1M
332,84 DA
↓ Back, per 1M
1 065,07 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Z.AIAsia…
↑ Sent, per 1M
332,84 DA
↓ Back, per 1M
1 065,07 DA
Cache read
66,57 DA
Latency
…
Throughput
…
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| StreamLake40 % off | … | … | … | |||
| GMICloud40 % offUnited States | … | … | … | |||
| Baidu | 232,98 DA | 745,55 DA | 46,60 DA | … | … | … |
| SiliconFlowUnited States | 316,19 DA | 848,73 DA | 66,57 DA | … | … | … |
| Amazon Bedrock | 332,84 DA | 1 065,07 DA | none | … | … | … |
| VeniceUnited States | 332,84 DA | 1 065,07 DA | 66,57 DA | … | … | … |
| Novita | 332,84 DA | 1 065,07 DA | 66,57 DA | … | … | … |
| Z.AIAsia | 332,84 DA | 1 065,07 DA | 66,57 DA | … | … | … |
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
See it in action
Real requests, real replies. Try any of them yourself — one click, pre-filled.
Writing
You send
Two lines to welcome a shop in Oran.
It replied
Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.
Try in Chat LabTry your own request — same model, pre-selected.
Open Chat LabCall it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="z-ai/glm-5",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)pip install openaiFull reference for this route
Runs this request once on your balance.
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceQuestions about GLM 5
How much does GLM 5 cost in dinars?
About 0,87 DA per message. ↑ 332,84 DA · ↓ 1 065,07 DA per 1M tokens.
Is GLM 5 free? Can I try it?
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
What is GLM 5 best for?
GLM-5 reads and writes text, keeps about 200 pages in mind at once, and is the flagship of Z.ai's line, a model you can download and run yourself. It is made for building whole software systems, not single snippets: it plans the work, reasons about the back end, corrects its own mistakes and carries tasks through on its own. Z.ai says it rivals the best closed models on large programming jobs.
GLM 5 or GLM 5 Turbo?
GLM 5 Turbo costs 0,20 DA more for the same message.
How do I pay for GLM 5 without an international card?
Deposit dinars with your Edahabia or CIB card. Every model, GLM 5 included, is paid from that balance. No foreign card, no conversion.
Does GLM 5 work in Arabic, French or Darja?
Z.ai lists English and Chinese. Arabic, French and Darja are not named.
Can it read PDFs, images or a whole book?
It reads text. Up to 205K tokens in one request, about 200 pages. It writes up to 98 000 words at once.
Is GLM 5 open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes GLM 5, and when was it released?
Z.AI. Released 11 February 2026.
Other Z.AI models, priced in dinars
See all Z.AI modelsGLM 5.3 FlashZ.AI · Aug 26, 2026
#8 for agent work · GLM-5.3 Flash takes text, images and video, writes back text, and keeps about 1,000 pages in mind at once. Z.ai built it for light, quick coding and long tasks it carries out by itself, and says it stays accurate over very long material while using less computing. Pick it when the job includes screenshots or clips and you want to keep running costs down.
#20 of 119 for codingThinks firstUses your tools
≈0,13 DAper message
View modelGLM 5.3Z.AI · Aug 18, 2026
#2 for slide decks · GLM-5.3 reads and writes text, keeps about 1,000 pages in mind at once, and always thinks before it answers, though you choose low, high or maximum effort, with maximum the default. Z.ai says it beats the earlier GLM-5.2 at coding and gets good results without wasting effort. Pick it for demanding programming and long jobs it carries out by itself. GLM-5.3 Prime is a faster version of it, and GLM-5.3 Flash suits work with pictures and video.
#13 of 119 for codingThinks firstUses your tools
≈0,26 DAper message
View modelGLM 5.2Z.AI · Jun 16, 2026
#10 for games · GLM 5.2 thinks before it answers. It reads and writes text, keeps about 1,000 pages in mind at once, and can write an answer several hundred pages long. Z.ai made it for software projects from start to finish: it keeps track of the requirements, follows the same standards throughout, and carries a job from the first brief to release on several platforms, and you can ask it to think hard or at maximum.
#28 of 119 for codingThinks firstUses your tools
≈1,13 DAper message
View modelGLM 5.3 FlashXZ.AI · Sep 18, 2026
The high-speed FlashX edition of GLM-5.3-Flash, reaching up to 200 tokens a second on the same 320B hybrid-attention model with 18B active, for efficient coding, visual understanding and long agent tasks
Thinks firstUses your tools1 000 pages at once
≈0,33 DAper message
View model