Z.AI models
All 19 Z.AI models on OpenDunes, priced in Algerian Dinars.
19 models
#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.
#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.
#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.
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
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-5.3 Prime offers all of GLM-5.3's abilities with answers that Z.ai says arrive one and a half to two times quicker. It reads and writes text, keeps about 1,000 pages in mind at once, and writes up to about 130 pages per answer. Pick it for coding and for assistants that carry out many steps or talk with users live, where waiting hurts.
Z.ai: GLM 4.7
Going away Dec 31, 2026GLM-4.7 reads and writes text, keeps about 200 pages in mind at once, and can write answers up to about 130 pages long. Z.ai upgraded it for programming and for carrying out multi-step jobs without losing the thread, and it holds more natural conversations and builds better-looking web pages. Pick it for coding and for assistants that carry out tasks. GLM-4.7 Flash is the lighter version for coding assistants, and GLM-5 takes on bigger long-running engineering work.
#2 for slide decks · GLM-5.1 reads and writes text and keeps about 200 pages in mind at once. Z.ai built it for programming jobs that run long: where earlier models handled minute-long exchanges, it can work on a single task by itself for over 8 hours, planning, carrying out and improving its own work until it delivers a finished result. Pick it for big coding projects you hand off and leave. GLM-5 Turbo is faster for quick back-and-forth, and GLM-5.2 takes far longer inputs.
This model reads text, pictures and video, keeps about 1,000 pages in mind at once, and writes answers of up to 130 pages. It was tuned on legal material, so it suits work a lawyer sits down to do: reading long contracts and case files, spotting risky clauses, and drafting letters or agreements. It thinks before answering, can fill a fixed answer form, and costs less on repeated reads thanks to cheaper re-reading of the same material. It cannot search the web, so a question needing fresh sources or current law needs a model that can.
#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.
GLM-4.7 Flash is a compact model that reads and writes text and keeps about 200 pages in mind at once. It balances quality against running cost and is tuned for coding assistants: planning long tasks, writing code and working with the tools you connect. Z.ai reports it leads other open models of its size on public tests.
GLM-4.6 reads and writes text and keeps about 200 pages in mind at once, up from about 130 in GLM-4.5. Z.ai improved it for programming, including better-looking web pages, for thinking that can use your tools mid-answer, for assistants that search and carry out tasks, and for writing that reads more naturally and plays characters better. GLM-4.6V handles pictures, and GLM-4.7 adds further coding gains.
The lightweight version of Z.ai's GLM-4.5 family, GLM-4.5 Air reads and writes text with about 130 pages in mind at once. Like its bigger sibling, it switches between thinking before it answers, for harder reasoning and jobs that use your tools, and replying straight away for live conversation.
GLM-5 Turbo reads and writes text, keeps about 200 pages in mind at once, and is built to answer fast. Z.ai tuned it for assistants that carry out long chains of steps: breaking a big instruction into parts, using your tools, running on a schedule or continuously, and staying steady across a long task. Pick it for an automated assistant that must run quickly and reliably. GLM-5 is the flagship for large programming jobs, and GLM-5.1 for single tasks that run for hours.
GLM-4.6V takes text, images and video and writes back text, keeping about 130 pages in mind at once. It reads pages with complex layouts and charts straight from the picture, and it can pass what it sees to the tools you connect. It can also rebuild a web page from a screenshot and refine it through repeated edits, so pick it for documents full of charts. GLM-4.5V is the older, shorter-memory version, and GLM-5V Turbo is made for coding guided by what it sees.
Z.ai: GLM 4.5
Going away Dec 31, 2026GLM-4.5 reads and writes text, keeping about 130 pages in mind at once. It has two modes: thinking before it answers, for hard questions and jobs that use your tools, or replying at once for quick answers. Z.ai built it for assistants that carry out tasks, with gains in reasoning and programming.
#5 for mobile apps · GLM-5V Turbo takes text, images and video and writes back text, keeping about 200 pages in mind at once. Z.ai calls it its first model built from the start to see and act: it looks at what it is given, plans the steps and carries them out, and it is made for coding guided by pictures and video.
Z.ai: GLM 4.5V
Going away Dec 31, 2026GLM-4.5V takes text and pictures and writes back text, keeping about 65 pages in mind at once. Z.ai built it for assistants that look at images: answering questions about a picture, reading the text in it, working through documents, finding where things are, and writing web page code. It can think before answering or reply at once.
#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.