AIHubMixAIHubMix

Z.AI Models

64 modelsGeneral models free to startUp to 1M context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

228B

Requests

3M

Models in use

54 of 64

Tokens per day

07.9B15.8B07-1307-2007-2708-0308-102026-07-13 — 9,918,157,040 tokens2026-07-14 — 11,589,875,615 tokens2026-07-15 — 8,620,894,025 tokens2026-07-16 — 9,896,634,120 tokens2026-07-17 — 10,025,532,080 tokens2026-07-18 — 5,460,109,235 tokens2026-07-19 — 6,344,453,775 tokens2026-07-20 — 6,099,300,355 tokens2026-07-21 — 5,028,851,350 tokens2026-07-22 — 11,124,628,340 tokens2026-07-23 — 15,843,694,810 tokens2026-07-24 — 8,883,641,515 tokens2026-07-25 — 3,615,730,225 tokens2026-07-26 — 2,993,448,495 tokens2026-07-27 — 3,184,329,180 tokens2026-07-28 — 4,743,023,160 tokens2026-07-29 — 6,356,994,015 tokens2026-07-30 — 12,792,717,625 tokens2026-07-31 — 5,725,622,850 tokens2026-08-01 — 3,673,283,425 tokens2026-08-02 — 2,507,995,155 tokens2026-08-03 — 4,463,338,270 tokens2026-08-04 — 10,181,814,485 tokens2026-08-05 — 8,392,866,115 tokens2026-08-06 — 10,657,976,760 tokens2026-08-07 — 13,338,325,155 tokens2026-08-08 — 7,003,480,570 tokens2026-08-09 — 5,851,429,285 tokens2026-08-10 — 4,734,214,155 tokens2026-08-11 — 9,145,389,365 tokens

Which models that traffic went to

  1. glm-5.244.0%100B
  2. coding-glm-523.1%52.7B
  3. coding-glm-5.29.8%22.4B
  4. coding-glm-4.67.8%17.9B
  5. coding-glm-5.14.2%9.6B
  6. glm-5.14.2%9.5B
  7. coding-glm-4.72.8%6.3B
  8. coding-glm-5.2-free1.8%4.2B
  9. 36 more models2.3%5.3B

Share of 228B tokens. 10 models with traffic report no token counts and cannot be ranked here, including coding-glm-5-turbo-free and glm-4-flash — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 64 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 64 Z.AI Models

Open in model list
Z.AI models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
coding-glm-5.2-freeTakes text, returns text.1M—FreeFree/M———
glm-5.2Takes text, returns text.1M128K$1.13$3.94/M$0.28/M46 tok/s0.95 s
glm-5.2-fast-previewTakes text, returns text.1M128K$2.25$7.89/M$0.56/M38 tok/s2.00 s
glm-4.6Takes text, returns text.205K131KFreeFree/MFree/M43 tok/s3.27 s
glm-5Takes text, returns text.203K—FreeFree/MFree/M33 tok/s0.99 s
glm-5-turboTakes text, returns text.203K—$1.20$4.00/M$0.24/M16 tok/s1.26 s
coding-glm-4.6-freeTakes text, returns text.200K128KFreeFree/M———
glm-4.7Takes text, returns text.200K128K$0.27$1.10/M$0.05/M113 tok/s0.41 s
glm-5v-turboTakes text, vision, video, returns text.200K128K$0.70$3.10/M$0.17/M45 tok/s4.92 s
glm-5.1Takes text, returns text.200K128K$0.84$3.38/M$0.18/M19 tok/s1.61 s
coding-glm-4.5-airTakes text. Output modality not published.131K—$0.01$0.08/M———
glm-4.5-airTakes text. Output modality not published.131K98K$0.14$0.84/M—91 tok/s1.42 s
glm-4.5Takes text. Output modality not published.131K98K$0.40$1.60/M—107 tok/s0.46 s
glm-4.6vTakes text, vision, video, returns text.128K—$0.14$0.41/M$0.03/M5 tok/s4.39 s
glm-4.5vTakes text, vision, video, returns text.64K16K$0.27$0.82/M—51 tok/s8.22 s
glm-ocrTakes vision, returns text.32K—$0.03$0.03/M———
embedding-2Takes text. Output modality not published.8K—$0.07$0.07/M———
embedding-3Takes text. Output modality not published.8K—$0.07$0.07/M———
coding-glm-4.7-freeTakes text, returns text.——FreeFree/M———
coding-glm-5-freeTakes text, returns text.——FreeFree/M———
coding-glm-5-turbo-freeTakes text, returns text.——FreeFree/M———
coding-glm-5.1-freeTakes text, returns text.——FreeFree/M———
glm-4.7-flash-freeTakes text, returns text.——FreeFree/M———
glm-imageTakes text, returns vision.——FreeFree/M———
Pro/THUDM/GLM-4.1V-9B-Thinking——$0.04$0.16/M———
THUDM/GLM-4-9B-0414——$0.05$0.05/M———
THUDM/GLM-Z1-9B-0414——$0.05$0.05/M———
cc-glm-4.6——$0.06$0.22/M———
cc-glm-4.7——$0.06$0.22/M———
cc-glm-5Takes text, returns text.——$0.06$0.22/M———
cc-glm-5-turboTakes text, returns text.——$0.06$0.22/M———
cc-glm-5.1Takes text, returns text.——$0.06$0.22/M———
coding-glm-4.6Takes text, returns text.——$0.06$0.22/M$0.01/M——
coding-glm-4.7Takes text, returns text.——$0.06$0.22/M$0.01/M——
coding-glm-5Takes text, returns text.——$0.06$0.22/M———
coding-glm-5-turboTakes text, returns text.——$0.06$0.22/M———
coding-glm-5.1Takes text, returns text.——$0.06$0.22/M———
coding-glm-5.2Takes text, returns text.——$0.06$0.22/M———
THUDM/GLM-4-32B-0414——$0.08$0.08/M———
THUDM/GLM-Z1-32B-0414——$0.08$0.08/M———
glm-4-flash——$0.10$0.10/M———
THUDM/GLM-4.1V-9B-Thinking——$0.10$0.10/M———
doubao-1-5-pro-32k-250115——$0.11$0.27/M———
chatglm_lite——$0.29$0.29/M———
alicloud-glm-4.7——$0.41$1.92/M$0.41/M——
alicloud-glm-5——$0.56$2.54/M$0.11/M——
doubao-1-5-pro-256k-250115——$0.68$1.23/M———
glm-3-turbo——$0.71$0.71/M———
chatglm_std——$0.71$0.71/M———
chatglm_turbo——$0.71$0.71/M———
glm-4.5-airxTakes text. Output modality not published.——$1.10$4.51/M$0.22/M——
zai-glm-5-turboTakes , returns text.——$1.20$4.00/M$0.24/M——
cloudflare-glm-5.2Takes , returns text.——$1.40$4.40/M$0.26/M——
chatglm_pro——$1.43$1.43/M———
glm-4v-plus——$2.00$2.00/M———
glm-zero-preview——$2.00$2.00/M———
glm-4.5-xTakes text. Output modality not published.——$2.20$8.91/M$0.44/M1 tok/s0.59 s
cbs-glm-4.7——$2.25$2.75/M———
glm-4-plus——$8.00$8.00/M———
cogview-3-plus——$10.00$10.00/M———
glm-4——$14.20$14.20/M———
glm-4v——$14.20$14.20/M———
code-davinci-edit-001——$20.00$20.00/M———
cogview-3——$35.50$35.50/M———

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

cc-glm-5 vs cc-glm-5-turbocc-glm-5 vs cc-glm-5.1cc-glm-5 vs cloudflare-glm-5.2cc-glm-5 vs qwen3.8-max-previewcc-glm-5 vs kimi-k3

Z.AI on AIHubMix

Which Z.AI model should I start with?

coding-glm-4.6-free is free on input — the cheapest entry here that declares tool calling, and it carries a 200K context. Move up to cogview-3 when answer quality matters more than cost, or to coding-glm-5.2-free for long-form reasoning.

Which of these models reason before answering?

23 of the 64 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (THUDM/…), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example coding-glm-4.6 bills cache hits at 18.33% of the input rate and coding-glm-4.7 bills cache hits at 18.33% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate Z.AI account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsLlama
52 modelsByteDance
46 models

Start calling Z.AI in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect