Z.ai API pricing
Updated
Z.ai lists standard prices for 21 models, 3 of them free. The cheapest is GLM-4-32B-0414-128K at USD 0.10 input and USD 0.10 output per 1M tokens; the dearest is GLM-4.5-X at USD 2.20 / USD 8.90. It publishes cached-input prices for 17 of them, and lists no per-model batch, flex or priority prices on the pages we read.
- Models with a standard price
- 21
- Median input / output
- USD 0.60 / USD 2
- Cached-input prices
- 17 of 18
- Cheapest host for
- 4 of 12 shared models
Which models is Z.ai the cheapest provider for?
Of the 12 models that Z.ai and at least one other provider both price at the standard tier, Z.ai has the lowest price for 4, ranked on a blend of 3 input tokens to 1 output token (all of them tied with another provider at the same price; the maker's own API is listed first on a tie). It is the dearest for 3. Another 6 models have a standard price from Z.ai only.
| Model | Z.ai input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| GLM 4.5V | USD 0.60 / USD 1.80 | Novita AI USD 0.60 / USD 1.80 | tie | 2 |
| GLM 4.6V | USD 0.30 / USD 0.90 | Novita AI USD 0.30 / USD 0.90 | tie | 2 |
| GLM 5.3 FlashX | USD 0.37 / USD 1.25 | Novita AI USD 0.37 / USD 1.25 | tie | 2 |
| GLM-4.5-FP8 | USD 0.60 / USD 2.20 | GMI Cloud USD 0.60 / USD 2.20 | tie | 2 |
How does Z.ai price the most widely hosted models?
The 6 models Z.ai sells that the most other providers also sell, with Z.ai's rank among them on the 3:1 blend.
| Model | Z.ai | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 1.40 / USD 4.40 | 6 of 24 | DeepInfra USD 0.5625 / USD 2.50 |
| GLM 5.3 Flash | USD 0.15 / USD 0.50 | 3 of 20 | GMI Cloud USD 0.075 / USD 0.25 |
| GLM 5.2 | USD 1.40 / USD 4.40 | 5 of 19 | DeepInfra USD 0.5625 / USD 1.80 |
| GLM 5.1 | USD 1.40 / USD 4.40 | 5 of 12 | Chutes USD 0.90 / USD 2.90 |
| GLM 5 | USD 1 / USD 3.20 | 4 of 10 | GMI Cloud USD 0.60 / USD 1.92 |
| GLM 4.7 | USD 0.60 / USD 2.20 | 3 of 8 | DeepInfra USD 0.40 / USD 1.75 |
Z.ai price list
USD per 1M tokens: 21 prices for 21 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Z.ai is cheaper. Z.ai is the maker of every model here, so there is no maker price to compare with.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| GLM 4.5 Air | standard | USD 0.20 | USD 0.03 | USD 1.10 | not stated | own model | source |
| GLM 4.5V | standard | USD 0.60 | USD 0.11 | USD 1.80 | not stated | own model | source |
| GLM 4.6 | standard | USD 0.60 | USD 0.11 | USD 2.20 | not stated | own model | source |
| GLM 4.6V | standard | USD 0.30 | USD 0.05 | USD 0.90 | not stated | own model | source |
| GLM 4.7 | standard | USD 0.60 | USD 0.11 | USD 2.20 | not stated | own model | source |
| GLM 4.7 Flashfree | standard | USD 0 | USD 0 | USD 0 | not stated | own model | source |
| GLM 5 | standard | USD 1 | USD 0.20 | USD 3.20 | not stated | own model | source |
| GLM 5.1 | standard | USD 1.40 | USD 0.26 | USD 4.40 | not stated | own model | source |
| GLM 5.2 | standard | USD 1.40 | USD 0.26 | USD 4.40 | not stated | own model | source |
| GLM 5.3 | standard | USD 1.40 | USD 0.26 | USD 4.40 | not stated | own model | source |
| GLM 5.3 Flash | standard | USD 0.15 | USD 0.03 | USD 0.50 | not stated | own model | source |
| GLM 5.3 FlashX | standard | USD 0.37 | USD 0.075 | USD 1.25 | not stated | own model | source |
| GLM-4-32B-0414-128K | standard | USD 0.10 | — | USD 0.10 | not stated | own model | source |
| GLM-4.5-AirX | standard | USD 1.10 | USD 0.22 | USD 4.50 | not stated | own model | source |
| GLM-4.5-Flashfree | standard | USD 0 | USD 0 | USD 0 | not stated | own model | source |
| GLM-4.5-FP8 | standard | USD 0.60 | USD 0.11 | USD 2.20 | not stated | own model | source |
| GLM-4.5-X | standard | USD 2.20 | USD 0.45 | USD 8.90 | not stated | own model | source |
| GLM-4.6V-Flashfree | standard | USD 0 | USD 0 | USD 0 | not stated | own model | source |
| GLM-4.6V-FlashX | standard | USD 0.04 | USD 0.004 | USD 0.40 | not stated | own model | source |
| GLM-4.7-FlashX | standard | USD 0.07 | USD 0.01 | USD 0.40 | not stated | own model | source |
| GLM-5.3-FlashX-Legal | standard | USD 0.37 | USD 0.075 | USD 1.25 | not stated | own model | source |
- Cached "—" means Z.ai's page shows no cache price for that row; budget cached tokens at the input price.
- Context "not stated": Z.ai's pricing page does not give context windows.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does Z.ai publish?
Standard prices only: Z.ai publishes no per-model batch, flex, priority or fast price on the pages we read.
Cached input: 17 of 18 standard prices include a cache-read price, a median 19% of the input price. What cached input means.
What we recorded about Z.ai's pricing page: Z.ai international API (docs.z.ai). Cached-input storage is listed as limited-time free. Lower rows come from the page's "Other Pricing" section. GLM-OCR, image, video and agent prices left out.
BroadNet Inference and Z.ai
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 1 model that Z.ai prices: GLM 5.3 at USD 0.78 / USD 3.46 against Z.ai's USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on Z.ai
- Z.ai's own pricing page (the source; checked 2026-11-14)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Quick answers
Is Z.ai OpenAI-compatible?
Yes, for chat completions, using the OpenAI Python SDK with Z.ai's base URL (Z.ai, OpenAI Python SDK guide, checked 2026-11-15).
What is Z.ai's API base URL?
https://api.z.ai/api/paas/v4/, as Z.ai documents it. The path ends in /v4/, not /v1 (Z.ai, OpenAI Python SDK guide, checked 2026-11-15).
Questions
How much does the Z.ai API cost per token?
Z.ai's standard prices run from USD 0.10 input and USD 0.10 output per 1M tokens (GLM-4-32B-0414-128K) to USD 2.20 / USD 8.90 (GLM-4.5-X). The median across 18 standard prices is USD 0.60 input and USD 2 output per 1M, which is USD 0.0000006 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Z.ai?
GLM-4-32B-0414-128K, at USD 0.10 input and USD 0.10 output per 1M tokens (USD 0.10 on a 3:1 input-to-output blend). GLM 4.7 Flash, GLM-4.5-Flash and GLM-4.6V-Flash are listed free.
Is Z.ai cheaper than other providers?
It depends on the model. Of 12 models that other providers also price, Z.ai is the cheapest standard price for 4 (all of them tied with another provider), for example GLM 4.5V, GLM 4.6V and GLM 5.3 FlashX; another provider is cheaper for 8; and it is the dearest for 3. Its median rank is 3 of a median 7 providers, on a 3:1 input-to-output blend.
Does Z.ai have batch, cached or priority pricing?
Cached input: yes, for 17 of 18 standard prices, at a median 19% of the input price. No batch, flex or priority prices are listed per model on the pages we read.
Is any model free on Z.ai?
Z.ai lists 3 models at 0 input and 0 output: GLM 4.7 Flash, GLM-4.5-Flash and GLM-4.6V-Flash. Free rows usually come with tight rate limits; they are not counted in the price range above.
How much does a chatbot cost per month on Z.ai?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 8.86 on GLM-4.6V-FlashX, USD 59.94 on GLM 4.5V (the middle of Z.ai's list) and USD 263.70 on GLM-4.5-X. Try your own numbers.