NewHow we catch a seller listing the wrong model, and refund you if one does.

Cheapest GLM API: below Z.ai on 10 of 11 models (November 2026)

Updated November 20, 2026, 11:00 UTC. MartLLM prices are read live when the page is built (every hour); other providers' prices were checked November 19, 2026 or read from their public price lists at build. MartLLM wrote this page and is one of the providers in it.

On November 20, 2026, MartLLM was below Z.ai’s own price on both input and output for 10 of the 11 GLM models we compared, with MartLLM’s card fee added. Among the real-time prices in the table, MartLLM was lowest on 14 of the 15 models; someone else was lower on GLM 4.7 Flash. MartLLM prices are the best seller’s price now; they move during the day.

Some MartLLM prices here are more than 70% below list. They are what buyers were billed, not errors. Why so cheap?

ProviderHow you payPrice against Z.ai’s
MartLLMPer token, prepaid; 5.5% + $0.50 card fee when adding creditBelow it on 10 of 11 models (card fee added)
Z.ai APIPer token, direct from Z.aiThe list price
OpenRouterPrepaid credit; 5.5% when buying creditAgainst Z.ai’s price: the same on 3, lower on 7, higher on 1 of 11
Vercel AI GatewayCredit in your Vercel accountAgainst Z.ai’s price: the same on 10, higher on 1 of 11
RequestyPrepaid; 5% on model costs, added when you top upAgainst Z.ai’s price: the same on 6, lower on 4 of 10
DeepInfraRuns models on its own GPUs, per tokenAgainst Z.ai’s price: the same on 2, lower on 7, higher on 1 of 10
Novita AIRuns open models on its own GPUs, per tokenAgainst Z.ai’s price: the same on 6, lower on 3, higher on 1 of 10

MartLLM first, then Z.ai’s own API, then the other providers that list these models. The table below shows, model by model, who is lowest. An empty cell means we could not confirm it on the provider's own pages.

GLM prices, model by model ($ per 1M input / output tokens)

ModelMartLLMZ.aiOpenRouterVercel AI GatewayRequestyDeepInfraNovita AI
GLM 5.3Why so cheap?$0.00286 / $0.00999$1.40 / $4.40$0.0699 / $1.40$1.40 / $4.40$0.75 / $2.40$0.90 / $4.00$1.40 / $4.40
GLM 5.3 FlashWhy so cheap?$0.00168 / $0.00415$0.15 / $0.50$0.0399 / $0.0784$0.15 / $0.50$0.12 / $0.46$0.15 / $0.50$0.15 / $0.50
GLM-5.2Why so cheap?$0.00578 / $0.0202$1.40 / $4.40$0.62 / $2.42$1.40 / $4.40$0.75 / $2.40$0.75 / $2.40$1.40 / $4.40
GLM 5.3 Prime$0.016 / $0.0504$1.68 / $5.28
GLM 4.7 Flash$0.000326 / $0.002Free$0.0605 / $0.40$0.07 / $0.40$0.06 / $0.40$0.07 / $0.40
GLM 5.1Why so cheap?$0.0136 / $0.0429$1.40 / $4.40$1.19 / $3.74$1.40 / $4.40$1.05 / $3.50$1.05 / $3.50$1.38 / $4.40
GLM 5.3 FlashXWhy so cheap?$0.0407 / $0.1375$0.37 / $1.25$0.37 / $1.25$0.37 / $1.25$0.37 / $1.25$0.37 / $1.25
GLM 4.5 AirWhy so cheap?$0.000129 / $0.000842$0.20 / $1.10$0.13 / $0.85$0.20 / $1.10$0.20 / $1.10$0.20 / $1.10$0.13 / $0.85
GLM-4.6Why so cheap?$0.00417 / $0.017$0.60 / $2.20$0.50 / $2.00$0.60 / $2.20$0.60 / $2.20$0.50 / $2.00$0.55 / $2.20
GLM 4.5Why so cheap?$0.00588 / $0.0216$0.60 / $2.20$0.60 / $2.20$0.60 / $2.20$0.60 / $2.20$0.38 / $1.60
GLM 5V Turbo$0.7175 / $2.3916$1.20 / $4.00$1.20 / $4.00
GLM-4.7Why so cheap?$0.00275 / $0.011$0.60 / $2.20$0.40 / $1.75$0.60 / $2.20$0.60 / $2.20$0.40 / $1.75$0.60 / $2.20
GLM-5 Turbo$0.06 / $0.20$1.20 / $4.00$1.20 / $4.00
GLM-5Why so cheap?$0.00387 / $0.0124$1.00 / $3.20$1.00 / $3.20$1.00 / $3.20$1.00 / $3.20$0.60 / $2.08$1.00 / $3.20
GLM 5.3 FlashX Legal$0.185 / $0.625$0.37 / $1.25$0.37 / $1.25

MartLLM: the best seller’s price, read November 20, 2026; the 5.5% card fee is not in the cell. Z.ai: its own pricing page, checked November 19, 2026; an empty cell means its page does not list that model. OpenRouter, Vercel AI Gateway, Requesty, DeepInfra and Novita AI: each one’s public model list, read when this page was built.

Each provider, good and bad

MartLLM

Pick it if: You want GLM below Z.ai’s price, billed per request with no plan, and the same key for every other model.

Watch for: Requests go to third-party providers, not to Z.ai directly: if you need Z.ai’s own data terms, use its API. The price is a market price and can be higher when the lower-priced sellers are busy (cap it with provider.max_price).

Source: MartLLM GLM prices (live, November 20, 2026)

Z.ai API

Pick it if: You want Z.ai’s own service, its free GLM 4.7 Flash, or a monthly GLM Coding Plan.

Watch for: Per-token prices are the list price; the Coding Plan is a subscription, not pay per request.

Source: Z.ai pricing (checked 2026-11-19)

OpenRouter

Pick it if: You already use OpenRouter for other models and want automatic failover.

Watch for: Its 5.5% credit fee comes on top of the prices in the table.

Source: OpenRouter pricing, its model list (checked 2026-11-19)

Vercel AI Gateway

Pick it if: Your app runs on Vercel or uses the AI SDK.

Watch for: No markup on provider token prices, so no saving per token either.

Source: Vercel AI Gateway pricing, its model list (checked 2026-11-19)

Requesty

Pick it if: You want routing rules, fallbacks and per-team spend limits.

Watch for: The 5% top-up fee comes on top of the prices in the table.

Source: Requesty pricing, its model list (checked 2026-11-19)

DeepInfra

Pick it if: Steady prices on US hosting for open models.

Watch for: Not every version is listed.

Source: DeepInfra pricing, its model list (checked 2026-11-19)

Novita AI

Pick it if: Low prices on open models.

Watch for: Check that your version is listed.

Source: Novita pricing, its model list (checked 2026-11-19)

How to switch to MartLLM

MartLLM takes OpenAI-style requests: change the base URL, the key and the model id (GLM ids on MartLLM start with z-ai/).

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.martllm.com/v1",  # was: https://api.z.ai/api/paas/v4/
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="z-ai/glm-5.3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Questions

Is there a free GLM API?

Yes. Z.ai lists GLM 4.7 Flash as free on its own API.

What is the GLM Coding Plan?

A Z.ai subscription for coding tools, from 18 USD a month according to its docs, in Lite, Pro and Max tiers. MartLLM bills per request instead, with no plan.

Can I cap what a GLM request costs on MartLLM?

Yes. Send provider.max_price with the most you will pay per million tokens; the request only goes to sellers at or under it.

Are there other fees on MartLLM?

No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.