GLM-4.5-Air pricing.
prices as of · 23 providers · 28 prices
Z.ai's GLM-4.5-Air holds 131k tokens of context and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
GLM-4.5-Air costs $0.20 in and $1.10 out per million tokens from Z.ai; the cheapest price we can explain is $0.80 at Submodel, checked 16 Sept 2026.
Z.ai list price
$1.70/M tokens
$0.20 in · $1.10 out
read · 52% below the market median
Cheapest price we can explain
$0.80/M tokens
$0.10 in · $0.50 out · 53% under list
read
What it costs for your work
Z.ai list price
$0.186a month
cheapest we can explain · Submodel
$0.09a month
difference
$0.096saved
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Every provider selling GLM-4.5-Air
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Z.ai's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
$0.20 / $1.10in / out per M
1.00×of list price
Cheaper, and we know why
17 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Submodel
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.50in / out per M
0.47×of list price
$0.11 / $0.56in / out per M
0.52×of list price
NanoGPTRoutes to a host serving the open weights; precision not disclosed.
128k context hereNanoGPT ↗$0.12 / $0.80in / out per M
0.68×of list price
- NanoGPT
Routes to a host serving the open weights; precision not disclosed.
128k context hereNanoGPT ↗$0.12 / $0.80in / out per M
0.68×of list price
$0.13 / $0.85in / out per M
0.73×of list price
LLM GatewayRoutes to a host serving the open weights; precision not disclosed.
131k context hereLLM Gateway ↗$0.13 / $0.85in / out per M
0.73×of list price
NovitaHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.13 / $0.85in / out per M
0.73×of list price
Hugging Face Inference ProvidersRoutes to a host serving the open weights; precision not disclosed.
$0.13 / $0.85in / out per M
0.73×of list price
$0.13 / $0.85in / out per M
0.73×of list price
- Novita
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.
bf16 precisionNovita ↗$0.13 / $0.85in / out per M
0.73×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.13 / $0.85in / out per M
0.73×of list price
Eden AIServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionEden AI ↗$0.13 / $0.85in / out per M
0.73×of list price
SiliconFlow (China)SiliconFlow's China-region catalog, priced in the domestic market.
131k context hereSiliconFlow (China) ↗$0.14 / $0.86in / out per M
0.75×of list price
SiliconFlowHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context hereSiliconFlow ↗$0.14 / $0.86in / out per M
0.75×of list price
- SiliconFlow
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionSiliconFlow ↗$0.14 / $0.86in / out per M
0.75×of list price
io.net IntelligenceHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context hereio.net Intelligence ↗$0.16 / $0.94in / out per M
0.83×of list price
$0.17 / $0.99in / out per M
0.87×of list price
Same price as the maker
10 pricesThe same price the maker charges, sold by someone else.
$0.20 / $1.10in / out per M
1.00×of list price
OrcaRouterThe same price Z.ai charges.
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
$0.20 / $1.10in / out per M
1.00×of list price
Frequently asked
- Who sells GLM-4.5-Air cheapest?
- Submodel, at $0.10 in and $0.50 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
- Is GLM-4.5-Air open weights?
- Yes. Z.ai publishes the weights, so anyone may host GLM-4.5-Air, which is why 23 providers sell it and why their prices differ so much.
- How much context does GLM-4.5-Air hold?
- 131,072 tokens in one call, which is about 131k, and it can call your own functions.
- How does GLM-4.5-Air compare with the rest of the market?
- At $1.70 per million tokens, Z.ai's price is 52% below the $3.55 median across the 337 text models we track.