GLM-4.6 pricing.
prices as of · 33 providers · 41 prices
Z.ai's GLM-4.6 holds 205k 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-4.6 costs $0.60 in and $2.20 out per million tokens from Z.ai; the cheapest price we can explain is $2.00 at 302.AI, checked 16 Sept 2026.
Z.ai list price
$4/M tokens
$0.60 in · $2.20 out
read · 13% above the market median
Cheapest price we can explain
$2.00/M tokens
$0.29 in · $1.14 out · 50% under list
302.AIread
What it costs for your work
Z.ai list price
$0.492a month
cheapest we can explain · 302.AI
$0.24a month
difference
$0.252saved
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-4.6
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.
$0.60 / $2.20in / out per M
1.00×of list price
Cheaper, and we know why
19 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- 302.AI
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.29 / $1.14in / out per M
0.50×of list price
NanoGPTRoutes to a host serving the open weights; precision not disclosed.
200k context hereNanoGPT ↗$0.35 / $1.40in / out per M
0.61×of list price
- NanoGPT
Routes to a host serving the open weights; precision not disclosed.
200k context hereNanoGPT ↗$0.35 / $1.40in / out per M
0.61×of list price
$0.35 / $1.54in / out per M
0.65×of list price
HeliconeHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.45 / $1.50in / out per M
0.71×of list price
FastRouterRoutes to a host serving the open weights; precision not disclosed.
203k context hereFastRouter ↗$0.43 / $1.74in / out per M
0.76×of list price
$0.43 / $1.75in / out per M
0.76×of list price
Kilo GatewayRoutes to a host serving the open weights; precision not disclosed.
198k context hereKilo Gateway ↗$0.43 / $1.75in / out per M
0.76×of list price
VeniceServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
$0.43 / $1.75in / out per M
0.76×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.43 / $1.75in / out per M
0.76×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
203k context hereTrustedRouter ↗$0.45 / $1.85in / out per M
0.80×of list price
DeepInfraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
203k context hereDeepInfra ↗$0.50 / $2in / out per M
0.88×of list price
Eden AIRoutes to a host serving the open weights; precision not disclosed.
203k context hereEden AI ↗$0.50 / $2in / out per M
0.88×of list price
- DeepInfra
Serves the open weights at fp4, a lower precision than the maker's, so not quite the same product.
$0.50 / $2in / out per M
0.88×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.
200k context hereio.net Intelligence ↗$0.52 / $2.04in / out per M
0.90×of list price
$0.55 / $2.20in / out per M
0.96×of list price
$0.55 / $2.20in / out per M
0.96×of list price
Hugging Face Inference Providers8% under the list price, an ordinary reseller margin.
$0.55 / $2.20in / out per M
0.96×of list price
$0.55 / $2.20in / out per M
0.96×of list price
Same price as the maker
17 pricesThe same price the maker charges, sold by someone else.
$0.60 / $2.20in / out per M
1.00×of list price
OrcaRouterThe same price Z.ai charges.
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
OpenCode ZenThe same price Z.ai charges.
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.61 / $2.22in / out per M
1.01×of list price
$1 / $3in / out per M
1.50×of list price
$1 / $3in / out per M
1.50×of list price
Cheaper, and nobody says why
2 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
MeganovaLists closed models at 0.80× the maker's price across its catalog.
203k context hereMeganova ↗$0.45 / $1.90in / out per M
0.81×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
203k context hereFeatherless ↗$0.55 / $2.20in / out per M
0.96×of list price
Given away with limits
2 free tiers · never rankedThese providers give GLM-4.6 away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
iFlow
ModelScope
Frequently asked
- Who sells GLM-4.6 cheapest?
- 302.AI, at $0.29 in and $1.14 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-4.6 open weights?
- Yes. Z.ai publishes the weights, so anyone may host GLM-4.6, which is why 33 providers sell it and why their prices differ so much.
- How much context does GLM-4.6 hold?
- 204,800 tokens in one call, which is about 205k, and it can call your own functions.
- How does GLM-4.6 compare with the rest of the market?
- At $4 per million tokens, Z.ai's price is 13% above the $3.55 median across the 337 text models we track.