GLM-5.1 pricing.
prices as of · 67 providers · 81 prices
Z.ai's GLM-5.1 holds 200k 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-5.1 costs $1.40 in and $4.40 out per million tokens from Z.ai; the cheapest price we can explain is $3.50 at Crof, checked 16 Sept 2026.
Z.ai list price
$8.60/M tokens
$1.40 in · $4.40 out
read · 142% above the market median
Cheapest price we can explain
$3.50/M tokens
$0.45 in · $2.15 out · 59% under list
Crofread
What it costs for your work
Z.ai list price
$1.10a month
cheapest we can explain · Crof
$0.399a month
difference
$0.705saved
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-5.1
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.
$1.40 / $4.40in / out per M
1.00×of list price
Cheaper, and we know why
35 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Crof
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
203k context hereCrof ↗$0.45 / $2.15in / out per M
0.41×of list price
HPC-AIHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
202k context here$0.61 / $2.46in / out per M
0.50×of list price
$0.75 / $2.60in / out per M
0.56×of list price
AvianHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
203k context hereAvian ↗$0.74 / $2.97in / out per M
0.60×of list price
LLM GatewayRoutes to a host serving the open weights; precision not disclosed.
203k context hereLLM Gateway ↗$0.93 / $2.93in / out per M
0.67×of list price
Alibaba Cloud (China)Alibaba's China-region Model Studio, which prices the Qwen models below the international list. A region, not a deal.
203k context hereAlibaba Cloud (China) ↗$0.82 / $3.30in / out per M
0.67×of list price
Empirio LabsRoutes to a host serving the open weights; precision not disclosed.
202k context hereEmpirio Labs ↗$0.82 / $3.30in / out per M
0.67×of list price
OpenRouterRoutes to a host serving the open weights; precision not disclosed.
205k context hereOpenRouter ↗$0.97 / $3.04in / out per M
0.69×of list price
StreamLakeServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precision$0.97 / $3.04in / out per M
0.69×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
205k context hereNous Portal ↗$0.97 / $3.04in / out per M
0.69×of list price
EBCloudHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.86 / $3.43in / out per M
0.70×of list price
ChutesHosts the open weights on its own servers, so the price is its own, not a resale. Precision tee.
203k context hereChutes ↗$0.98 / $3.08in / out per M
0.70×of list price
GMI CloudServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.98 / $3.08in / out per M
0.70×of list price
- Chutes
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.98 / $3.08in / out per M
0.70×of list price
$0.88 / $3.51in / out per M
0.71×of list price
- Ollama Cloud
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
203k context here$1 / $3.20in / out per M
0.72×of list price
Hugging Face Inference ProvidersRoutes to a host serving the open weights; precision not disclosed.
203k context hereHugging Face Inference Providers ↗$1 / $3.20in / out per M
0.72×of list price
- Wafer
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
203k context here$1 / $3.20in / out per M
0.72×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
203k context hereTrustedRouter ↗$1.03 / $3.25in / out per M
0.74×of list price
$1.05 / $3.50in / out per M
0.77×of list price
$1.05 / $3.50in / out per M
0.77×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 ↗$1.05 / $3.50in / out per M
0.77×of list price
- DeepInfra
Serves the open weights at fp4, a lower precision than the maker's, so not quite the same product.
$1.05 / $3.50in / out per M
0.77×of list price
CrossModelHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$1 / $3.80in / out per M
0.79×of list price
SiliconFlowServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$1.19 / $3.74in / out per M
0.85×of list price
showing the 25 cheapest of 35 · every row in the open dataset
Same price as the maker
36 pricesThe same price the maker charges, sold by someone else.
Charm HyperThe same price Z.ai charges.
203k context here$1.36 / $4.27in / out per M
0.97×of list price
$1.36 / $4.27in / out per M
0.97×of list price
$1.38 / $4.40in / out per M
0.99×of list price
Jalapeno CloudThe same price Z.ai charges.
203k context here$1.38 / $4.40in / out per M
0.99×of list price
$1.38 / $4.40in / out per M
0.99×of list price
$1.38 / $4.40in / out per M
0.99×of list price
TokenGoThe same price Z.ai charges.
$1.40 / $4.40in / out per M
1.00×of list price
AurikoThe same price Z.ai charges.
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
OrcaRouterThe same price Z.ai charges.
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
- TensorX
The same price Z.ai charges.
203k context here$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
Merge GatewayThe same price Z.ai charges.
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
302.AIThe same price Z.ai charges.
$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
OpenCode GoThe same price Z.ai charges.
203k context here$1.40 / $4.40in / out per M
1.00×of list price
$1.40 / $4.40in / out per M
1.00×of list price
showing the 25 cheapest of 36 · every row in the open dataset
Cheaper, and nobody says why
4 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 ↗$1.05 / $3.50in / out per M
0.77×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
203k context hereFeatherless ↗$1.30 / $4.30in / out per M
0.95×of list price
AmbientWe could not read this provider's prices reliably, so the row is listed but never ranked.
$1.40 / $4.40in / out per M
1.00×of list price
FriendliAIWe could not read this provider's prices reliably, so the row is listed but never ranked.
203k context hereFriendliAI ↗$1.40 / $4.40in / out per M
1.00×of list price
Given away with limits
5 free tiers · never rankedThese providers give GLM-5.1 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.
Alibaba Token Plan
Kenari
Zhipu AI Coding Plan- SCNet Token Plan
Alibaba Token Plan (China)
Frequently asked
- Who sells GLM-5.1 cheapest?
- Crof, at $0.45 in and $2.15 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-5.1 open weights?
- Yes. Z.ai publishes the weights, so anyone may host GLM-5.1, which is why 67 providers sell it and why their prices differ so much.
- How much context does GLM-5.1 hold?
- 200,000 tokens in one call, which is about 200k, and it can call your own functions.
- How does GLM-5.1 compare with the rest of the market?
- At $8.60 per million tokens, Z.ai's price is 142% above the $3.55 median across the 337 text models we track.