Models / Zhipu AI / GLM-5

Zhipu AI · glm

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

$1.00 in · $3.20 out

per 1M tokens · first-party price. Reference price from Zhipu AI, the lab's own listing.

Provider input prices run from $0.40 to $1.10 per 1M tokens. Output prices run from $1.75 to $3.36.

Context
204,800
Max output
131,072
Cache read
$0.20
Cache write
$0
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Feb 12, 2026
Updated in source
Feb 12, 2026
Knowledge
—
Providers
31

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

GLM-5

$10.80

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Vultr$0.40$1.75———
ZenMux$0.58$2.60$0.14——
CrossModel$0.60$3.00$0.16$0.60—
GMI Cloud$0.60$1.92$0.12——
Kilo Gateway$0.60$1.92$0.12——
NanoGPT$0.60$1.90$0.10——
OpenRouter$0.60$1.92$0.12——
DevPass$0.72$2.30$0.14$0—
DInference$0.75$2.40———
TokenGo$0.89$3.26$0.22——
Abacus$1.00$3.20———
Amazon Bedrock$1.00$3.20———
Eden AI$1.00$3.20$0.20——
Impossibl$1.00$3.20$0.20——
LLM Gateway$1.00$3.20$0.20——
Merge Gateway$1.00$3.20$0.20$0—
Novita AI$1.00$3.20$0.20——
Ofox$1.00$3.20$0.20——
OrcaRouter$1.00$3.20$0.26$0—
Tempr Gateway$1.00$3.20$0.20$0—
TensorX$1.00$3.20$0.25$1.25—
Together AI$1.00$3.20——deprecated
Venice AI$1.00$3.20$0.20——
Vercel AI Gateway$1.00$3.20———
Vertex$1.00$3.20$0.10—deprecated
Z.AI$1.00$3.20$0.20$0—
Zhipu AIreference$1.00$3.20$0.20$0—
Melious$1.10$3.36$0.27——
Alibaba Token Plan$0$0$0$0—
Alibaba Token Plan$0$0$0$0—
SCNet Token Plan$0$0$0——

Jobs this model qualifies for

Comparisons