Skip to content
Sovyron

GLM-5.2

glm1.0M context1.0M max outputreleased Jun 13, 2026Open weightsReasoningTool calling3 subscription plans →

As of Nov 22, 2026, the cheapest GLM-5.2 API price is $0.19 per 1M input tokens (Wafer) and $1.5 per 1M output tokens (engy). GLM-5.2 is offered by 81 providers in the glm family, open weights, reasoning enabled. Z.AI's own rate is $4.4 per 1M output tokens. 2 providers list it as a free-tier offer. It is also included in 3 flat-rate subscription plans, Qwen (Alibaba Cloud) Token Plan Lite from $8/mo.

Cheapest input
$0.19
Cheapest output
$1.5
Official (Z.AI)
$4.4
output per 1M tokens
Providers
81
offering this model
Spread
4.5×
max / min output
Free offers
2
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GLM-5.2 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
IteraComputeopenz-ai/glm-5.2$0.53$1.72$0.12—1.0M—
NanoGPTopenz-ai/glm-5.2$0.53$1.79$0.1—1.0Myesterdayout +35.6%
Standard Computeopenz-ai/glm-5.2$0.5625$1.8$0.105—1.0M—
engyopenglm-5.2$0.68Cheapest$1.5$0.18—262k—
DevPass (LLM Gateway)openglm-5.2$0.582$1.94$0.0873free1.0M4d agoout −7.2%
Ambientopenz-ai/glm-5.2$0.6$2$0.15free203k—
SCX.aiopenGLM-5.2$0.61$1.98$0.22—1.0M7d agoout +11%
LLM Gatewayopenscx-ai-gp/glm-5.2$0.605$2.123$0.154—1.0M4d agoout −6.5%
OpenRouteropenz-ai/glm-5.2$0.62$2.42$0.14—1.0M2d agoout −64.4%
CoreWeaveopenzai-org/GLM-5.2$0.62$2.42$0.14—1.0M38d ago
Kenariopenglm-5-2$0.2857$3.43$0.0531—1.0M5d agoout +0%
Tokenifyopenz-ai/glm-5.2$0.7$2.2$0.26—1.0M—
Deep Infraopenzai-org/GLM-5.2$0.75$2.4$0.14$0.93751.0M—
routing.runopenglm-5.2$0.8$2.4——200k—
Requestyopenglm-5.2$0.8$2.55$0.16—1.0M—
WaferopenGLM-5.2Cheapest$0.19$4.4$0.18—1.0M7d agoout +0%
Vultropenglm-5.2$0.75$3——1.0M—
Doublewordopenzai-org/GLM-5.2-FP8$0.93$3$0.186$1.16251.0M—
GMI Cloudopenzai-org/GLM-5.2-FP8$0.979$3.08$0.182—1.0M—
Merge Gatewayopenzai/glm-5.2$1.05$3.3$0.195—1.0M—
Zenifraopenzenifra/glm-5.2$1.0336$3.6267$0.2539—1.0M—
Phalaopenz-ai/glm-5.2$1.26$3$0.22—1.0M—
Alibaba (China)openglm-5.2$1.1$3.851$0.275free1.0M—
AIHubMixopenglm-5.2$1.1268$3.9438$0.2817—1.0M—
Volcengine Arkopenglm-5-2-260617$1.1875$4.1562$0.2969—1.0M—
Zhipu AIopenglm-5.2$1.1952$4.1831$0.2988free1.0M33d ago
SiliconFlow (China)openzai-org/GLM-5.2$1.1956$4.1845$0.2989free1.0M31d ago
Huawei Cloud MAASopenglm-5.2$1.1994$4.1979——1.0M—
SiliconFlowopenzai-org/GLM-5.2$1.302$4.092$0.26free1.0M61d ago
CrossModelopenz-ai/glm-5.2$1.2$4.4$0.3$1.21.0M—
Cortecsopenglm-5.2$1.3$4.2$0.25—1.0M2d agoout +29.6%
302.AIopenglm-5.2$1.4$4.4$0.26—1.0M—
Abacusopenzai-org/GLM-5.2$1.4$4.4$0.26—1.0M—
Adaptionopenglm-5.2$1.4$4.4$0.26—1.0M—
AI/ML APIopenzhipu/glm-5.2$1.4$4.4$0.26—1.0M30d agoout −23.1%
Alibabaopenglm-5.2$1.4$4.4$0.28free1.0M—
Arceeopenzai-org/glm-5.2$1.4$4.4$0.26—262k—
Basetenopenzai-org/GLM-5.2$1.4$4.4$0.14—1.0M—
BytePlus ModelArkopenglm-5-2-260617$1.4$4.4$0.26—1.0M—
CommandCodeopenzai-org/GLM-5.2$1.4$4.4$0.26—1.0M—
Databricksopendatabricks-glm-5-2$1.4$4.4$0.26—1.0M—
DigitalOceanopenglm-5.2$1.4$4.4$0.21—262k61d ago
Eden AIopenzai/glm-5.2$1.4$4.4$0.26—1.0M—
EmpirioLabs AIopenglm-5-2$1.4$4.4$1.4—1.0M—
Friendliopenzai-org/GLM-5.2$1.4$4.4$0.26—1.0M—
Vertexopenzai-org/glm-5.2-maas$1.4$4.4$0.14—1.0M—
HPC-AIopenzai-org/glm-5.2$1.4$4.4$0.26—1.0M—
Hugging Faceopenzai-org/GLM-5.2$1.4$4.4——262k—
Impossiblopenzai/glm-5.2$1.4$4.4$0.26—1.0M—
Jalapeno CloudopenGLM-5.2$1.4$4.4$0.26—1.0M—
Kelnopenzai-org/glm-5.2$1.4$4.4$0.28—1.0M—
Kilo Gatewayopenz-ai/glm-5.2$1.4$4.4$0.14—1.0M—
LLM Gatewayopenalibaba/glm-5.2$1.4$4.4$0.28—1.0M—
LLM Gatewayopennovita/glm-5.2$1.4$4.4$0.26—1.0M—
LLM Gatewayopentencent/glm-5.2$1.4$4.4$0.26—1.0M—
LLM Gatewayopenzai/glm-5.2$1.4$4.4$0.26—1.0M—
Nebius Token Factoryopenzai-org/GLM-5.2$1.4$4.4$0.14—1.0M—
Neonopenglm-5-2$1.4$4.4$0.26—1.0M—
Novita AIopenzai-org/glm-5.2$1.4$4.4$0.26—1.0M—
Ofoxopenz-ai/glm-5.2$1.4$4.4$0.26—1.0M—
Ollama Cloudopenglm-5.2$1.4$4.4$0.26—976k—
OrcaRouteropenz-ai/glm-5.2$1.4$4.4$0.26—1.0M—
Together AIopenzai-org/GLM-5.2$1.4$4.4$0.26—1.0M—
TokenGoopenz-ai/glm-5.2$1.4$4.4$0.26—1.0M—
Venice AIopenzai-org-glm-5-2$1.4$4.4$0.26—1.0M—
Vercel AI Gatewayopenzai/glm-5.2$1.4$4.4$0.14—1.0M17d agoout +72.5%
Watt CloudopenGLM-5.2$1.4$4.4——1.0M—
Z.AIopenglm-5.2$1.4$4.4$0.26free1.0M—
ZenMuxopenz-ai/glm-5.2$1.4$4.4$0.26—1.0M31d ago
TensorXopenz-ai/glm-5.2$1.5$4.5$0.375—1.0M—
above.devopenglm-5.2$1.54$4.84$0.154—1.0M—
Prime Inferenceopenz-ai/glm-5.2$1.54$4.84——1.0M—
Morphopenmorph-glm52-744b$1.19$6$0.1955—1.0M—
evrocopenzai-org/GLM-5.2$1.4375$5.75——524k—
GreenPTopenglm-5.2$1.7383$5.1589$0.4486—1.0M31d ago
Opperopenglm-5.2$1.6271$5.811——1.0M—
Scalewayopenglm-5.2$2.0187$6.1682——256k31d ago
Regolo AIopenglm5.2$2.31$6——96k—
DevPass (LLM Gateway)openglm-5.2-fast$2.1256$6.776$0.429—1.0M5d agoout +0%
AIHubMixfreecoding-glm-5.2-freefreefree——1.0M—
SenseNova (China)freeglm-5.2freefreefree—1.0M—

GLM-5.2 price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 19 providers whose rate moved. Each step is a recorded change. All recent price changes.

GLM-5.2 output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$5$10$15$20Sep 10, 2026Oct 17, 2026Nov 22, 2026
NanoGPT$1.79DevPass (LLM Gateway)$1.94SCX.ai$1.98LLM Gateway$2.123OpenRouter$2.42CoreWeave$2.42
GLM-5.2 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
NanoGPT$0.42 → $0.53$1.32 → $1.79+35.6%
OpenRouter$0.007 → $0.62$6.8 → $2.42−64.4%
Cortecs$0.9 → $1.3$3.24 → $4.2+29.6%
DevPass (LLM Gateway)$0.665 → $0.582$2.09 → $1.94−7.2%
LLM Gateway$0.7224 → $0.605$2.2704 → $2.123−6.5%
NanoGPT$0.189 → $0.42$0.594 → $1.32+122.2%
LLM Gateway$0.605 → $0.7224$2.123 → $2.2704+6.9%
DevPass (LLM Gateway)$0.605 → $0.665$2.123 → $2.09−1.6%
Kenari$0.2857 → $0.2857$3.4286 → $3.43+0%
DevPass (LLM Gateway)$2.156 → $2.1256$6.776−1.4%
SCX.ai$0.55 → $0.61$1.784 → $1.98+11%
Wafer$1.4 → $0.19$4.4−86.4%
NanoGPT$0.42 → $0.189$1.32 → $0.594−55%
OpenRouter$0.006 → $0.007$6.8+16.7%
NanoGPT$0.189 → $0.42$0.594 → $1.32+122.2%
NanoGPT$0.42 → $0.189$1.32 → $0.594−55%
Vercel AI Gateway$0.8 → $1.4$2.55 → $4.4+72.5%
NanoGPT$0.134 → $0.42$1.4 → $1.32−5.7%
NanoGPT$0.078 → $0.134$1.4+71.8%
NanoGPT$0.07 → $0.078$1.4+11.4%

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Alibaba Token Planplanfreefree1.0M
Alibaba Token Plan (China)planfreefree1.0M
SCNet Token Planplanfreefree1.0M
Tencent Token Planplan——1.0M
Tencent Token Planplan——1.0M

GLM-5.2 pricing FAQ

What is the cheapest GLM-5.2 API?

As of Nov 22, 2026, engy has the lowest GLM-5.2 output price at $1.5 per 1M tokens, and Wafer has the lowest input price at $0.19 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does GLM-5.2 cost on Z.AI?

Z.AI charges $1.4 per 1M input tokens and $4.4 per 1M output tokens for GLM-5.2.

How many providers offer GLM-5.2?

81 providers list GLM-5.2 on Sovyron; 79 of them sell it at a metered per-token price.

Is GLM-5.2 free?

2 providers list a free-tier offer: AIHubMix, SenseNova (China). Free tiers usually have rate limits.

Is GLM-5.2 included in a subscription plan?

Yes. 3 flat-rate plans include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

What is the context window of GLM-5.2?

GLM-5.2 supports a 1.0M-token context window and up to 1.0M output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—