Pricingby GlyphGLM 5.2 is a large-scale reasoning model from Z.ai.
Ways to buy 33
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp4-flex, fp4 · cached $0.112 | $0.6 | $1.92 | $0.6 / $1.92Cheapest | $0.112 | Cheapest |
| Ambient fp8 · cached $0.15 | $0.6 | $2 | $0.6 / $2+2% vs cheapest | $0.15 | +2% vs cheapest |
| Morph fp8 · cached $0.196 | $0.365 | $3.07 | $0.365 / $3.07+12% vs cheapest | $0.196 | +12% vs cheapest |
fp4 · cached $0.14 | $0.62 | $2.42 | $0.62 / $2.42+15% vs cheapest | $0.14 | +15% vs cheapest |
Default region · cached $0.105 | $0.7 | $2.2 | $0.7 / $2.2+16% vs cheapest | $0.105 | +16% vs cheapest |
fp4 · cached $0.14 | $0.75 | $2.4 | $0.75 / $2.4+25% vs cheapest | $0.14 | +25% vs cheapest |
fp8 · cached $0.193 | $0.966 | $3.04 | $0.966 / $3.04+60% vs cheapest | $0.193 | +60% vs cheapest |
fp8-us-east-1, fp8 · cached $0.224 | $1.12 | $3.52 | $1.12 / $3.52+85% vs cheapest | $0.224 | +85% vs cheapest |
| Wafer us, fp4 · cached $0.033 | $0.034 | $7 | $0.034 / $7+91% vs cheapest | $0.033 | +91% vs cheapest |
| Relace fp4 · cached $0.0065 | $0.0065 | $7.91 | $0.0065 / $7.91+113% vs cheapest | $0.0065 | +113% vs cheapest |
Default region · cached $0.26 | $1.18 | $4.4 | $1.18 / $4.4+113% vs cheapest | $0.26 | +113% vs cheapest |
| Inceptron fp4 · cached $0.25 | $1.39 | $4.39 | $1.39 / $4.39+130% vs cheapest | $0.25 | +130% vs cheapest |
| AtlasCloud fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
| Baidu fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
fp8 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.14 | +131% vs cheapest |
fp8-us, fp8 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.14 | +131% vs cheapest |
Default region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
| GMICloud fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
zdr, nvfp4 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.14 | +131% vs cheapest |
fp4 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.14 | +131% vs cheapest |
fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
fp4 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
| StreamLake fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
Default region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
| Wafer Default region, fp4 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+131% vs cheapest | $0.26 | +131% vs cheapest |
eu · cached $0.154 | $1.54 | $4.84 | $1.54 / $4.84+154% vs cheapest | $0.154 | +154% vs cheapest |
fast, fp8 · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+247% vs cheapest | $0.21 | +247% vs cheapest |
us-fast, fp8 · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+247% vs cheapest | $0.21 | +247% vs cheapest |
fast, fp8 · cached $0.462 | $2.31 | $7.26 | $2.31 / $7.26+281% vs cheapest | $0.462 | +281% vs cheapest |
| Baidu fast, fp4 · cached $0.56 | $2.25 | $7.88 | $2.25 / $7.88+293% vs cheapest | $0.56 | +293% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $98.40 direct.
LiteLLM$98.40+0%
Neon AI Gateway$98.40+0%
Vercel AI Gateway$98.40+0%
Requesty$103.32+5%
Eden AI$103.81+5.5%
OpenRouter$103.81+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Kong AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. |
Z.ai · 1M | $2.8 | $8.8 | $2.8 / $8.8 | $4.3 | 1M | Lab list price | · | GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. |
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. |
Z.ai · 1M | $0.012 | $0.158 | $0.012 / $0.158 | $0.049 | 1M | on Relace (fp4) | · | GLM-5.3-Flash is a native multimodal model from Z.ai. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · | Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. |
Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | · | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. |
About GLM 5.2
Takes text in and returns text. First listed Sep 23, 2026. Up to 944K output tokens. Blended price $0.93 per 1M tokens at 3 input to 1 output. Model id glm-5-2.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does GLM 5.2 cost?
$0.6 per million input tokens and $1.92 per million output tokens, with cached input at $0.112.
What is the context window of GLM 5.2?
1M tokens, with up to 944K tokens of output.
Where is GLM 5.2 cheapest?
Of 33 routes tracked, DeepInfra is cheapest at $0.6 input and $1.92 output per million tokens.
Has GLM 5.2's price changed?
Yes. The input price went from $0.06 to $0.034, first seen Oct 25, 2026.