Ways to buy 35
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| Baidu fp8 · cached $0.104 | $0.561 | $1.76 | $0.561 / $1.76Cheapest | $0.104 | Cheapest |
| Morph Default region · cached $0.108 | $0.655 | $2.06 | $0.655 / $2.06+17% vs cheapest | $0.108 | +17% vs cheapest |
 DeepInfrafp4 · cached $0.125 | $0.563 | $2.5 | $0.563 / $2.5+21% vs cheapest | $0.125 | +21% vs cheapest |
| InferenceNet Default region · cached $0.114 | $0.684 | $2.28 | $0.684 / $2.28+26% vs cheapest | $0.114 | +26% vs cheapest |
 Novita AIfp8 · cached $0.145 | $0.783 | $2.46 | $0.783 / $2.46+39% vs cheapest | $0.145 | +39% vs cheapest |
| Reka Default region · cached $0.152 | $0.761 | $2.57 | $0.761 / $2.57+41% vs cheapest | $0.152 | +41% vs cheapest |
| Io Net fp8 · cached $0.14 | $0.78 | $2.62 | $0.78 / $2.62+44% vs cheapest | $0.14 | +44% vs cheapest |
| Inceptron fp4 · cached $0.203 | $0.786 | $2.65 | $0.786 / $2.65+45% vs cheapest | $0.203 | +45% vs cheapest |
| Phala Default region · cached $0.156 | $0.84 | $2.64 | $0.84 / $2.64+50% vs cheapest | $0.156 | +50% vs cheapest |
 DigitalOceanDefault region · cached $0.169 | $0.91 | $2.86 | $0.91 / $2.86+62% vs cheapest | $0.169 | +62% vs cheapest |
| GMICloud fp8 · cached $0.182 | $0.98 | $3.08 | $0.98 / $3.08+75% vs cheapest | $0.182 | +75% vs cheapest |
| Sail Research fp8 · cached $0.19 | $0.77 | $4 | $0.77 / $4+83% vs cheapest | $0.19 | +83% vs cheapest |
| Sail Research us, fp8 · cached $0.19 | $0.77 | $4 | $0.77 / $4+83% vs cheapest | $0.19 | +83% vs cheapest |
 SiliconFlowfp8 · cached $0.208 | $1.12 | $3.52 | $1.12 / $3.52+100% vs cheapest | $0.208 | +100% vs cheapest |
| Decart fp4 · cached $0.196 | $1.19 | $3.74 | $1.19 / $3.74+112% vs cheapest | $0.196 | +112% vs cheapest |
 Qwen (Alibaba)Default region · cached $0.238 | $1.19 | $3.74 | $1.19 / $3.74+112% vs cheapest | $0.238 | +112% vs cheapest |
| Makora fp4 · cached $0.19 | $1.05 | $4.2 | $1.05 / $4.2+113% vs cheapest | $0.19 | +113% vs cheapest |
 FriendliDefault region · cached $0.234 | $1.26 | $3.96 | $1.26 / $3.96+124% vs cheapest | $0.234 | +124% vs cheapest |
| AkashML fp8 · cached $0.26 | $1.3 | $4.4 | $1.3 / $4.4+141% vs cheapest | $0.26 | +141% vs cheapest |
| AtlasCloud fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Basetenfp4 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.14 | +149% vs cheapest |
 Cloudflare Workers AIDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Crusoefp4 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Fireworks AIDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Mistral AInvfp4 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.14 | +149% vs cheapest |
 ModalDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Parasailfp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
| PrimeIntellect Default region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Together AIDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 VeniceDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
| Wafer Default region · cached $0.36 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.36 | +149% vs cheapest |
| Wafer us · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
 Z.aifp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+149% vs cheapest | $0.26 | +149% vs cheapest |
| Baseten fast, fp8 · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+274% vs cheapest | $0.21 | +274% vs cheapest |
| Qwen (Alibaba) fast · cached $0.56 | $2.8 | $8.8 | $2.8 / $8.8+399% vs cheapest | $0.56 | +399% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $91.43 direct.
Helicone$91.43+0%
Kong AI Gateway$91.43+0%
LiteLLM$91.43+0%
Vercel AI Gateway$91.43+0%
Requesty$96.00+5%
Eden AI$96.46+5.5%
OpenRouter$96.46+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| GLM 5.3 Prime Z.ai · 1M | $2.8 | $8.8 | $2.8 / $8.8 | $4.3 | 1M | Lab list price | · |
| GLM 5.3 FlashX Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · |
| GLM 5.3 Flash Z.ai · 1.31M | $0.045 | $0.14 | $0.045 / $0.14 | $0.069 | 1.31M | on InferenceNet (fp4) | · |
| GLM 5.2 Z.ai · 1M | $0.561 | $1.76 | $0.561 / $1.76 | $0.862 | 1M | on Baidu (fp8) | · |
 Gemini 3.8 FlashGoogle · 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 3.7 Flash Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75100% | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | 100% |
| Gemini 3.6 Flash 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) | · |
 Kimi K2.5Moonshot AI · 262K | $0.45 | $2.25 | $0.45 / $2.25 | $0.9 | 262K | on SiliconFlow (int4) | · |
About GLM 5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Takes text in and returns text. First listed Sep 23, 2026. Up to 944K output tokens. Blended price $0.862 per 1M tokens at 3 input to 1 output. Overall score 8 on leadersboard.fru.dev (rank 21). Model id glm-5-3.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across fru.devCompany profile
Questions
How much does GLM 5.3 cost?
$0.561 per million input tokens and $1.76 per million output tokens, with cached input at $0.104.
What is the context window of GLM 5.3?
1.31M tokens, with up to 944K tokens of output.
Where is GLM 5.3 cheapest?
Of 35 routes tracked, Baidu is cheapest at $0.561 input and $1.76 output per million tokens.
Has GLM 5.3's price changed?
Yes. The output price went from $3.53 to $2.65, first seen Sep 25, 2026.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.