FindCostShortlistChangesModels
← All tracked models

Z.ai

GLM 5.3 API prices by provider

z-ai/glm-5.3

33 inference providers serve this exact model through OpenRouter. Input and output rates are paired per endpoint; route tags may identify a region or sub-endpoint whose eligibility is not yet verified.

Active endpoints
42 / 42
Lowest at 1M in + 1M out
$2.7456
Inceptron · standard tier
Context up to
1.05M
Latest price change
None yet
Rates unchanged since first record 2026-10-14
GLM 5.3 endpoint prices per million tokens
Provider · routeTierInput / 1MOutput / 1MCache readCache writeContextTools1M + 1MStatusPrice since

Inceptron

inceptron/fp4 · fp4

Standard$0.55$2.1956$0.18—1.05MYes$2.7456ActiveSince

Baidu

baidu/fp8 · fp8

Promo$0.6986$2.1956$0.1297—1.05MYes$2.8942ActiveSince

Novita

novita/fp8 · fp8

Promo$0.70$2.20$0.13—1.05MYes$2.90ActiveSince

SiliconFlow

siliconflow/fp8 · fp8

Promo$0.70$2.20$0.13—1.05MYes$2.90ActiveSince

DeepInfra

deepinfra/fp4 · fp4

Promo$0.5625$2.50$0.125—1.05MYes$3.0625ActiveSince

Io Net

io-net/fp8 · fp8

Standard$0.49$2.90$0.19—262KYes$3.39ActiveSince

Phala

phala · unknown

Promo$0.84$2.64$0.156—1.05MYes$3.48ActiveSince

Decart

decart/fp4 · fp4

Standard$0.84$2.65$0.19—1.05MYes$3.49ActiveSince

Sail Research

sail-research/fp8 · fp8

Standard$0.15$3.40$0.14—1.05MYes$3.55ActiveSince

Sail Research

sail-research/us · fp8

Standard$0.15$3.40$0.14—1.05MYes$3.55ActiveSince

DigitalOcean

digitalocean · unknown

Standard$0.91$2.86$0.169—1.05MYes$3.77ActiveSince

GMICloud

gmicloud/fp8 · fp8

Promo$0.98$3.08$0.182—1.05MYes$4.06ActiveSince

Reka

reka · unknown

Promo$0.14$4.20$0.105—262KYes$4.34ActiveSince

Relace

relace · unknown

Standard$0.063$4.40$0.0586—1.05MYes$4.463ActiveSince

InferenceNet

inference-net/fp4 · fp4

Standard$0.08$4.40$0.06—1.05MYes$4.48ActiveSince

Makora

makora/fp4 · fp4

Standard$0.14$4.40$0.10—1.05MYes$4.54ActiveSince

AkashML

akashml/fp8 · fp8

Standard$0.19$4.40$0.19—1.05MYes$4.59ActiveSince

Wafer

wafer/us · unknown

Standard$0.079$4.80$0.059—1.05MYes$4.879ActiveSince

Alibaba

alibaba · unknown

Standard$1.19$3.74$0.238—1MYes$4.93ActiveSince

Wafer

wafer · unknown

Standard$0.17$4.80$0.16—1.05MYes$4.97ActiveSince

Friendli

friendli · unknown

Promo$1.26$3.96$0.234—1.05MYes$5.22ActiveSince

AtlasCloud

atlas-cloud/fp8 · fp8

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

BaseTen

baseten/fp4 · fp4

Standard$1.40$4.40$0.14—1.05MYes$5.80ActiveSince

BaseTen

baseten/fp4/us · fp4

Standard$1.40$4.40$0.14—1.05MYes$5.80ActiveSince

Cloudflare

cloudflare · unknown

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Crusoe

crusoe/fp4 · fp4

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Fireworks

fireworks · unknown

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Mistral

mistral/nvfp4 · nvfp4

Standard$1.40$4.40$0.14—1.05MYes$5.80ActiveSince

Mistral

mistral/zdr · nvfp4

Standard$1.40$4.40$0.14—1.05MYes$5.80ActiveSince

Modal

modal · unknown

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Parasail

parasail/fp8 · fp8

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

PrimeIntellect

primeintellect · unknown

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Together

together · unknown

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Venice

venice · unknown

Promo$1.40$4.40$0.26—1MYes$5.80ActiveSince

Z.AI

z-ai/fp8 · fp8

Standard$1.40$4.40$0.26—1.05MYes$5.80ActiveSince

Morph

morph/fp8 · fp8

Standard$0.084$6.00$0.09—1.05MYes$6.084ActiveSince

Mistral

mistral/nvfp4/eu · nvfp4

Standard$1.54$4.84$0.154—1.05MYes$6.38ActiveSince

BaseTen

baseten/fast · fp8

Standard$2.10$6.60$0.21—1.05MYes$8.70ActiveSince

BaseTen

baseten/fast/us · fp8

Standard$2.10$6.60$0.21—1.05MYes$8.70ActiveSince

Fireworks

fireworks/fast · unknown

Standard$2.10$6.60$0.39—1.05MYes$8.70ActiveSince

ModelRun

modelrun/fp4 · fp4

Standard$2.10$6.60$0.40—1.05MYes$8.70ActiveSince

Alibaba

alibaba/fast · unknown

Standard$2.80$8.80$0.56—1MYes$11.60ActiveSince

“—” means no rate is published for that endpoint; it is excluded from estimates, not counted as zero. “Since” is the first record with no rate change observed; “Changed” is the latest observed rate or billing change. Per-request fees: not published for any endpoint here. Status is the upstream operational flag, not a measured uptime.