FindCostShortlistChangesModels
← All tracked models

Z.ai

GLM 5.3 Flash API prices by provider

z-ai/glm-5.3-flash

31 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
32 / 33
Lowest at 1M in + 1M out
$0.5005
AtlasCloud · standard tier
Context up to
1.31M
Latest price change
2026-09-29
Checked through 2026-09-29
GLM 5.3 Flash endpoint prices per million tokens
Provider · routeTierInput / 1MOutput / 1MCache readCache writeContextTools1M + 1MStatusPrice since

InferenceNet

inference-net/fp4 · fp4

Promo$0.045$0.14$0.01—1.05MYes$0.185ActiveSince

DeepInfra

deepinfra/fp4 · fp4

Promo$0.075$0.25$0.015—1.05MYes$0.325ActiveSince

Novita

novita/fp8 · fp8

Promo$0.084$0.28$0.0168—1.05MYes$0.364ActiveSince

GMICloud

gmicloud/fp8 · fp8

Promo$0.09$0.30$0.018—1.05MYes$0.39ActiveSince

AtlasCloud

atlas-cloud/fp8 · fp8

Standard$0.1155$0.385$0.0231—1.05MYes$0.5005ActiveSince

Relace

relace · unknown

Standard$0.025$0.50$0.025—1.05MYes$0.525ActiveSince

Decart

decart/fp4 · fp4

Promo$0.1275$0.425$0.0255—1.05MYes$0.5525ActiveSince

Phala

phala/fp8 · fp8

Promo$0.1275$0.425$0.0255—1.05MYes$0.5525ActiveSince

StreamLake

streamlake/fp8 · fp8

Promo$0.1275$0.425$0.0255—1.02MYes$0.5525ActiveSince

Near AI

near-ai/fp8 · fp8

Promo$0.132$0.44$0.0308—1.05MYes$0.572ActiveSince

Io Net

io-net/fp8 · fp8

Promo$0.138$0.46$0.0276—262KYes$0.598ActiveSince

Inceptron

inceptron/fp8 · fp8

Standard$0.15$0.45$0.06—1.05MYes$0.60ActiveSince

Sail Research

sail-research/fp8 · fp8

Standard$0.045$0.60$0.0285—1.05MYes$0.645ActiveSince

Sail Research

sail-research/us · fp8

Standard$0.045$0.60$0.0285—1.05MYes$0.645ActiveSince

BaseTen

baseten/fp8 · fp8

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

CoreWeave

coreweave/nvfp4 · nvfp4

Standard$0.15$0.50$0.05—1.05MYes$0.65ActiveSince

Crusoe

crusoe/fp4 · fp4

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

DigitalOcean

digitalocean · unknown

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Fireworks

fireworks · unknown

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Friendli

friendli · unknown

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Modal

modal/nvfp4 · nvfp4

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Parasail

parasail/fp8 · fp8

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Reka

reka · unknown

Standard$0.15$0.50$0.03—262KYes$0.65ActiveSince

SiliconFlow

siliconflow/fp8 · fp8

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Together

together · unknown

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Venice

venice · unknown

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Z.AI

z-ai/fp8 · fp8

Standard$0.15$0.50$0.03—1.05MYes$0.65ActiveSince

Morph

morph/fp8 · fp8

Standard$0.1531$0.5358$0.04—1.05MYes$0.6889ActiveSince

NextBit

nextbit/fp8 · fp8

Standard$0.165$0.55$0.033—1.05MYes$0.715ActiveSince

Fireworks

fireworks/us · unknown

Standard$0.225$0.75$0.045—1.05MYes$0.975ActiveSince

Wafer

wafer · unknown

Standard$0.75$0.27$0.03—1.05MYes$1.02ActiveChanged

Cloudflare

cloudflare · unknown

Standard$0.30$1.00$0.03—1.31MYes$1.30ActiveSince

OpenInference

open-inference/fp4 · fp4

Standard$0.02$0.30$0.01—1.05MYes$0.32UnavailableSince

“—” 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.