FindCostShortlistChangesModels
← All tracked models

Z.ai

GLM 5.1 API prices by provider

z-ai/glm-5.1

14 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
14 / 14
Lowest at 1M in + 1M out
$4.06
Chutes · standard tier
Context up to
205K
Latest price change
None yet
Rates unchanged since first record 2026-09-29
GLM 5.1 endpoint prices per million tokens
Provider · routeTierInput / 1MOutput / 1MCache readCache writeContextTools1M + 1MStatusPrice since

Baidu

baidu/fp8 · fp8

Promo$0.9646$3.0316$0.1791—203KYes$3.9962ActiveSince

StreamLake

streamlake/fp8 · fp8

Promo$0.966$3.036$0.1794—200KYes$4.002ActiveSince

Chutes

chutes/fp8 · fp8

Standard$0.98$3.08$0.098—203KYes$4.06ActiveSince

DeepInfra

deepinfra/fp4 · fp4

Standard$1.05$3.50$0.205—203KYes$4.55ActiveSince

SiliconFlow

siliconflow/fp8 · fp8

Standard$1.19$3.74$0.60—205KYes$4.93ActiveSince

AtlasCloud

atlas-cloud/fp8 · fp8

Standard$1.26$3.96$0.234—203KYes$5.22ActiveSince

Phala

phala · unknown

Standard$1.21$4.20$0.60—203KYes$5.41ActiveSince

Alibaba

alibaba/fp8 · fp8

Standard$1.33$4.18$0.247—203KYes$5.51ActiveSince

Novita

novita/fp8 · fp8

Standard$1.38$4.40$0.26—205KYes$5.78ActiveSince

Friendli

friendli · unknown

Standard$1.40$4.40$0.26—203KYes$5.80ActiveSince

GMICloud

gmicloud/fp8 · fp8

Standard$1.40$4.40$0.26—203KNot declared$5.80ActiveSince

Nebius

nebius/fp8 · fp8

Standard$1.40$4.40——203KYes$5.80ActiveSince

Z.AI

z-ai/fp8 · fp8

Standard$1.40$4.40$0.26—203KYes$5.80ActiveSince

Venice

venice/fp8 · fp8

Promo$1.4014$4.4044$0.2603—200KYes$5.8058ActiveSince

“—” 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.