← Model list

GLM-5.3

zhipuai·zhipuai/glm-5.3-2·GA·Closed·glm series·NEW

Flagship GLM model for long-horizon coding, agents, and complex project delivery

At a glance
Reference price$1.75 / $5.50 per 1M
Cache read $0.325 · Venice AI
Lowest paid$0.70 / $2.20
Merge Gateway Gateway · 2.5× spread
2 more $0 channels
Context1,000,000
⚠ Providers report 1,000,000–1,048,576; the table below is authoritative
Output limit131,072
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
Text
Knowledge cutoff
Released / updated2026-08-14 / 2026-08-14

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier max

Intelligence59.5
Value55
Coding74.8
Agentic59.1
Output speed85 tok/s
TTFT1.88 s
Cost per task$0.6829
Value formulaIQ 59.5 ÷ min blended $1.075 = 55

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 15 providers13 with public prices · 2 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Zhipu AI Coding Plan
glm-5.3
GatewaySubscription$0$01,000,000131,072
Z.AI Coding Plan
glm-5.3
GatewaySubscription$0$01,000,000131,072
Merge Gateway
zai/glm-5.3
Gateway$0.70$2.20$0.131,000,000131,072
Ofox
z-ai/glm-5.3
Gateway$1.26$3.96$0.2341,000,000131,072
Requesty
glm-5.3
Gateway$1.26$3.96$0.2341,000,000128,000
Vivgrid
glm-5.3
Gateway$1.20$4.20$0.261,000,000131,072
CrossModel
z-ai/glm-5.3
Gateway$1.20$4.40$0.30$1.201,000,000128,000
OpenRouter
z-ai/glm-5.3
Gateway$1.40$4.40$0.261,048,576131,072
OpenCode Go
glm-5.3
Gateway$1.40$4.40$0.261,000,000131,072
EmpirioLabs AI
glm-5-3
Gateway$1.40$4.40$1.401,000,000131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Merge Gateway$181.60
2Ofox$326.88
3Requesty$326.88
4Vivgrid$337.20
5CrossModel$352.00
6OpenRouter$363.20

2 more channels offer $0 (Zhipu AI Coding Plan, Z.AI Coding Plan); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = loweffort = higheffort = maxeffort = noneeffort = mediumbudget_tokens

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$5.50$02026-08-162026-08-212026-08-16 · Input list $1.402026-08-18 · Input list $1.402026-08-19 · Input list $1.752026-08-20 · Input list $1.752026-08-21 · Input list $1.752026-08-16 · Output list $4.402026-08-18 · Output list $4.402026-08-19 · Output list $5.502026-08-20 · Output list $5.502026-08-21 · Output list $5.502026-08-16 · Min blended $2.152026-08-18 · Min blended $1.952026-08-19 · Min blended $1.952026-08-20 · Min blended $1.942026-08-21 · Min blended $1.07