← Model list

GLM-5-Turbo

zhipuai·zhipuai/glm-5-turbo·GA·Closed·glm series

Faster GLM-5 lane for coding agents that need lower latency

At a glance
Official price$1.20 / $4.00 per 1M
Cache read $0.24 · Z.AI
Lowest paid$0.72 / $3.20
302.AI Gateway · 1.7× spread
2 more $0 channels
Context200,000
⚠ Providers report 200,000–202,800; the table below is authoritative
Output limit131,072
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-01-01
Released / updated2026-03-16 / 2026-03-16

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence39.1
Value29
Coding
Agentic
Output speed
TTFT
Value formulaIQ 39.1 ÷ min blended $1.340 = 29

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

Available at 17 providers15 with public prices · 2 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Zhipu AI Coding PlanGatewaySubscription$0$0200,000131,072
Z.AI Coding PlanGatewaySubscription$0$0200,000131,072
302.AIGateway$0.72$3.20200,000131,072
ZenMuxGateway$0.88$3.48200,000128,000
CrossModelGateway$0.90
tiered >32K: $1.10
$3.70$0.18$0.90200,000128,000
CortecsGateway$1.19$3.96$0.296$1.54202,752202,752
NanoGPTGateway$1.20$4.00$0.24202,800131,072
ImpossiblGateway$1.20$4.00$0.24200,000131,072
OpenRouterGateway$1.20$4.00$0.24202,752131,072
Z.AIOfficialFirst-party$1.20$4.00$0.24$0200,000131,072

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

1CrossModel$278.60
2302.AI$304.00
3NanoGPT$324.80
4Impossibl$324.80
5OpenRouter$324.80
6Z.AI · Official$324.80

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.

Switch to CrossModel to save $46.20/mo (14%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

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

Reasoning control

Toggle (on / off)effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max

4 / 17 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.00$02026-08-052026-08-132026-08-05 · Input list $1.202026-08-06 · Input list $1.202026-08-07 · Input list $1.202026-08-08 · Input list $1.202026-08-09 · Input list $1.202026-08-10 · Input list $1.202026-08-11 · Input list $1.202026-08-12 · Input list $1.202026-08-13 · Input list $1.202026-08-05 · Output list $4.002026-08-06 · Output list $4.002026-08-07 · Output list $4.002026-08-08 · Output list $4.002026-08-09 · Output list $4.002026-08-10 · Output list $4.002026-08-11 · Output list $4.002026-08-12 · Output list $4.002026-08-13 · Output list $4.002026-08-05 · Min blended $1.342026-08-06 · Min blended $1.342026-08-07 · Min blended $1.342026-08-08 · Min blended $1.342026-08-09 · Min blended $1.342026-08-10 · Min blended $1.342026-08-11 · Min blended $1.342026-08-12 · Min blended $1.342026-08-13 · Min blended $1.34