← Model list

GLM-4.5

zhipuai·zhipuai/glm-4.5·GA·Open weights·glm series

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

At a glance
Official price$0.60 / $2.20 per 1M
Cache read $0.11 · Z.AI
Lowest paid$0.286 / $1.14
302.AI Gateway · 2.1× spread
1 more $0 channels
Context131,072
⚠ Providers report 128,000–131,072; the table below is authoritative
Output limit98,304
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-04
Released / updated2025-07-28 / 2025-07-28

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

Intelligence19.7
Value39
Coding
Agentic
Output speed
TTFT
Value formulaIQ 19.7 ÷ min blended $0.500 = 39

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

Available at 18 providers16 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
ModelScope
ZhipuAI/GLM-4.5
CloudFree131,07298,304
302.AIGateway$0.286$1.14131,07298,304
NanoGPTGateway$0.30$1.30$0.15128,00065,536
ZenMuxGateway$0.35$1.54$0.07128,00064,000
OrcaRouterGateway$0.60$2.20$0.11$0131,07298,304
Hugging Face
zai-org/GLM-4.5
Cloud$0.60$2.20131,07298,304
ImpossiblGateway$0.60$2.20$0.11131,07298,304
Jiekou.AIGateway$0.60$2.20131,07298,304
OpenRouterGateway$0.60$2.20$0.11131,07298,304
Z.AIOfficialFirst-party$0.60$2.20$0.11$0131,07298,304

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

1NanoGPT$107.00
2ZenMux$113.40
3302.AI$114.30
4OrcaRouter$171.20
5Impossibl$171.20
6OpenRouter$171.20
7Z.AI · Official$171.20

1 more channels offer $0 (ModelScope); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to NanoGPT to save $64.20/mo (37%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index26.3indexSource ↗
SciCode34.8percent correctSource ↗
Terminal-Bench Hard22success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

Toggle (on / off)effort = noneeffort = high

3 / 18 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.20$02026-08-052026-08-132026-08-05 · Input list $0.602026-08-06 · Input list $0.602026-08-07 · Input list $0.602026-08-08 · Input list $0.602026-08-09 · Input list $0.602026-08-10 · Input list $0.602026-08-11 · Input list $0.602026-08-12 · Input list $0.602026-08-13 · Input list $0.602026-08-05 · Output list $2.202026-08-06 · Output list $2.202026-08-07 · Output list $2.202026-08-08 · Output list $2.202026-08-09 · Output list $2.202026-08-10 · Output list $2.202026-08-11 · Output list $2.202026-08-12 · Output list $2.202026-08-13 · Output list $2.202026-08-05 · Min blended $0.502026-08-06 · Min blended $0.502026-08-07 · Min blended $0.502026-08-08 · Min blended $0.502026-08-09 · Min blended $0.502026-08-10 · Min blended $0.502026-08-11 · Min blended $0.502026-08-12 · Min blended $0.502026-08-13 · Min blended $0.50