Inference
EN
Z.AI

GLM-4.5

GLM-4.5 is a standard model from Z.AI. 8 benchmarks count toward its index, in 4 categories.

  • Open weights
  • Standard
  • Input: text
  • Released 2025-07
  • Retires 31 Dec 2026
RankedEnough results for an index.
IndexAll categories, out of 100.45.7±9.2Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.25/sMedian 67/s
First tokenSeconds to the first output token.4.1 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.60Median $0.60
Output / 1MUS dollars per 1M output tokens.$2.20Median $2.55
ContextMaximum tokens in one request.131KMedian 262K
EloLMArena rating and rank.1430±5 #95Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
z-ai/glm-4.5
Max outputMaximum output tokens per request.
98K
Knowledge cutoffLast date of training data.
31 Dec 2024
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
No
Cache read / 1MUS dollars per 1M cached tokens.
$0.11
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
31 Dec 2026

Where to run

APIs that serve this model.
3 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterDeprecatedRouter$0.60$2.20131K
Z.AIMaker$0.60$2.20131K
Zhipu AIMaker$0.60$2.20131K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Run locally

358.34B parameters
16-bit
753.5 GB
8-bit
400.8 GB
4-bit
229.1 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy needs more than 128 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted48.1—
CodingCode writing and repair.3 counted43.3168 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted45.1167 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.2 counted48.493 / 168

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH 500Math94.0% ±1.114 / 59
AIMEMath86.7% ±1.331 / 95
Terminal-Bench 1.0Agentic41.3% ±5.518 / 47
SWE-bench Verified · swebench.comCoding54.2%18 / 46
SWE-bench Verified · SWE-bench/experimentsCoding59.2%32 / 65
MMLU ProKnowledge81.2% ±0.482 / 135
GPQA Diamond · Vals AIKnowledge72.2% ±2.388 / 135
LiveCodeBenchCoding67.4% ±1.196 / 142
IOI v1Coding2.9% ±1.053 / 61
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
TaxEval v2Finance72.4% ±0.962 / 143
CorpFin v2Finance61.0% ±1.060 / 131
MGSMMultilingual90.8% ±1.837 / 74
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
MedQAHealthcare90.0% ±0.350 / 95
LegalBenchLegal75.6% ±0.5114 / 149

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedSWE-bench teamNo licence statedmodels.devMIT

History

5 releases
Index46.8 → 45.7
23 Oct 202612 Nov 2026
Output / 1M$2.20 → $2.20
23 Oct 202612 Nov 2026

Questions

How much does GLM-4.5 cost?
$0.60 per 1M input tokens, $2.20 per 1M output tokens.
How good is GLM-4.5?
Its index is 45.7 out of 100. That is place 176 of 283 ranked models.
What is GLM-4.5 best at?
Math: 48.4 out of 100, place 93 of 168.
How fast is GLM-4.5?
25 output tokens per second, 4.1 s to the first token.
What is the context window of GLM-4.5?
131K tokens.
Is GLM-4.5 open source?
Yes. Its weights are published.
When was GLM-4.5 released?
July 2025.

Badge

GLM-4.5 on Inference360: place 176 of 283, index 45.7
HTML
<a href="https://inference360.ai/models/glm-4-5"><img src="https://inference360.ai/badges/glm-4-5.svg" alt="GLM-4.5 on Inference360: place 176 of 283, index 45.7" height="20"></a>
Markdown
[![GLM-4.5 on Inference360: place 176 of 283, index 45.7](https://inference360.ai/badges/glm-4-5.svg)](https://inference360.ai/models/glm-4-5)

Compare with

Grok 4 Fast (Reasoning)45.3Qwen3 Max45.0GLM-4.641.8

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Z.AI

All models
GLM-4.5-AirUnrankedGLM 4.5VUnrankedGLM-4.641.8GLM 4.6VUnrankedGLM-4.750.0