Model

GLM-5.2

Name: GLM-5.2
Brand: zhipuai

Open flagship GLM for long-horizon coding agents and million-token context work

86 providers · 103 listingsreleased Jun 13, 2026open weightsbeta

$0.3

lowest input /M · CrofAI

$1.05

lowest output /M · CrofAI

1.05M

context window

1.05M

max output

Compare providers (sorted by listed input price)

75 of 86 providers publish a price for GLM-5.2. The cheapest full-context option is CrofAI at $0.3/$1.05 per M — 77% below Zhipu AI's own price. Listed prices span 7.2× for identical weights.

			Cache read /M	Cache write /M		Capabilities
CrofAI glm-5.2	$0.3	$1.05	$0.05	—	1M	reasoningtoolsstructuredno vision	Jun 13, 2026
NanoGPTvariant z-ai/glm-5.2	$0.42	$1.32	$0.078	—	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
SCX.ai GLM-5.2	$0.55	$1.78	$0.111	—	1M	reasoningtoolsstructuredno vision	Jun 13, 2026
Ambientvariant z-ai/glm-5.2	$0.6	$2	$0.15	$0	203K	reasoningtoolsstructuredno vision	Jun 13, 2026
OpenRouter z-ai/glm-5.2	$0.683	$2.15	$0.127	—	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
DigitalOcean glm-5.2	$0.7	$2.20	$0.105	—	262K	reasoningtoolsstructuredno vision	Jun 13, 2026
Inceptron zai-org/GLM-5.2	$0.71	$2.35	$0.12	$0	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
Deep Infra zai-org/GLM-5.2	$0.75	$2.40	$0.14	—	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
Weights & Biases zai-org/GLM-5.2	$0.76	$2.42	$0.14	—	1.05M	reasoningtoolsstructuredno vision	Jun 16, 2026
LLM Gatewayvariant scx-ai-gp/glm-5.2	$0.8	$2.55	$0.16	—	1M	reasoningtoolsno structuredno vision	Jun 13, 2026
LLM Gatewayvariant runware/glm-5.2	$0.8	$2.55	$0.16	—	1.02M	reasoningtoolsno structuredno vision	Jun 13, 2026
routing.run glm-5.2	$0.8	$2.40	—	—	200K	reasoningtoolsstructuredno vision	Jun 13, 2026
Requestyvariant glm-5.2	$0.8	$2.55	$0.16	—	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
Vercel AI Gateway zai/glm-5.2	$0.8	$2.55	$0.16	—	1M	reasoningtoolsstructuredno vision	Jun 13, 2026
DevPass (LLM Gateway)variant glm-5.2	$0.8	$2.55	$0.16	$0	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
Vultr zai-org/GLM-5.2-FP8	$0.85	$3.10	—	—	393K	reasoningtoolsstructuredno vision	Jun 13, 2026
Lilac zai-org/glm-5.2	$0.9	$3	$0.27	—	524K	reasoningtoolsstructuredno vision	Jun 13, 2026
GMI Cloud zai-org/GLM-5.2-FP8	$0.979	$3.08	$0.182	—	1M	reasoningtoolsstructuredno vision	Jun 13, 2026
ai& zai-org/glm-5.2	$1	$4	—	—	1.05M	reasoningtoolsstructuredno vision	Jun 13, 2026
Merge Gateway zai/glm-5.2	$1.05	$3.30	$0.195	—	1M	reasoningtoolsno structuredno vision	Jun 13, 2026

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.3unchanged
Best output /M: $1.05unchanged
Provider coverage: 103; 98 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![GLM-5.2 price](https://www.vaanalytics.in/badge/zhipuai/glm-5.2.svg)

https://www.vaanalytics.in/badge/zhipuai/glm-5.2.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

contextvia kilo · Sep 14, 2026
- context: 203K → 1.05M tokens
- output: 182K → 131K tokens
repricedvia openrouter · Sep 14, 2026
- output: 182K → 131K tokens
- input: $0.6 → $0.683
- output: $2 → $2.15
- cache_read: $0.15 → $0.127
repricedvia openrouter · Sep 13, 2026
- output: 131K → 182K tokens
- input: $0.966 → $0.6
- output: $3.04 → $2
- cache_read: $0.193 → $0.15
new modelvia llmgateway-providers · Sep 13, 2026
contextvia kilo · Sep 13, 2026
- context: 1M → 203K tokens
- output: 131K → 182K tokens
repricedvia ofox · Sep 11, 2026
- input: $0.98 → $1.40
- output: $3.08 → $4.40
- cache_read: $0.182 → $0.26

Benchmarks

SWE-Bench Pro ↗(resolve rate)report ↗Unclassified source62.1
Terminal-Bench ↗(success rate)report ↗Unclassified source82.7
FrontierSWE ↗(dominance)report ↗Unclassified source74.4
Humanity's Last Exam ↗(accuracy)report ↗Unclassified source40.5
Humanity's Last Exam ↗(accuracy)report ↗Unclassified source54.7
CritPt(accuracy)report ↗Unclassified source20.9
AIME(accuracy)report ↗Unclassified source99.2
HMMT(accuracy)report ↗Unclassified source94.4
HMMT(accuracy)report ↗Unclassified source92.5
IMOAnswerBench(accuracy)report ↗Unclassified source91
GPQA Diamond ↗(accuracy)report ↗Unclassified source91.2
NL2Repo(resolve rate)report ↗Unclassified source48.9
DeepSWE(resolve rate)report ↗Unclassified source46.2
Program Bench(score)report ↗Unclassified source63.7
Terminal-Bench ↗(success rate)report ↗Unclassified source81
PostTrainBench(score)report ↗Unclassified source34.3
SWE Marathon ↗(resolve rate)report ↗Unclassified source13
MCP Atlas(score)report ↗Unclassified source76.8
Tool-Decathlon(score)report ↗Unclassified source48.2

Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.

Weights

Permissivemit753B params

Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.