Textby Z.AI

GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

  • By price it is in the pricier half of the 347 text models GenMagic runs (253rd cheapest).
  • It scores 34 on the Artificial Analysis Intelligence Index, 31st of the 120 text models with a score.
  • Among the models GenMagic runs, it places in the top 10 on 3 of its 51 benchmarks: 4th of 27 on SWE-bench Verified, 6th of 11 on PostTrainBench, 9th of 25 on Design Arena: Game Dev (agentic).
  • It was listed on Jun 16, 2026.

Data last changed Nov 11, 2026 · tracked since Oct 29, 2026 · Every model change

Try GLM 5.2

Generate with GLM 5.2 right here. Verify your email to start with free credits.

Try

Specifications

Context window

1M tokens

Max output

944K tokens

Input price

$0.011 / 1M tokens

Output price

$10.20 / 1M tokens

Cached input

$0.009 / 1M tokens

Benchmarks

How GLM 5.2 scores on public benchmarks. Each card links to the benchmark explainer and to the original source.

38.4

source date 2026-11-10
Source: openrouter

68.8

source date 2026-11-10
Source: openrouter

34

source date 2026-09-18
Source: openrouter
AIMEMathematics

28.9%± 6.8

nonesource date 2026-08-10
Source: epoch
APEX-AgentsAgentic & Tool Use

45.2%

unknown
Source: epoch
ARC-AGI-1Reasoning & Knowledge

77%

unknown
Source: epoch
ARC-AGI-2Reasoning & Knowledge

22.8%

unknown
Source: epoch
Chess PuzzlesReasoning & Knowledge

22%± 4.2

maxsource date 2026-10-14
Source: epoch
Design Arena: 3DDesign & Generation

1271 Elo

Source: designarena
Design Arena: CodeDesign & Generation

1280 Elo

Source: designarena
Design Arena: SVGDesign & Generation

1204 Elo

Source: designarena
DeepSWECoding

43.8%

max; Reasoning effort: max; Harness: mini-swe-agent
Source: epoch
DTBenchReasoning & Knowledge

93.6%

max
Source: epoch

9.5

maxsource date 2026-06-29
Source: epoch

24.5

none; Reasoning effort: none; Harness: mini-swe-agent
Source: epoch

29.3%± 7.2

maxsource date 2026-06-19
Source: epoch

42.5%± 2.9

nonesource date 2026-08-29
Source: epoch
GPQA DiamondReasoning & Knowledge

84.9%± 1.6

source date 2026-10-31
Source: openrouter
LMArena (Coding)Instruction & Preference

1488 Elo

maxsource date 2026-11-09
Source: lmarena
LMArena: Creative WritingInstruction & Preference

1460 Elo

maxsource date 2026-11-09
Source: lmarena
LMArena: Hard PromptsInstruction & Preference

1481 Elo

maxsource date 2026-11-09
Source: lmarena

1479 Elo

maxsource date 2026-11-09
Source: lmarena
LMArena: MathMathematics

1489 Elo

maxsource date 2026-11-09
Source: lmarena
LMArena: Multi-TurnInstruction & Preference

1470 Elo

maxsource date 2026-11-09
Source: lmarena
LMArena (Overall)Instruction & Preference

1469 Elo

maxsource date 2026-11-09
Source: lmarena
LMCAReasoning & Knowledge

45.8

max
Source: epoch

36.7

maxsource date 2026-10-21
Source: epoch
Mystery Game PuzzlesReasoning & Knowledge

15%± 3.6

mediumsource date 2026-08-27
Source: epoch
PostTrainBenchAgentic & Tool Use

31.7

max; Scaffold: Claude Code
Source: epoch
ProofBenchMathematics

35%± 4.8

max; Reasoning effort: max
Source: epoch
SciCodeCoding

51.2%

max
Source: epoch
SimpleBenchReasoning & Knowledge

58.8%

unknown
Source: epoch
SimpleQA VerifiedReasoning & Knowledge

34.2%± 1.5

maxsource date 2026-08-27
Source: epoch

78.7%± 1.9

maxsource date 2026-06-25
Source: epoch
tau-bench (Airline)Agentic & Tool Use

71.5%± 3.2

source date 2026-10-31
Source: openrouter
WebDev ArenaAgentic & Tool Use

1593 Elo

max
Source: epoch
WeirdMLCoding

70.1%± 0.0

max
Source: epoch

Compare against every model in the full benchmark matrix.

Capabilities

Reasoning

Works through multi-step problems before answering, for harder tasks.

Tool use

Can call functions and tools, enabling agentic and structured workflows.

Structured output

Returns validated JSON that conforms to a schema you define.

Use GLM 5.2 through the API

The model id is z-ai/glm-5.2. Requests bill your GenMagic balance at the price above, and each response reports what it cost.

curl
curl https://genmagic.co/api/v1/chat/completions \
  -H "Authorization: Bearer $GENMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.2",
    "messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
  }'
Python (openai SDK)
from openai import OpenAI

client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")

resp = client.chat.completions.create(
    model="z-ai/glm-5.2",
    messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)

From an AI agent, call generate_text with "model": "z-ai/glm-5.2" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.

Use GLM 5.2 in n8n

  1. In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
  2. Set Resource to Text and Operation to Generate.
  3. In Model Name or ID, pick Z.ai: GLM 5.2, or enter z-ai/glm-5.2 as an expression.
  4. Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.

Ready-to-import workflows that already use the node are on GenMagic for n8n.

Similar-priced text models from other providers

Other text models GenMagic runs at a comparable price, on the same balance and API key.

ModelProviderPriceContext
Z.ai: GLM 5.2 (this model)Z.AI$0.011 in / $10.20 out per 1M tokens1M
Writer: Palmyra X5Writer$0.90 in / $9.00 out per 1M tokens1M
OpenAI: GPT-6.1 Terra ProOpenAI$1.50 in / $7.50 out per 1M tokens1.1M
Anthropic: Claude Haiku 4.5Anthropic$1.50 in / $7.50 out per 1M tokens200K
Qwen: Qwen3.7 MaxQwen$2.21 in / $6.64 out per 1M tokens1M
SpaceXAI: Grok 4.7xAI$3.00 in / $9.00 out per 1M tokens500K

Compare GLM 5.2

More from Z.AI

All 19 Z.AI models

Price and listing history

Every change GenMagic has recorded for GLM 5.2 since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.

DateChangeBeforeAfter
Nov 11, 2026Price up 17%$0.009 in / $10.20 out per 1M tokens$0.011 in / $10.20 out per 1M tokens
Nov 1, 2026Price up 36%$0.0066 in / $7.70 out per 1M tokens$0.009 in / $10.20 out per 1M tokens

Where these figures come from

  • Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
  • Specs and description: as Z.AI publishes them (model card on Hugging Face), checked daily.
  • Benchmarks: 51 scores from Artificial Analysis and OpenRouter, Epoch AI, Design Arena, LMArena, re-read daily. Each score above links to its source.
  • Changes: the data on this page last changed on Nov 11, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.

Generate with GLM 5.2 today

One GenMagic plan unlocks GLM 5.2 and every other model across text, image, audio, and video.