Singularity Logs

THE MODEL, IN DETAIL / Z.ai (Zhipu AI)

GLM-5.3 (max)

z-ai/glm-5.3Open weightsReasoningmax configuration

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

OpenRouter
Source-linked model intelligenceCatalog added 18 Aug 2026Specifications observed 28 Oct 2026

Specifications and providers describe Z.ai: GLM 5.3. Evaluation scores retain the exact max configuration.

GPQA Diamond

90.9%

Source-reported

Context window

1M

943.7K max output tokens

Input price

$0.0699

USD / million input tokens

Output price

$1.4

USD / million output tokens

Inference providers

37

48 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

Individual benchmark accuracy. Axes represent different tasks, not a composite index.FrontierMath Ti…FrontierMath Ti…GPQA DiamondOTIS Mock AIME …SimpleQA VerifiedFrontierMath Tier 4 v2: 29.3FrontierMath Tiers 1–3 v2: 68.8GPQA Diamond: 90.9OTIS Mock AIME 2024–2025: 91.1SimpleQA Verified: 41Each axis: 0–100% · Individual evaluations

Performance meets price

GPQA Diamond · same published source and version

Higher score · lower cost80$085$2.87590$5.7595$8.625100$11.5Gemini 4 Argon (high) GPQA Diamond: 96.4 Input: $2/M tokensGPT-6 Astra (max) GPQA Diamond: 95.8 Input: $10/M tokensClaude Sonnet 5.5 (max) GPQA Diamond: 95.6 Input: $2/M tokensGLM-5.2 GPQA Diamond: 91.9 Input: $0.0068/M tokensDeepSeek V4 Pro 0813 (max) GPQA Diamond: 91.7 Input: $0.66/M tokensGPT-5.6 Luna (max) GPQA Diamond: 91.6 Input: $0.2/M tokensGPT-5.2 (xhigh) GPQA Diamond: 91.4 Input: $1.75/M tokensClaude Opus 4.8 GPQA Diamond: 91 Input: $5/M tokensDeepSeek V4 Flash 0731 (max) GPQA Diamond: 91 Input: $0.119/M tokensGLM-5.3 (max) GPQA Diamond: 90.9 Input: $0.0699/M tokensGLM-5.3 (max)MiniMax-M3 GPQA Diamond: 90.9 Input: $0.3/M tokensQwen3.7 Max GPQA Diamond: 90.9 Input: $1.475/M tokensKimi K2.6 GPQA Diamond: 90.8 Input: $0.65/M tokensGPT-5.5 (low) GPQA Diamond: 90.7 Input: $5/M tokensClaude Opus 5.5 (max) GPQA Diamond: 90.6 Input: $4/M tokensGLM-5.3-Flash (max) GPQA Diamond: 90.2 Input: $0.15/M tokensInput price · USD / million tokens
Google DeepMindOpenAIAnthropicZ.ai (Zhipu AI)DeepSeekMiniMaxAlibabaMoonshot

In good company

GPQA Diamond · Epoch AI · benchmark data

96.4
Google DeepMind
95.8
OpenAI
95.6
Anthropic
91.9
Z.ai (Zhipu AI)
91.7
DeepSeek
91.6
OpenAI
91.4
OpenAI
91
Anthropic
91
DeepSeek
90.9
This model

Rank #32 in this published cohort. 325 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

5published results
1 evaluation source
Reasoning5 evaluations
CodingAwaiting evidence
Mathematics3 evaluations
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

5 published results
020406080100FrontierMath Tier 4 v2: 29.3% · Epoch AI · independent runs · Epoch AI · benchmark data29.3%FrontierMath Tie…Higher is betterFrontierMath Tiers 1–3 v2: 68.8% · Epoch AI · independent runs · Epoch AI · benchmark data68.8%FrontierMath Tie…Higher is betterGPQA Diamond: 90.9% · Epoch AI · independent runs · Epoch AI · benchmark data90.9%GPQA DiamondHigher is betterOTIS Mock AIME 2024–2025: 91.1% · Epoch AI · independent runs · Epoch AI · benchmark data91.1%OTIS Mock AIME 2…Higher is betterSimpleQA Verified: 41% · Epoch AI · independent runs · Epoch AI · benchmark data41%SimpleQA VerifiedHigher is better

5 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Published benchmark results for GLM-5.3 (max)
BenchmarkScoreVersion & metricSourcePublishedEvidence
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$0.0699per million tokens
Output$1.4per million tokens
Cache read$0.0689per million tokens
Cache write—per million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

$2.099estimated total
Uncached input$0.699
Cached input$0
Output$1.4
Per request$0.0021
Without cache discount$2.099
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

37 providers · 48 routes
Provider routes for GLM-5.3 (max), observed 28 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
WWaferFP4$0.0699$1.4$0.06891M943.7K——100%
RRelaceQuantization not disclosed$0.0703$4.3843$0.07031M131.1K——100%
IInferenceNetFP4$0.08$3.6$0.0761M943.7K——100%
IInferenceNetFP4$0.08$3.6$0.0761M943.7K——100%
RRekaQuantization not disclosed$0.14$2.1$0.1051M262.1K——99.86%
MMakoraFP4$0.14$4.4$0.11M128K——99.64%
WWaferFP4$0.179$1.4$0.1781M943.7K——100%
AAkashMLFP8$0.19$4.4$0.191M131.1K——100%
MMorphFP8$0.203$2.208$0.0691M943.7K——99.74%
DDekaLLMQuantization not disclosed$0.25$2.95$0.181M943.7K——100%
SSail ResearchFP8$0.5$2$0.081M943.7K——100%
SSail ResearchFP8$0.5$2$0.081M943.7K——100%
DDeepInfraFP4$0.5625$2.5$0.1251M131.1K——99.52%
TTenstorrentFP8$0.6$2.5$0.11M131.1K——100%
NNovitaFP8$0.63$1.98$0.1171M131.1K——100%
SSiliconFlowFP8$0.7$2.2$0.131M262.1K——99.91%
GGMICloudFP8$0.7$2.2$0.131M943.7K——100%
PPhalaQuantization not disclosed$0.84$2.64$0.1561M943.7K——100%
DDecartFP4$0.84$2.69$0.191M943.7K——100%
DDigitalOceanQuantization not disclosed$0.91$2.86$0.1691M128K——100%
FFireworksQuantization not disclosed$0.98$3.08$0.1821M943.7K——100%
PPrimeIntellectQuantization not disclosed$0.98$3.08$0.1821M131.1K——100%
AAlibabaQuantization not disclosed$1.19$3.74$0.2381M131.1K——100%
IInceptronFP4$1.2$3.5$0.141M943.7K——99.86%
CCoreWeaveFP8$1.2$4$0.191M943.7K——99.53%
FFriendliQuantization not disclosed$1.26$3.96$0.2341M943.7K——100%
MMistralNVFP4$1.4$4.4$0.141M131.1K——100%
BBaiduFP8$1.4$4.4$0.261M131.1K——100%
BBaseTenFP4$1.4$4.4$0.141M262.1K——100%
MMistralNVFP4$1.4$4.4$0.141M131.1K——100%
NNebiusFP4$1.4$4.4$0.261M921.6K——100%
CCrusoeFP4$1.4$4.4$0.261M943.7K——99.92%
VVeniceQuantization not disclosed$1.4$4.4$0.261M131.1K——100%
TTogetherQuantization not disclosed$1.4$4.4$0.261M943.7K——100%
PParasailFP8$1.4$4.4$0.261M943.7K——99.91%
MModalQuantization not disclosed$1.4$4.4$0.261M943.7K——100%
BBaseTenFP4$1.4$4.4$0.141M262.1K——100%
FFireworksQuantization not disclosed$1.4$4.4$0.261M943.7K——100%
CCloudflareQuantization not disclosed$1.4$4.4$0.261M943.7K——100%
AAtlasCloudFP8$1.4$4.4$0.261M131.1K——100%
ZZ.AIFP8$1.4$4.4$0.261M131.1K——100%
MMistralNVFP4$1.54$4.84$0.1541M131.1K——100%
AAmazon BedrockQuantization not disclosed$1.68$5.28$0.3121M131.1K——75.65%
MModelRunFP4$2.1$6.6$0.41M524.3K——91.1%
FFireworksQuantization not disclosed · priority$2.1$6.6$0.391M943.7K——99.77%
BBaseTenFP8 · priority$2.1$6.6$0.211M262.1K——98.65%
BBaseTenFP8 · priority$2.1$6.6$0.211M262.1K——98.93%
AAlibabaQuantization not disclosed · priority$2.8$8.8$0.561M131.1K——100%

Snapshot observed 28 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput
Waferfp4
Input
$0.0699
Output
$1.4
Relace
Input
$0.0703
Output
$4.3843
InferenceNetfp4
Input
$0.08
Output
$3.6
InferenceNetfp4
Input
$0.08
Output
$3.6
Reka
Input
$0.14
Output
$2.1
Makorafp4
Input
$0.14
Output
$4.4
Waferfp4
Input
$0.179
Output
$1.4
AkashMLfp8
Input
$0.19
Output
$4.4
Morphfp8
Input
$0.203
Output
$2.208
DekaLLM
Input
$0.25
Output
$2.95

Reported availability

Provider availability over the selected observation window

Wafer · FP4100%
Relace100%
InferenceNet · FP4100%
InferenceNet · FP4100%
Reka99.86%
Makora · FP499.64%
Wafer · FP4100%
AkashML · FP8100%
Morph · FP899.74%
DekaLLM100%

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

Wafer · FP41M
Relace1M
InferenceNet · FP41M
InferenceNet · FP41M
Reka1M
Makora · FP41M
Wafer · FP41M
AkashML · FP81M
Morph · FP81M
DekaLLM1M

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

Text
GLM-5.3 (max)Reasoning supported

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningSupported
Tool callingSupported
Tool choiceSupported
Structured outputsSupported
Response formatSupported
Reasoning detailsSupported
Seed controlSupported
Stop sequencesSupported
Prompt cachingSupported
TemperatureSupported

Room to work

Context capacity and completion limits

1Mtotal context tokens
Context window
943.7Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context
1,048,576 tokens
Maximum output
943,718 tokens
Top-provider context
1,048,576 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider routeReasoningToolsStructured outputResponse formatImplicit caching
Wafer · FP4SupportedSupportedSupportedSupportedSupported
RelaceSupportedSupportedNot listedSupportedSupported
InferenceNet · FP4SupportedSupportedSupportedSupportedSupported
InferenceNet · FP4SupportedSupportedSupportedSupportedSupported
RekaSupportedSupportedSupportedSupportedSupported
Makora · FP4SupportedSupportedSupportedSupportedSupported
Wafer · FP4SupportedSupportedSupportedSupportedSupported
AkashML · FP8SupportedSupportedSupportedSupportedSupported
Morph · FP8SupportedSupportedSupportedSupportedSupported
DekaLLMSupportedSupportedSupportedSupportedSupported
Sail Research · FP8SupportedSupportedSupportedSupportedSupported
Sail Research · FP8SupportedSupportedSupportedSupportedSupported
DeepInfra · FP4SupportedSupportedSupportedSupportedSupported
Tenstorrent · FP8SupportedSupportedNot listedNot listedSupported
Novita · FP8SupportedSupportedNot listedSupportedSupported
SiliconFlow · FP8SupportedSupportedNot listedSupportedSupported
GMICloud · FP8SupportedSupportedNot listedSupportedSupported
PhalaSupportedSupportedSupportedSupportedSupported
Decart · FP4SupportedSupportedSupportedSupportedSupported
DigitalOceanSupportedSupportedSupportedSupportedSupported
FireworksSupportedSupportedSupportedSupportedSupported
PrimeIntellectSupportedSupportedSupportedSupportedSupported
AlibabaSupportedSupportedNot listedSupportedSupported
Inceptron · FP4SupportedSupportedNot listedSupportedSupported
CoreWeave · FP8SupportedSupportedSupportedSupportedSupported
FriendliSupportedSupportedSupportedSupportedSupported
Mistral · NVFP4SupportedSupportedSupportedSupportedSupported
Baidu · FP8SupportedSupportedSupportedSupportedSupported
BaseTen · FP4SupportedSupportedSupportedSupportedSupported
Mistral · NVFP4SupportedSupportedSupportedSupportedSupported
Nebius · FP4SupportedSupportedSupportedSupportedSupported
Crusoe · FP4SupportedSupportedSupportedSupportedSupported
VeniceSupportedSupportedSupportedSupportedSupported
TogetherSupportedSupportedSupportedSupportedSupported
Parasail · FP8SupportedSupportedSupportedSupportedSupported
ModalSupportedSupportedSupportedSupportedSupported
BaseTen · FP4SupportedSupportedSupportedSupportedSupported
FireworksSupportedSupportedSupportedSupportedSupported
CloudflareSupportedSupportedSupportedSupportedSupported
AtlasCloud · FP8SupportedSupportedSupportedSupportedSupported
Z.AI · FP8SupportedSupportedNot listedSupportedSupported
Mistral · NVFP4SupportedSupportedSupportedSupportedSupported
Amazon BedrockSupportedSupportedSupportedSupportedNot listed
ModelRun · FP4SupportedSupportedSupportedSupportedSupported
Fireworks · prioritySupportedSupportedSupportedSupportedSupported
BaseTen · priority · FP8SupportedSupportedNot listedNot listedSupported
BaseTen · priority · FP8SupportedSupportedNot listedNot listedSupported
Alibaba · prioritySupportedSupportedNot listedSupportedSupported

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer
Z.ai (Zhipu AI)
Exact identity
glm-5.3_max
Subject
Model Configuration
Access
Open weights
License
Not disclosed
Parameters
Not disclosed
Tokenizer
Other
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
Yes
Reasoning by default
Enabled
Published configuration
max
Supported reasoning efforts
max, high, low
Default reasoning effort
max
API parameters
21
Provider moderation
No
Quantization variants
fp4, fp8, nvfp4

Dates & limits

Catalog added
18 Aug 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
28 Oct 2026
Providers observed
28 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
z-ai/glm-5.3-20260816

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

frequency_penaltySupported · default not supplied
include_reasoningSupported · default not supplied
logit_biasSupported · default not supplied
logprobsSupported · default not supplied
max_tokensSupported · default not supplied
min_pSupported · default not supplied
parallel_tool_callsSupported · default not supplied
presence_penaltySupported · default not supplied
reasoningSupported · default not supplied
reasoning_effortSupported · default not supplied
repetition_penaltySupported · default not supplied
response_formatSupported · default not supplied
seedSupported · default not supplied
stopSupported · default not supplied
structured_outputsSupported · default not supplied
temperatureDefault: 1
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
top_kSupported · default not supplied
top_logprobsSupported · default not supplied
top_pDefault: 0.95

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "z-ai/glm-5.3",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ],
      "reasoning": {
        "effort": "max"
      }
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The observation trail

Recorded events, in chronological order

Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

Provider routes observed

48 inference routes in this snapshot.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

Published observation history for GLM-5.3 (max)
ObservedBenchmarkScoreVersionSourceVerification
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does GLM-5.3 (max) cost?

Catalog starting rates are $0.0699 per million input tokens and $1.4 per million output tokens. Cache-read pricing is $0.0689 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

1,048,576 tokens in the catalog context window. The catalog lists a maximum of 943,718 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 28 Oct 2026. Provider routes were observed on 28 Oct 2026. Missing measurements are not estimated or treated as zero.

KEEP EXPLORING

More from Z.ai (Zhipu AI).

Explore related identities from the same developer, or take them into a side-by-side comparison.

THE RIGHT MODEL STARTS WITH THE RIGHT CONTEXT.

Put the details side by side.

Explore the trade-offs in a direct model comparison.

Compare GLM-5.3 (max)
Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard
GLM-5.3 (max) — Singularity Logs