Enterprise DNAEnterprise DNA
Z.ai (Zhipu) logo

Models · Best coding

GLM 5.3

by Z Ai

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

Visit Z Ai ↗

Our verdict

Not reviewed yet

We have not reviewed GLM 5.3 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

Notes

GLM 5.3 is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.070 per million tokens
Checked OpenRouter models API
Output price
$1.40 per million tokens
Checked OpenRouter models API
Price on akashml
$0.190 per million cached input tokens
Checked OpenRouter models API
Price on akashml
$0.190 per million input tokens
Checked OpenRouter models API
Price on akashml
$4.40 per million output tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.312 per million cached input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$1.68 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$5.28 per million output tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.260 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
90.9% (for 14 Aug 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
68.8% (for 14 Aug 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
41% (for 14 Aug 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `z-ai/glm-5.3`.

  • openrouter · z-ai/glm-5.3 · Docs

OpenRouter id: z-ai/glm-5.3

Price

What GLM 5.3 costs, over time

Input price

$1.40 to $0.070

US dollars per million input tokens. 3 Sept 2026 to 7 Nov 2026, 41 days.

Source: OpenRouter models API. Checked .

Output price

$4.40 to $1.40

US dollars per million output tokens. 3 Sept 2026 to 7 Nov 2026, 41 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
akashmlCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
akashmlInput$0.190 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
akashmlOutput$4.40 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockCached input$0.312 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockInput$1.68 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockOutput$5.28 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudCached input$0.260 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$1.40 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$4.40 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
baiduCached input$0.260 per million cached input tokensSince 7 Nov 20263 changesOpenRouter models API
baiduInput$1.40 per million input tokensSince 7 Nov 20263 changesOpenRouter models API
baiduOutput$4.40 per million output tokensSince 7 Nov 20263 changesOpenRouter models API
basetenCached input$0.140 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenInput$1.40 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenOutput$4.40 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareCached input$0.130 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
cloudflareInput$0.700 per million input tokensSince 7 Nov 20261 changeOpenRouter models API
cloudflareOutput$2.20 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
coreweaveCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveInput$0.750 per million input tokensSince 7 Nov 20261 changeOpenRouter models API
coreweaveOutput$3.00 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
crusoeCached input$0.260 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeInput$1.40 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeOutput$4.40 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
decartCached input$0.100 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
decartInput$0.560 per million input tokensSince 7 Nov 20261 changeOpenRouter models API
decartOutput$1.78 per million output tokensSince 7 Nov 20264 changesOpenRouter models API
deepinfraCached input$0.125 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.563 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmCached input$0.150 per million cached input tokensSince 30 Oct 20261 changeOpenRouter models API
dekallmInput$0.180 per million input tokensSince 30 Oct 20261 changeOpenRouter models API
dekallmOutput$2.95 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.169 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.910 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$2.86 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
fireworksCached input$0.182 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
fireworksInput$0.980 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
fireworksOutput$3.08 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
friendliCached input$0.234 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
friendliInput$1.26 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
friendliOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.130 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.700 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$2.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
inceptronCached input$0.140 per million cached input tokensSince 26 Oct 20261 changeOpenRouter models API
inceptronInput$1.00 per million input tokensSince 7 Nov 20263 changesOpenRouter models API
inceptronOutput$4.90 per million output tokensSince 7 Nov 20265 changesOpenRouter models API
inference-netCached input$0.076 per million cached input tokensSince 1 Nov 20262 changesOpenRouter models API
inference-netInput$0.080 per million input tokensSince 1 Nov 20262 changesOpenRouter models API

Usage

How much GLM 5.3 is used

Tokens served a day

370.7B to 417.5B

tokens a day on OpenRouter. 19 Sept 2026 to 7 Nov 2026, 50 readings.

Source: OpenRouter model activity (741 of 741 series). Checked .

Scores

How GLM 5.3 scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index31.7indexAs of 7 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index74.8indexAs of 7 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index53.1indexAs of 7 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,476EloAs of 7 Nov 2026LMArena (CC-BY-4.0), published 2026-11-06
LMArena web development rating (Elo)1,621EloAs of 7 Nov 2026LMArena (CC-BY-4.0), published 2026-11-06
Design Arena rating (Elo)1,315EloAs of 7 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)56.6percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)37percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)87.7percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)40.1percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)29.3percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)68.8percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Show 8 more scores
ScoreValueSourceChecked
Frontierswe (best-across-versions)30.2percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)90.9percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)55.5percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)33percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated91.1percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)49percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)41percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)75.4percentAs of 14 Aug 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Compare

Compare GLM 5.3 side by side

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.08 to 0.12

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 2 to 3

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.5 to 0.75

    Source: OpenRouter models API

  4. Price changed

    cached input per mtok: 0.069 to 0.25

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 1.4 to 3

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.078 to 0.74

    Source: OpenRouter models API

  7. Price changed

    cached input per mtok: 0.1 to 0.125

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.14 to 0.3

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 3.96 to 4.9

    Source: OpenRouter models API

  10. Price changed

    input per mtok: 1.4 to 1

    Source: OpenRouter models API

  11. Price changed

    cached input per mtok: 0.19 to 0.1

    Source: OpenRouter models API

  12. Price changed

    output per mtok: 2.71 to 1.78

    Source: OpenRouter models API

  13. Price changed

    input per mtok: 0.84 to 0.56

    Source: OpenRouter models API

  14. Price changed

    output per mtok: 4 to 3

    Source: OpenRouter models API

  15. Price changed

    input per mtok: 1.2 to 0.75

    Source: OpenRouter models API

  16. Price changed

    cached input per mtok: 0.26 to 0.13

    Source: OpenRouter models API

  17. Price changed

    output per mtok: 4.4 to 2.2

    Source: OpenRouter models API

  18. Price changed

    input per mtok: 1.4 to 0.7

    Source: OpenRouter models API

  19. Price changed

    cached input per mtok: 0.052 to 0.25974

    Source: OpenRouter models API

  20. Price changed

    output per mtok: 0.88 to 4.3956

    Source: OpenRouter models API

USAGE / OPENROUTER

How much GLM 5.3 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
3.6T ▼17.6%
Requests, last 7 days
70.9M
Tool calls, last 7 days
33.9M
Intelligence score
31.7
People's vote
1476
Average cost per request
$1.15
Price per million tokens
$0.07 in · $1.4 out
0500B1T19 Sept: 371B tokens, 3.7M requests20 Sept: 309B tokens, 4.1M requests21 Sept: 524B tokens, 6.5M requests22 Sept: 334B tokens, 4.6M requests23 Sept: 451B tokens, 5.9M requests24 Sept: 625B tokens, 9.1M requests25 Sept: 427B tokens, 6.1M requests26 Sept: 222B tokens, 3.4M requests27 Sept: 216B tokens, 3.2M requests28 Sept: 448B tokens, 5.7M requests29 Sept: 410B tokens, 5.9M requests30 Sept: 396B tokens, 6.4M requests1 Oct: 440B tokens, 6M requests2 Oct: 424B tokens, 6.3M requests3 Oct: 501B tokens, 8.4M requests4 Oct: 325B tokens, 5.4M requests5 Oct: 474B tokens, 7.6M requests6 Oct: 503B tokens, 8.9M requests7 Oct: 495B tokens, 9.2M requests8 Oct: 578B tokens, 21M requests9 Oct: 546B tokens, 8.2M requests10 Oct: 516B tokens, 7.1M requests11 Oct: 674B tokens, 9.7M requests12 Oct: 652B tokens, 8.2M requests13 Oct: 719B tokens, 8.4M requests14 Oct: 743B tokens, 9.6M requests15 Oct: 981B tokens, 11.6M requests16 Oct: 943B tokens, 11.5M requests17 Oct: 630B tokens, 8.1M requests18 Oct: 525B tokens, 7.9M requests19 Oct: 746B tokens, 10M requests20 Oct: 753B tokens, 10.9M requests21 Oct: 633B tokens, 9.1M requests22 Oct: 920B tokens, 11.4M requests23 Oct: 817B tokens, 10.3M requests24 Oct: 610B tokens, 8.9M requests25 Oct: 571B tokens, 8.7M requests26 Oct: 892B tokens, 9.8M requests27 Oct: 705B tokens, 10.7M requests28 Oct: 641B tokens, 10.1M requests29 Oct: 664B tokens, 11.4M requests30 Oct: 541B tokens, 9.2M requests31 Oct: 403B tokens, 8.3M requests1 Nov: 379B tokens, 7.1M requests2 Nov: 532B tokens, 10.5M requests3 Nov: 524B tokens, 10.5M requests4 Nov: 541B tokens, 10.2M requests5 Nov: 632B tokens, 12.2M requests6 Nov: 616B tokens, 11.9M requests7 Nov: 418B tokens, 8.5M requests19 Sept3 Oct17 Oct31 Oct7 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GLM 5.3.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-05. Hosting routes and app features can differ.

DeveloperZ Ai
Exact model identifierz-ai/glm-5.3
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
glm-5.3, open weights
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
18 Aug 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

z-ai/glm-5.3: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-05
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-05
Licence source ↗

Licence declared in the zai-org/GLM-5.3 model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 7 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 31.7 (2026-11-06) ↗Coding Index: 74.8 (2026-11-06) ↗Agentic Index: 53.1 (2026-11-06) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →