GeekRadar / The comparison desk

COMPARE.

AI models

zai

GLM-5.3-Flash

AI model Released Aug 20, 2026

API mode: Chat^*
Context window: 1,048,576 tokens
Maximum output: 128,000 tokens^*
Open weights: Yes

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

GLM-5.3-Flash 153.2^* GLM-5.3-Flash · 95% interval 150.9–155.4

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

GLM-5.3-Flash 1473.0 GLM-5.3-Flash · 95% interval 1468.4–1477.7 · 41,642 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

GLM-5.3-Flash

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

GLM-5.3-Flash 90.2^*% Approx. 95% interval: 86.8–93.5% · 2026-08-26

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

GLM-5.3-Flash 8.0^*% Approx. 95% interval: 2.7–13.3% · 2026-08-28

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

GLM-5.3-Flash 55.8^*% Approx. 95% interval: 50.0–61.6% · 2026-08-27

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

GLM-5.3-Flash Not available

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

GLM-5.3-Flash 93.9^*% Approx. 95% interval: 89.7–98.1% · 2026-08-26

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

GLM-5.3-Flash 17.1^*% Approx. 95% interval: 5.4–28.7% · 2026-08-27

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Test version

Arena text preference / chinesehuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,529.77 rating

Confidence interval: 1,518.69 – 1,540.86

3299 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,509.18 rating

Confidence interval: 1,502.29 – 1,516.07

10603 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,441.50 rating

Confidence interval: 1,433.95 – 1,449.04

8779 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,475.19 rating

Confidence interval: 1,469.16 – 1,481.21

15227 votes

Oct 28, 2026

Category: english
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,478.86 rating

Confidence interval: 1,472.78 – 1,484.93

30481 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,513.57 rating

Confidence interval: 1,503.78 – 1,523.37

4239 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,488.25 rating

Confidence interval: 1,471.70 – 1,504.81

1571 votes

Oct 28, 2026

Category: french
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,455.34 rating

Confidence interval: 1,432.38 – 1,478.29

726 votes

Oct 28, 2026

Category: german
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,492.23 rating

Confidence interval: 1,486.82 – 1,497.63

26491 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,489.18 rating

Confidence interval: 1,482.23 – 1,496.13

9796 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,461.01 rating

Confidence interval: 1,453.35 – 1,468.67

7532 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,441.50 rating

Confidence interval: 1,434.49 – 1,448.52

10525 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,475.04 rating

Confidence interval: 1,464.04 – 1,486.05

3332 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,484.05 rating

Confidence interval: 1,476.07 – 1,492.03

6813 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,495.65 rating

Confidence interval: 1,483.09 – 1,508.20

2427 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,477.85 rating

Confidence interval: 1,466.01 – 1,489.68

2794 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,501.64 rating

Confidence interval: 1,495.50 – 1,507.78

15570 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,455.59 rating

Confidence interval: 1,448.83 – 1,462.34

11432 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,480.61 rating

Confidence interval: 1,474.31 – 1,486.90

14398 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,449.68 rating

Confidence interval: 1,427.13 – 1,472.24

834 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,442.09 rating

Confidence interval: 1,419.46 – 1,464.72

741 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,483.67 rating

Confidence interval: 1,477.60 – 1,489.74

18242 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,501.65 rating

Confidence interval: 1,488.39 – 1,514.90

2131 votes

Oct 28, 2026

Category: math
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,471.05 rating

Confidence interval: 1,462.80 – 1,479.30

6403 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,463.44 rating

Confidence interval: 1,458.05 – 1,468.82

26402 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,473.04 rating

Confidence interval: 1,468.39 – 1,477.68

41642 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,451.77 rating

Confidence interval: 1,429.83 – 1,473.71

708 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,467.24 rating

Confidence interval: 1,458.72 – 1,475.75

5882 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

GLM-5.3-Flash

1,473.30 rating

Confidence interval: 1,457.46 – 1,489.14

1574 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GLM-5.3-Flash
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,528.03 rating

Confidence interval: 1,515.59 – 1,540.48

2515 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,507.58 rating

Confidence interval: 1,500.18 – 1,514.98

8457 votes

Oct 15, 2026

Category: coding
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,441.17 rating

Confidence interval: 1,433.03 – 1,449.31

6983 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,474.46 rating

Confidence interval: 1,468.05 – 1,480.87

12160 votes

Oct 15, 2026

Category: english
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,475.77 rating

Confidence interval: 1,469.40 – 1,482.14

24109 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,510.28 rating

Confidence interval: 1,499.65 – 1,520.92

3417 votes

Oct 15, 2026

Category: expert
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,490.14 rating

Confidence interval: 1,471.67 – 1,508.61

1186 votes

Oct 15, 2026

Category: french
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,466.40 rating

Confidence interval: 1,441.16 – 1,491.64

568 votes

Oct 15, 2026

Category: german
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,490.36 rating

Confidence interval: 1,484.70 – 1,496.03

20935 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,490.08 rating

Confidence interval: 1,482.57 – 1,497.59

7713 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,461.36 rating

Confidence interval: 1,453.12 – 1,469.60

6067 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,440.77 rating

Confidence interval: 1,433.21 – 1,448.32

8287 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,473.96 rating

Confidence interval: 1,461.95 – 1,485.96

2692 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,482.72 rating

Confidence interval: 1,474.13 – 1,491.31

5416 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,494.49 rating

Confidence interval: 1,480.47 – 1,508.50

1867 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,475.85 rating

Confidence interval: 1,462.85 – 1,488.86

2224 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,500.56 rating

Confidence interval: 1,494.02 – 1,507.09

12400 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,454.59 rating

Confidence interval: 1,447.31 – 1,461.87

9070 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,477.65 rating

Confidence interval: 1,470.90 – 1,484.41

11345 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,435.15 rating

Confidence interval: 1,409.33 – 1,460.97

616 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,438.96 rating

Confidence interval: 1,413.82 – 1,464.10

586 votes

Oct 15, 2026

Category: korean
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,482.29 rating

Confidence interval: 1,475.86 – 1,488.72

14580 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,504.51 rating

Confidence interval: 1,489.64 – 1,519.39

1647 votes

Oct 15, 2026

Category: math
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,468.86 rating

Confidence interval: 1,459.88 – 1,477.83

5012 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,460.66 rating

Confidence interval: 1,454.99 – 1,466.32

20756 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,470.53 rating

Confidence interval: 1,465.67 – 1,475.38

32925 votes

Oct 15, 2026

Category: overall
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,449.41 rating

Confidence interval: 1,424.90 – 1,473.92

556 votes

Oct 15, 2026

Category: polish
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,464.75 rating

Confidence interval: 1,455.43 – 1,474.08

4598 votes

Oct 15, 2026

Category: russian
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

GLM-5.3-Flash

1,476.34 rating

Confidence interval: 1,458.99 – 1,493.69

1258 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: glm-5.3-flash
Evaluation type: human preference

Run it locally

Inference · memory estimate

GLM-5.3-Flash

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Context window: 1,048,576 tokens
Maximum input: 1,048,576 tokens^*
Maximum output: 128,000 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Open weights: Yes
API mode: Chat^*
Image input: Yes^*
Prompt caching: Yes^*
Tool choice: Yes^*
Model license: MIT

Input modalities

text
image

Output modalities

text

Processing & platform

Architecture: glm5_next

System configuration

Detailed specifications

Specifications · 13 fields

cache creation input token cost

0^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost

3.0e-8^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

1.5e-7^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

zai^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

1,048,576^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max output tokens

128,000^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

5.0e-7^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports function calling

Yes^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports prompt caching

Yes^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports reasoning

Yes^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports tool choice

Yes^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports vision

Yes^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5.3-flash^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Provisional data