GeekRadar / The comparison desk

COMPARE.

AI models

zai

GLM-5

AI model Released Feb 11, 2026

API mode: Chat^*
Context window: 202,752 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-5 145.8^* GLM-5 · 95% interval 143.8–147.8

Human preference · Arena

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

GLM-5 1445.9 GLM-5 · 95% interval 1441.7–1450.1 · 29,255 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

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

2 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GLM-5 87.8^*% Approx. 95% interval: 83.2–92.4% · 2026-02-12 · Older result

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 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GLM-5 Not available

Factual answers

SimpleQA Verified · 25%

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

GLM-5 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 80.0^*% Approx. 95% interval: 68.2–91.8% · 2026-02-12 · Older result

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

1,511.06 rating

Confidence interval: 1,497.67 – 1,524.46

2019 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,460.88 rating

Confidence interval: 1,453.71 – 1,468.05

7624 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,437.80 rating

Confidence interval: 1,428.89 – 1,446.70

4850 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,457.32 rating

Confidence interval: 1,451.55 – 1,463.09

12908 votes

Oct 28, 2026

Category: english
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,442.98 rating

Confidence interval: 1,437.26 – 1,448.70

21181 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,453.87 rating

Confidence interval: 1,442.33 – 1,465.42

2610 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,455.89 rating

Confidence interval: 1,435.58 – 1,476.20

910 votes

Oct 28, 2026

Category: french
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,446.18 rating

Confidence interval: 1,420.40 – 1,471.95

510 votes

Oct 28, 2026

Category: german
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,451.58 rating

Confidence interval: 1,446.44 – 1,456.71

18200 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,459.91 rating

Confidence interval: 1,452.95 – 1,466.86

8273 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,430.05 rating

Confidence interval: 1,422.10 – 1,438.00

5894 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,425.05 rating

Confidence interval: 1,416.98 – 1,433.12

5901 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,453.65 rating

Confidence interval: 1,441.11 – 1,466.20

2273 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,460.66 rating

Confidence interval: 1,451.93 – 1,469.39

4718 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,451.57 rating

Confidence interval: 1,436.76 – 1,466.37

1596 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,455.17 rating

Confidence interval: 1,442.27 – 1,468.06

2136 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,459.78 rating

Confidence interval: 1,453.69 – 1,465.86

11149 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,436.34 rating

Confidence interval: 1,428.94 – 1,443.73

7019 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,427.77 rating

Confidence interval: 1,421.25 – 1,434.29

9588 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,416.17 rating

Confidence interval: 1,380.12 – 1,452.21

276 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,422.34 rating

Confidence interval: 1,397.49 – 1,447.18

555 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,445.54 rating

Confidence interval: 1,439.25 – 1,451.83

11117 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,439.98 rating

Confidence interval: 1,425.93 – 1,454.03

1694 votes

Oct 28, 2026

Category: math
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,455.98 rating

Confidence interval: 1,447.12 – 1,464.83

4683 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,430.21 rating

Confidence interval: 1,425.00 – 1,435.42

16347 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,445.87 rating

Confidence interval: 1,441.66 – 1,450.09

29255 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,434.56 rating

Confidence interval: 1,411.31 – 1,457.80

604 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,436.26 rating

Confidence interval: 1,426.35 – 1,446.17

3448 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,453.20 rating

Confidence interval: 1,435.37 – 1,471.04

1130 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GLM-5
Evaluation type: human preference

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

GLM-5

1,510.54 rating

Confidence interval: 1,497.16 – 1,523.93

2019 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,461.08 rating

Confidence interval: 1,453.91 – 1,468.25

7637 votes

Oct 15, 2026

Category: coding
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,437.76 rating

Confidence interval: 1,428.85 – 1,446.67

4852 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,457.58 rating

Confidence interval: 1,451.81 – 1,463.36

12922 votes

Oct 15, 2026

Category: english
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,443.06 rating

Confidence interval: 1,437.34 – 1,448.78

21192 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,453.82 rating

Confidence interval: 1,442.26 – 1,465.38

2609 votes

Oct 15, 2026

Category: expert
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,455.25 rating

Confidence interval: 1,434.94 – 1,475.56

912 votes

Oct 15, 2026

Category: french
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,444.98 rating

Confidence interval: 1,419.11 – 1,470.84

508 votes

Oct 15, 2026

Category: german
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,451.58 rating

Confidence interval: 1,446.44 – 1,456.72

18210 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,460.04 rating

Confidence interval: 1,453.08 – 1,466.99

8279 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,429.88 rating

Confidence interval: 1,421.93 – 1,437.82

5900 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,425.37 rating

Confidence interval: 1,417.29 – 1,433.45

5903 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,452.70 rating

Confidence interval: 1,440.16 – 1,465.25

2269 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,460.44 rating

Confidence interval: 1,451.70 – 1,469.17

4716 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,451.26 rating

Confidence interval: 1,436.42 – 1,466.11

1593 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,455.13 rating

Confidence interval: 1,442.23 – 1,468.04

2136 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,460.02 rating

Confidence interval: 1,453.93 – 1,466.11

11159 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,436.32 rating

Confidence interval: 1,428.92 – 1,443.72

7022 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,427.71 rating

Confidence interval: 1,421.19 – 1,434.23

9599 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,416.30 rating

Confidence interval: 1,380.20 – 1,452.40

276 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,421.96 rating

Confidence interval: 1,396.98 – 1,446.93

553 votes

Oct 15, 2026

Category: korean
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,445.46 rating

Confidence interval: 1,439.17 – 1,451.75

11126 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,440.01 rating

Confidence interval: 1,425.95 – 1,454.07

1694 votes

Oct 15, 2026

Category: math
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,456.02 rating

Confidence interval: 1,447.17 – 1,464.87

4688 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,430.16 rating

Confidence interval: 1,424.95 – 1,435.38

16350 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,445.93 rating

Confidence interval: 1,441.71 – 1,450.15

29272 votes

Oct 15, 2026

Category: overall
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,435.18 rating

Confidence interval: 1,411.92 – 1,458.44

603 votes

Oct 15, 2026

Category: polish
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,436.28 rating

Confidence interval: 1,426.36 – 1,446.20

3447 votes

Oct 15, 2026

Category: russian
Evaluated configuration: glm-5
Evaluation type: human preference

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

GLM-5

1,453.53 rating

Confidence interval: 1,435.67 – 1,471.39

1127 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: glm-5
Evaluation type: human preference

Run it locally

Inference · memory estimate

GLM-5

1404.2 GiB checkpoint tensor payload · 753.86 B stored tensor elements · BF16/F32

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

Capabilities

Context window: 202,752 tokens
Maximum input: 200,000 tokens^*
Maximum output: 128,000 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Structured output: Yes^*
Open weights: Yes
API mode: Chat^*
Image input: No^*
Audio input: No^*
Prompt caching: Yes^*
System messages: Yes^*
Tool choice: Yes^*
Model license: mit
Checkpoint tensor payload: 1,404.18 GiB

Input modalities

text

Output modalities

text

Processing & platform

Architecture: glm_moe_dsa

System configuration

Detailed specifications

Specifications · 31 fields

cache creation input token cost

0^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5^*
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

2.0e-7^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5^*
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

1.0e-6^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5^*
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

1.0e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 batches

5.0e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 priority

1.75e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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

bedrock_converse^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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^*
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

200,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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

200,000^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5^*
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^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 tokens

128,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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^*
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

3.2e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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

3.2e-6^*

Scope and conditions

native_context

provider: zai^*
mode: chat^*
full_native_model_id: zai/glm-5^*
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 batches

1.6e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 priority

5.6e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 audio input

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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^*
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 native structured output

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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^*
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^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 response schema

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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 system messages

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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^*
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

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: zai.glm-5^*
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