geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
zai

GLM-4.7

AI model Released

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-4.7 143.2* GLM-4.7 · 95% interval 141.3–145.2

Human preference · Arena

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

GLM-4.7 1435.4 GLM-4.7 · 95% interval 1429.4–1441.5 · 12,239 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-4.7

Radar task score

Unrated

2/4 core tests · not enough evidence

3 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GLM-4.7 83.3*% Approx. 95% interval: 78.7–88.0% · 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-4.7 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GLM-4.7 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-4.7 32.2*% Approx. 95% interval: 29.3–35.1%

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-4.7 83.3*% Approx. 95% interval: 74.0–92.7% · 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.

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

GLM-4.7

1,494.73 rating

Confidence interval: 1,476.52 – 1,512.95

1020 votes

Category
chinese
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

GLM-4.7

1,454.18 rating

Confidence interval: 1,442.44 – 1,465.92

2478 votes

Category
coding
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GLM-4.7

1,401.28 rating

Confidence interval: 1,388.18 – 1,414.39

1960 votes

Category
creative_writing
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

GLM-4.7

1,453.03 rating

Confidence interval: 1,444.40 – 1,461.66

5027 votes

Category
english
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GLM-4.7

1,430.97 rating

Confidence interval: 1,422.58 – 1,439.36

8492 votes

Category
exclude_ties
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

GLM-4.7

1,423.60 rating

Confidence interval: 1,403.16 – 1,444.03

807 votes

Category
expert
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

GLM-4.7

1,431.96 rating

Confidence interval: 1,398.43 – 1,465.49

306 votes

Category
french
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

GLM-4.7

1,426.16 rating

Confidence interval: 1,388.82 – 1,463.50

223 votes

Category
german
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GLM-4.7

1,442.97 rating

Confidence interval: 1,435.29 – 1,450.66

6788 votes

Category
hard_prompts
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GLM-4.7

1,452.45 rating

Confidence interval: 1,441.16 – 1,463.73

2699 votes

Category
hard_prompts_english
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GLM-4.7

1,429.30 rating

Confidence interval: 1,417.15 – 1,441.45

2292 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GLM-4.7

1,400.92 rating

Confidence interval: 1,389.20 – 1,412.63

2420 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GLM-4.7

1,444.43 rating

Confidence interval: 1,425.92 – 1,462.95

969 votes

Category
industry_legal_and_government
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GLM-4.7

1,457.59 rating

Confidence interval: 1,445.05 – 1,470.12

2141 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GLM-4.7

1,411.31 rating

Confidence interval: 1,389.00 – 1,433.62

624 votes

Category
industry_mathematical
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GLM-4.7

1,468.61 rating

Confidence interval: 1,448.56 – 1,488.66

826 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GLM-4.7

1,453.48 rating

Confidence interval: 1,444.19 – 1,462.77

4116 votes

Category
industry_software_and_it_services
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GLM-4.7

1,410.92 rating

Confidence interval: 1,399.95 – 1,421.90

2825 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GLM-4.7

1,412.34 rating

Confidence interval: 1,402.07 – 1,422.62

3300 votes

Category
instruction_following
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

GLM-4.7

1,438.85 rating

Confidence interval: 1,384.60 – 1,493.11

125 votes

Category
japanese
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

GLM-4.7

1,399.10 rating

Confidence interval: 1,356.01 – 1,442.20

177 votes

Category
korean
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GLM-4.7

1,432.45 rating

Confidence interval: 1,422.12 – 1,442.78

3260 votes

Category
longer_query
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

GLM-4.7

1,423.95 rating

Confidence interval: 1,403.53 – 1,444.38

738 votes

Category
math
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GLM-4.7

1,445.79 rating

Confidence interval: 1,432.37 – 1,459.20

1928 votes

Category
multi_turn
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GLM-4.7

1,417.05 rating

Confidence interval: 1,409.64 – 1,424.46

7212 votes

Category
non_english
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

GLM-4.7

1,435.43 rating

Confidence interval: 1,429.41 – 1,441.45

12239 votes

Category
overall
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

GLM-4.7

1,435.02 rating

Confidence interval: 1,409.43 – 1,460.61

461 votes

Category
polish
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

GLM-4.7

1,423.41 rating

Confidence interval: 1,409.64 – 1,437.19

1639 votes

Category
russian
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

GLM-4.7

1,434.38 rating

Confidence interval: 1,403.59 – 1,465.16

345 votes

Category
spanish
Evaluated configuration
GLM-4.7
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

GLM-4.7

1,495.30 rating

Confidence interval: 1,477.08 – 1,513.52

1021 votes

Category
chinese
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

GLM-4.7

1,454.35 rating

Confidence interval: 1,442.63 – 1,466.08

2486 votes

Category
coding
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GLM-4.7

1,401.25 rating

Confidence interval: 1,388.15 – 1,414.36

1960 votes

Category
creative_writing
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

GLM-4.7

1,453.04 rating

Confidence interval: 1,444.41 – 1,461.67

5027 votes

Category
english
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GLM-4.7

1,431.02 rating

Confidence interval: 1,422.63 – 1,439.40

8502 votes

Category
exclude_ties
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

GLM-4.7

1,423.89 rating

Confidence interval: 1,403.48 – 1,444.30

809 votes

Category
expert
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

GLM-4.7

1,431.58 rating

Confidence interval: 1,398.03 – 1,465.13

306 votes

Category
french
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

GLM-4.7

1,425.96 rating

Confidence interval: 1,388.60 – 1,463.32

223 votes

Category
german
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GLM-4.7

1,442.86 rating

Confidence interval: 1,435.17 – 1,450.54

6796 votes

Category
hard_prompts
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GLM-4.7

1,452.37 rating

Confidence interval: 1,441.08 – 1,463.66

2699 votes

Category
hard_prompts_english
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GLM-4.7

1,429.26 rating

Confidence interval: 1,417.11 – 1,441.42

2293 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GLM-4.7

1,401.03 rating

Confidence interval: 1,389.32 – 1,412.74

2426 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GLM-4.7

1,444.78 rating

Confidence interval: 1,426.25 – 1,463.30

970 votes

Category
industry_legal_and_government
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GLM-4.7

1,457.86 rating

Confidence interval: 1,445.32 – 1,470.39

2142 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GLM-4.7

1,411.48 rating

Confidence interval: 1,389.21 – 1,433.76

625 votes

Category
industry_mathematical
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GLM-4.7

1,468.71 rating

Confidence interval: 1,448.66 – 1,488.76

826 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GLM-4.7

1,453.51 rating

Confidence interval: 1,444.23 – 1,462.80

4126 votes

Category
industry_software_and_it_services
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GLM-4.7

1,410.74 rating

Confidence interval: 1,399.76 – 1,421.72

2827 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GLM-4.7

1,412.05 rating

Confidence interval: 1,401.78 – 1,422.32

3306 votes

Category
instruction_following
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

GLM-4.7

1,438.72 rating

Confidence interval: 1,384.44 – 1,493.00

125 votes

Category
japanese
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

GLM-4.7

1,398.97 rating

Confidence interval: 1,355.85 – 1,442.08

177 votes

Category
korean
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GLM-4.7

1,432.61 rating

Confidence interval: 1,422.28 – 1,442.93

3267 votes

Category
longer_query
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

GLM-4.7

1,423.95 rating

Confidence interval: 1,403.55 – 1,444.35

739 votes

Category
math
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GLM-4.7

1,445.93 rating

Confidence interval: 1,432.53 – 1,459.34

1931 votes

Category
multi_turn
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GLM-4.7

1,417.04 rating

Confidence interval: 1,409.63 – 1,424.46

7226 votes

Category
non_english
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

GLM-4.7

1,435.40 rating

Confidence interval: 1,429.39 – 1,441.42

12253 votes

Category
overall
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

GLM-4.7

1,434.97 rating

Confidence interval: 1,409.37 – 1,460.56

461 votes

Category
polish
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

GLM-4.7

1,422.90 rating

Confidence interval: 1,409.14 – 1,436.65

1645 votes

Category
russian
Evaluated configuration
glm-4.7
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

GLM-4.7

1,434.27 rating

Confidence interval: 1,403.47 – 1,465.07

345 votes

Category
spanish
Evaluated configuration
glm-4.7
Evaluation type
human preference

Run it locally

Inference · memory estimate

GLM-4.7

667.5 GiB checkpoint tensor payload · 358.34 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
Reported value 1: 203,000 tokens*
Reported value 2: 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
667.46 GiB

Input modalities

  • text

Output modalities

  • text

Processing & platform

Architecture
glm4_moe

System configuration

Detailed specifications

Specifications · 33 fields
cache creation input token cost
0*
Scope and conditions
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
1.1e-7*
Scope and conditions
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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.*
deprecation date
2027-03-30*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
6.0e-7*
Scope and conditions
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
6.0e-7*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
3.0e-7*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 flex
3.0e-7*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
1.05e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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-4.7*
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-4.7*
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
203,000*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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
2.2e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
2.2e-6*
Scope and conditions
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
1.1e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 flex
1.1e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
3.85e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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-4.7*
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