GPT-5.4 mini
4 benchmark results for this configuration
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-5.4 mini
AI model Released
- API mode
- Chat*
- Context window
- 400,000 tokens
- Maximum output
- 128,000 tokens
- Open weights
- No
Capability & preference
General capability · ECI
A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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
GPT-5.4 mini
1,446.20 rating
Confidence interval: 1,436.07 – 1,456.33
3921 votes
- Category
- chinese
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,438.31 rating
Confidence interval: 1,432.47 – 1,444.16
17248 votes
- Category
- coding
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,370.39 rating
Confidence interval: 1,363.46 – 1,377.33
10797 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,411.80 rating
Confidence interval: 1,406.90 – 1,416.71
29163 votes
- Category
- english
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,397.57 rating
Confidence interval: 1,392.78 – 1,402.36
48753 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,435.06 rating
Confidence interval: 1,426.93 – 1,443.19
6344 votes
- Category
- expert
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,441.55 rating
Confidence interval: 1,427.20 – 1,455.89
2222 votes
- Category
- french
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,408.88 rating
Confidence interval: 1,388.84 – 1,428.91
933 votes
- Category
- german
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,424.24 rating
Confidence interval: 1,419.79 – 1,428.68
41637 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,419.71 rating
Confidence interval: 1,414.09 – 1,425.34
19855 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,417.44 rating
Confidence interval: 1,411.06 – 1,423.83
12859 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,373.06 rating
Confidence interval: 1,366.69 – 1,379.43
13897 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,413.96 rating
Confidence interval: 1,404.85 – 1,423.06
5066 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,417.20 rating
Confidence interval: 1,410.41 – 1,424.00
10527 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,428.39 rating
Confidence interval: 1,417.62 – 1,439.15
3423 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,394.51 rating
Confidence interval: 1,385.08 – 1,403.94
4760 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,436.02 rating
Confidence interval: 1,430.86 – 1,441.18
25046 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,392.91 rating
Confidence interval: 1,386.95 – 1,398.87
15833 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,405.10 rating
Confidence interval: 1,399.71 – 1,410.49
21713 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,374.49 rating
Confidence interval: 1,349.29 – 1,399.69
623 votes
- Category
- japanese
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,368.43 rating
Confidence interval: 1,348.56 – 1,388.30
989 votes
- Category
- korean
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,407.45 rating
Confidence interval: 1,402.25 – 1,412.66
27787 votes
- Category
- longer_query
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,418.20 rating
Confidence interval: 1,407.50 – 1,428.90
3366 votes
- Category
- math
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,429.15 rating
Confidence interval: 1,422.52 – 1,435.77
11876 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,404.87 rating
Confidence interval: 1,400.26 – 1,409.49
34268 votes
- Category
- non_english
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,411.58 rating
Confidence interval: 1,407.87 – 1,415.30
63432 votes
- Category
- overall
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,416.33 rating
Confidence interval: 1,398.94 – 1,433.71
1188 votes
- Category
- polish
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,417.38 rating
Confidence interval: 1,409.49 – 1,425.26
6992 votes
- Category
- russian
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GPT-5.4 mini
1,404.46 rating
Confidence interval: 1,389.76 – 1,419.17
1914 votes
- Category
- spanish
- Evaluated configuration
- GPT-5.4 mini (High)
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,445.60 rating
Confidence interval: 1,435.48 – 1,455.72
3931 votes
- Category
- chinese
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,438.36 rating
Confidence interval: 1,432.50 – 1,444.21
17236 votes
- Category
- coding
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,370.21 rating
Confidence interval: 1,363.27 – 1,377.15
10818 votes
- Category
- creative_writing
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,411.73 rating
Confidence interval: 1,406.82 – 1,416.64
29159 votes
- Category
- english
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,397.45 rating
Confidence interval: 1,392.66 – 1,402.25
48768 votes
- Category
- exclude_ties
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,434.94 rating
Confidence interval: 1,426.80 – 1,443.08
6338 votes
- Category
- expert
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,440.29 rating
Confidence interval: 1,425.91 – 1,454.68
2227 votes
- Category
- french
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,409.08 rating
Confidence interval: 1,388.99 – 1,429.18
934 votes
- Category
- german
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,424.25 rating
Confidence interval: 1,419.81 – 1,428.70
41651 votes
- Category
- hard_prompts
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,419.79 rating
Confidence interval: 1,414.16 – 1,425.41
19862 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,417.73 rating
Confidence interval: 1,411.34 – 1,424.12
12859 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,373.05 rating
Confidence interval: 1,366.67 – 1,379.42
13900 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,414.63 rating
Confidence interval: 1,405.52 – 1,423.75
5073 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,417.21 rating
Confidence interval: 1,410.42 – 1,424.00
10529 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,428.70 rating
Confidence interval: 1,417.93 – 1,439.48
3430 votes
- Category
- industry_mathematical
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,394.14 rating
Confidence interval: 1,384.70 – 1,403.58
4762 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,436.03 rating
Confidence interval: 1,430.87 – 1,441.19
25039 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,392.76 rating
Confidence interval: 1,386.79 – 1,398.73
15847 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,405.10 rating
Confidence interval: 1,399.70 – 1,410.49
21734 votes
- Category
- instruction_following
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,375.06 rating
Confidence interval: 1,349.79 – 1,400.32
624 votes
- Category
- japanese
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,370.88 rating
Confidence interval: 1,351.01 – 1,390.74
989 votes
- Category
- korean
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,407.31 rating
Confidence interval: 1,402.09 – 1,412.52
27795 votes
- Category
- longer_query
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,418.63 rating
Confidence interval: 1,407.92 – 1,429.33
3367 votes
- Category
- math
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,429.02 rating
Confidence interval: 1,422.39 – 1,435.65
11877 votes
- Category
- multi_turn
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,404.86 rating
Confidence interval: 1,400.25 – 1,409.48
34289 votes
- Category
- non_english
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,411.45 rating
Confidence interval: 1,407.73 – 1,415.17
63449 votes
- Category
- overall
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,415.20 rating
Confidence interval: 1,397.84 – 1,432.57
1193 votes
- Category
- polish
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,417.10 rating
Confidence interval: 1,409.20 – 1,425.00
6983 votes
- Category
- russian
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GPT-5.4 mini
1,404.47 rating
Confidence interval: 1,389.71 – 1,419.23
1906 votes
- Category
- spanish
- Evaluated configuration
- gpt-5.4-mini-high
- Evaluation type
- human preference
Run it locally
GPT-5.4 mini
Closed weights. No supported local deployment or GPU requirement is published.
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
GPT-5.4 mini
Capabilities
- Context window
- 400,000 tokens
- Maximum input
- 272,000 tokens*
- Maximum output
- 128,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- No
- Knowledge cutoff
- 2025-08-31
- API mode
- Chat*
- Image input
- Yes*
- PDF input
- Yes*
- Parallel tool calls
- Yes*
- Prompt caching
- Yes*
- System messages
- Yes*
- Tool choice
- Yes*
- Web search
- Yes*
- Model license
- Proprietary
Input modalities
- text
- image
Output modalities
- text
System configuration
Detailed specifications
Specifications · 39 fields
- cache read input token cost
- 7.5e-8*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 batches
- 3.75e-8*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 flex
- 3.75e-8*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 priority
- 1.5e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- default reasoning effort
- none*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 7.5e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 3.75e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 3.75e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 1.5e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 272,000*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 4.5e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 2.25e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 2.25e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- 9.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- regional processing uplift multiplier eu
- 1.1*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- regional processing uplift multiplier us
- 1.1*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- search context cost per query
- search_context_size_high
- 0.01*
- search_context_size_low
- 0.01*
- search_context_size_medium
- 0.01*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- supported endpoints
- /v1/chat/completions*
- /v1/batch*
- /v1/responses*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- supported modalities
- text*
- image*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
- supported output modalities
- text*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 minimal reasoning effort
- No*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 streaming
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 none reasoning effort
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 parallel function calling
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 pdf input
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 search
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 web search
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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 xhigh reasoning effort
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-5.4-mini*
- 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.*
0 selected Compare 0
* Provisional data