geekradar
Int
Explore GeekRadar

More to explore

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

GPT-5.4 nano

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.

GPT-5.4 nano 146.1* GPT-5.4 Nano · 95% interval 143.6–148.5

Human preference · Arena

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

GPT-5.4 nano 1372.0 GPT-5.4 nano (High) · 95% interval 1368.2–1375.7 · 62,314 votes · 2026-10-28

Model performance

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

GPT-5.4 nano

Radar task score

Unrated

Older results · no current score

6 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GPT-5.4 nano 78.5*% Approx. 95% interval: 73.7–83.3% · 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.

GPT-5.4 nano 5.0*% Approx. 95% interval: 0.7–9.3%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GPT-5.4 nano 44.9*% Approx. 95% interval: 39.1–50.7%

Factual answers

SimpleQA Verified · 25%

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

GPT-5.4 nano 11.7*% Approx. 95% interval: 9.7–13.7%

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.

GPT-5.4 nano 87.8*% Approx. 95% interval: 80.1–95.5% · Older result

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.

GPT-5.4 nano 12.2*% Approx. 95% interval: 2.1–22.3%

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

GPT-5.4 nano

1,391.18 rating

Confidence interval: 1,380.77 – 1,401.60

3821 votes

Category
chinese
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,404.48 rating

Confidence interval: 1,398.60 – 1,410.36

17640 votes

Category
coding
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,314.00 rating

Confidence interval: 1,306.84 – 1,321.16

10336 votes

Category
creative_writing
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,380.75 rating

Confidence interval: 1,375.77 – 1,385.72

28887 votes

Category
english
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,345.19 rating

Confidence interval: 1,340.25 – 1,350.14

47886 votes

Category
exclude_ties
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,395.79 rating

Confidence interval: 1,387.45 – 1,404.14

6381 votes

Category
expert
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,395.19 rating

Confidence interval: 1,380.32 – 1,410.07

2077 votes

Category
french
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,367.16 rating

Confidence interval: 1,346.56 – 1,387.76

932 votes

Category
german
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,380.40 rating

Confidence interval: 1,375.89 – 1,384.92

41247 votes

Category
hard_prompts
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,387.15 rating

Confidence interval: 1,381.45 – 1,392.85

19916 votes

Category
hard_prompts_english
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,365.98 rating

Confidence interval: 1,359.46 – 1,372.50

12572 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,324.53 rating

Confidence interval: 1,318.02 – 1,331.05

13644 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,367.36 rating

Confidence interval: 1,358.09 – 1,376.64

4965 votes

Category
industry_legal_and_government
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,373.99 rating

Confidence interval: 1,367.08 – 1,380.91

10505 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,408.73 rating

Confidence interval: 1,397.95 – 1,419.50

3477 votes

Category
industry_mathematical
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,368.85 rating

Confidence interval: 1,359.32 – 1,378.38

4770 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,402.20 rating

Confidence interval: 1,396.96 – 1,407.44

24934 votes

Category
industry_software_and_it_services
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,337.46 rating

Confidence interval: 1,331.33 – 1,343.59

15365 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,361.69 rating

Confidence interval: 1,356.20 – 1,367.18

21434 votes

Category
instruction_following
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,342.58 rating

Confidence interval: 1,317.04 – 1,368.12

611 votes

Category
japanese
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,320.22 rating

Confidence interval: 1,300.52 – 1,339.92

1035 votes

Category
korean
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,365.21 rating

Confidence interval: 1,359.90 – 1,370.52

27676 votes

Category
longer_query
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,405.23 rating

Confidence interval: 1,394.40 – 1,416.06

3261 votes

Category
math
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,382.09 rating

Confidence interval: 1,375.34 – 1,388.84

11782 votes

Category
multi_turn
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,359.37 rating

Confidence interval: 1,354.71 – 1,364.03

33427 votes

Category
non_english
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,371.98 rating

Confidence interval: 1,368.23 – 1,375.74

62314 votes

Category
overall
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,365.83 rating

Confidence interval: 1,347.67 – 1,384.00

1125 votes

Category
polish
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,362.49 rating

Confidence interval: 1,354.53 – 1,370.45

6862 votes

Category
russian
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

GPT-5.4 nano

1,370.23 rating

Confidence interval: 1,355.29 – 1,385.17

1913 votes

Category
spanish
Evaluated configuration
GPT-5.4 nano (High)
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,390.93 rating

Confidence interval: 1,380.54 – 1,401.32

3844 votes

Category
chinese
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,404.38 rating

Confidence interval: 1,398.50 – 1,410.27

17665 votes

Category
coding
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,314.18 rating

Confidence interval: 1,307.02 – 1,321.34

10371 votes

Category
creative_writing
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,381.01 rating

Confidence interval: 1,376.03 – 1,385.98

28906 votes

Category
english
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,345.23 rating

Confidence interval: 1,340.28 – 1,350.18

47934 votes

Category
exclude_ties
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,396.06 rating

Confidence interval: 1,387.70 – 1,404.41

6384 votes

Category
expert
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,395.56 rating

Confidence interval: 1,380.70 – 1,410.43

2092 votes

Category
french
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,367.50 rating

Confidence interval: 1,346.92 – 1,388.09

936 votes

Category
german
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,380.47 rating

Confidence interval: 1,375.96 – 1,384.98

41331 votes

Category
hard_prompts
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,387.34 rating

Confidence interval: 1,381.64 – 1,393.04

19941 votes

Category
hard_prompts_english
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,366.16 rating

Confidence interval: 1,359.64 – 1,372.68

12592 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,324.48 rating

Confidence interval: 1,317.96 – 1,331.00

13668 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,367.65 rating

Confidence interval: 1,358.37 – 1,376.93

4975 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,374.17 rating

Confidence interval: 1,367.26 – 1,381.08

10518 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,408.48 rating

Confidence interval: 1,397.69 – 1,419.28

3479 votes

Category
industry_mathematical
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,369.30 rating

Confidence interval: 1,359.78 – 1,378.82

4788 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,402.10 rating

Confidence interval: 1,396.86 – 1,407.34

24954 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,337.88 rating

Confidence interval: 1,331.74 – 1,344.01

15395 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,362.07 rating

Confidence interval: 1,356.58 – 1,367.56

21487 votes

Category
instruction_following
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,343.12 rating

Confidence interval: 1,317.47 – 1,368.76

610 votes

Category
japanese
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,320.51 rating

Confidence interval: 1,300.78 – 1,340.25

1034 votes

Category
korean
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,365.52 rating

Confidence interval: 1,360.20 – 1,370.83

27722 votes

Category
longer_query
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,405.94 rating

Confidence interval: 1,395.11 – 1,416.77

3264 votes

Category
math
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,382.19 rating

Confidence interval: 1,375.44 – 1,388.95

11780 votes

Category
multi_turn
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,359.32 rating

Confidence interval: 1,354.65 – 1,363.98

33490 votes

Category
non_english
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,372.01 rating

Confidence interval: 1,368.26 – 1,375.77

62396 votes

Category
overall
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,365.19 rating

Confidence interval: 1,347.02 – 1,383.36

1129 votes

Category
polish
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,362.42 rating

Confidence interval: 1,354.45 – 1,370.38

6868 votes

Category
russian
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-5.4 nano

1,370.60 rating

Confidence interval: 1,355.63 – 1,385.57

1914 votes

Category
spanish
Evaluated configuration
gpt-5.4-nano-high
Evaluation type
human preference

Run it locally

Inference · memory estimate

GPT-5.4 nano

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-5.4 nano

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 · 36 fields
cache read input token cost
2.0e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
1.0e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
1.0e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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-nano*
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
2027-04-01*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
2.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
1.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
1.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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
1.25e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
6.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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
6.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.4-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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-nano*
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