OpenAI: GPT-5.4 Mini

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reason…

openai/gpt-5.4-mini-20260317

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.

The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

Specifications & capabilities

Input
file, image, text
Output
text
Context window · tokens
400000
Knowledge cutoff
2025-08-31
Published model ID
gpt-5.4-mini-2026-03-17
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

41–60 / 117

LMArena

1,451.514

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
77
sample size
6922
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1443.5605614007138
confidence upper
1459.4680059647105
Original result ↗

LMArena

1,446.676

source id
lmarena
leaderboard name
LMArena Text Factuality Overall
dimension
factuality
metric
Arena rating
rank
78
sample size
62679
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1443.6741567816748
confidence upper
1449.6776248680503
Original result ↗

LMArena

1,473.334

source id
lmarena
leaderboard name
LMArena Text Factuality Expert
dimension
factuality
metric
Arena rating
rank
79
sample size
4952
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1465.2904354809018
confidence upper
1481.3776369483055
Original result ↗

LMArena

1,437.943

source id
lmarena
leaderboard name
LMArena Text Style Control Non English
dimension
style
metric
Arena rating
rank
80
sample size
33930
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1433.272036744452
confidence upper
1442.614145447794
Original result ↗

LMArena

1,422.274

source id
lmarena
leaderboard name
LMArena Text Factuality Spanish
dimension
factuality
metric
Arena rating
rank
80
sample size
1490
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1408.046564917407
confidence upper
1436.502358924128
Original result ↗

LMArena

1,440.281

source id
lmarena
leaderboard name
LMArena Text Factuality Instruction Following
dimension
factuality
metric
Arena rating
rank
82
sample size
19945
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1435.5906602967755
confidence upper
1444.9716997151202
Original result ↗

LMArena

1,449.036

source id
lmarena
leaderboard name
LMArena Text Style Control Exclude Ties
dimension
style
metric
Arena rating
rank
84
sample size
48253
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1444.143573082021
confidence upper
1453.9287391334324
Original result ↗

LMArena

1,486.081

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Software And It Services
dimension
style
metric
Arena rating
rank
85
sample size
24811
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1480.8792586044945
confidence upper
1491.2833603034812
Original result ↗

LMArena

1,480.653

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Software And It Services
dimension
factuality
metric
Arena rating
rank
85
sample size
23857
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1476.229666113053
confidence upper
1485.0761385830892
Original result ↗

LMArena

1,452.907

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
85
sample size
3372
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1442.0333894970852
confidence upper
1463.779702222588
Original result ↗

LMArena

1,469.505

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
86
sample size
41226
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1465.0156246817753
confidence upper
1473.9937989403422
Original result ↗

LMArena

1,472.546

source id
lmarena
leaderboard name
LMArena Text Factuality Chinese
dimension
factuality
metric
Arena rating
rank
87
sample size
3028
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1462.1523466833382
confidence upper
1482.9390395973574
Original result ↗

LMArena

1,465.166

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Life And Physical And Social Science
dimension
style
metric
Arena rating
rank
87
sample size
10407
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1458.276143918248
confidence upper
1472.0554154924764
Original result ↗

LMArena

1,447.434

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
87
sample size
62795
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1443.6773553906626
confidence upper
1451.1903661454564
Original result ↗

LMArena

1,461.141

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Life And Physical And Social Science
dimension
factuality
metric
Arena rating
rank
88
sample size
8620
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1454.4327430460085
confidence upper
1467.8490702855472
Original result ↗

LMArena

1,456.265

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
88
sample size
4994
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1446.9559552041394
confidence upper
1465.5734081785388
Original result ↗

LMArena

1,444.116

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
88
sample size
928
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1423.8900055698778
confidence upper
1464.3419314570501
Original result ↗

OpenRouter Benchmarks

66.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
88
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:04:42.468Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6666665
accuracy_std_dev
0.013333499999999998
cost_per_task_usd
0.08889954
output_tokens_per_task
12861.73
latency_seconds_per_task
108.43306
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-5.4-mini-20260317
source model id
openai/gpt-5.4-mini-20260317
Original result ↗

LMArena

1,494.905

source id
lmarena
leaderboard name
LMArena Text Style Control Coding
dimension
style
metric
Arena rating
rank
89
sample size
17079
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1489.0184279469058
confidence upper
1500.7906755218864
Original result ↗

LMArena

1,434.694

source id
lmarena
leaderboard name
LMArena Text Style Control Instruction Following
dimension
style
metric
Arena rating
rank
90
sample size
21493
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 mini (High)
confidence lower
1429.255031468408
confidence upper
1440.1323934081438
Original result ↗

Published prices

1–20 / 55

gpt-5.4-mini ↗

$0.05

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

gpt-5.4-mini ↗

$0.49

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cache write, 5 minutes (per 1M)

gpt-5.4-mini ↗

$0.49

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gpt-5.4-mini ↗

$2.93

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

openai/gpt-5.4-mini ↗

$0.08

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-5.4-mini ↗

$0.75

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-5.4-mini ↗

$4.50

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-5.4-mini ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4-mini ↗

$0.75

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4-mini ↗

$4.50

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4-mini ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
web_search
Currency
USD
Billing conditions

openai/gpt-5.4-mini:batch ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.4-mini:batch ↗

$0.38

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.4-mini:batch ↗

$2.25

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
mode
batch

~openai/gpt-mini-latest ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
OpenAI: GPT-5.4 Mini
slug
openai/gpt-5.4-mini
routing_alias
true

~openai/gpt-mini-latest ↗

$0.75

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
OpenAI: GPT-5.4 Mini
slug
openai/gpt-5.4-mini
routing_alias
true

~openai/gpt-mini-latest ↗

$4.50

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
OpenAI: GPT-5.4 Mini
slug
openai/gpt-5.4-mini
routing_alias
true

~openai/gpt-mini-latest ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
web_search
Currency
USD
Billing conditions
alias_target
name
OpenAI: GPT-5.4 Mini
slug
openai/gpt-5.4-mini
routing_alias
true

openai/gpt-5.4-mini ↗

$0.08

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–3 / 3

gpt-5.4-mini ↗

source model id
gpt-5.4-mini
hosting
gateway
platforms
  • Cheaper Inference
context length
400000
max output tokens
128000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

GPT-5.4 mini ↗

source model id
openai/gpt-5.4-mini
hosting
third-party
platforms
  • OpenAI
context length
128000
max output tokens
16384
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    GPT 5.4 Mini ↗

    source model id
    openai/gpt-5.4-mini
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    400000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    • image
    • pdf
    output_modalities
    • text
    capabilities
    • promptCaching
    • reasoning
    • structuredOutputs
    • toolCalling
    • visionInput
    • webSearch
    regions
    • us

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    35 / 100

    source id
    stanfordFMTI
    canonical model id
    openai/gpt-5.4-mini-20260317
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    OpenAI
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    35 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–14 / 14

    cloudflareWorkersAI ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    400000
    normalized value
    400000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    400000
    normalized value
    400000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    400000
    normalized value
    400000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    context_length
    value
    400000
    normalized value
    400000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-08-31
    normalized value
    2025-08-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-08-31
    normalized value
    2025-08-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-08-31
    normalized value
    2025-08-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-08-31
    normalized value
    2025-08-31
    precision
    day
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    Original sources

    1–11 / 11

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    GitHub · Catalog ↗

    LMArena · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    Source links

    1–8 / 8

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace