OpenAI: GPT-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inpu…

openai/gpt-5.4-20260305

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.

The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
1050000
Knowledge cutoff
2025-08-31
Published model ID
gpt-5.4-2026-03-05
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

21–40 / 227

LMArena

1,468.348

source id
lmarena
leaderboard name
LMArena Text Factuality Japanese
dimension
factuality
metric
Arena rating
rank
12
sample size
450
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4
confidence lower
1446.0252325158458
confidence upper
1490.6707062345886
Original result ↗

LMArena

1,324.92

source id
lmarena
leaderboard name
LMArena Vision Diagram
dimension
multimodal
metric
Arena rating
rank
12
sample size
8574
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1317.0524185651425
confidence upper
1332.7882552440822
Original result ↗

LMArena

1,534.008

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
13
sample size
16075
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1528.9444295658134
confidence upper
1539.0720732044713
Original result ↗

OpenRouter Benchmarks

89.955%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Azure
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
13
sample size
1188
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:18:24.536Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1188
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8995508333333332
accuracy_std_dev
0.0038470676025888335
cost_per_task_usd
0.15600541077441077
output_tokens_per_task
9623.925925925925
latency_seconds_per_task
138.8771792929293
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
43
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-5.4-20260305
source model id
openai/gpt-5.4-20260305
Original result ↗

LMArena

1,507.056

source id
lmarena
leaderboard name
LMArena Text Factuality French
dimension
factuality
metric
Arena rating
rank
14
sample size
1904
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4
confidence lower
1494.4273659686037
confidence upper
1519.6845748807887
Original result ↗

LMArena

1,490.488

source id
lmarena
leaderboard name
LMArena Text Factuality Exclude Ties
dimension
factuality
metric
Arena rating
rank
14
sample size
49070
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1486.7867020451013
confidence upper
1494.1891037553867
Original result ↗

LMArena

1,472.946

source id
lmarena
leaderboard name
LMArena Document Overall
dimension
productivity
metric
Arena rating
rank
15
sample size
35183
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4
confidence lower
1466.9860896493424
confidence upper
1478.9058551495007
Original result ↗

LMArena

1,318.876

source id
lmarena
leaderboard name
LMArena Vision Style Control Diagram
dimension
multimodal
metric
Arena rating
rank
15
sample size
8574
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1310.8347757541271
confidence upper
1326.9173732881611
Original result ↗

LMArena

1,490.351

source id
lmarena
leaderboard name
LMArena Text Factuality Math
dimension
factuality
metric
Arena rating
rank
16
sample size
2736
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1479.9028037410096
confidence upper
1500.7989167297521
Original result ↗

LMArena

1,485.098

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Business And Management And Financial Operations
dimension
factuality
metric
Arena rating
rank
16
sample size
11740
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4
confidence lower
1479.1853414680236
confidence upper
1491.0102313804193
Original result ↗

LMArena

1,456.861

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
16
sample size
879
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4
confidence lower
1437.8311934464691
confidence upper
1475.889847262611
Original result ↗

LMArena

1,310.475

source id
lmarena
leaderboard name
LMArena Vision Ocr
dimension
multimodal
metric
Arena rating
rank
16
sample size
22696
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1304.9405261798013
confidence upper
1316.0093913659107
Original result ↗

LMArena

1,298.753

source id
lmarena
leaderboard name
LMArena Vision English
dimension
multimodal
metric
Arena rating
rank
16
sample size
12546
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1290.9832199965947
confidence upper
1306.5225790539366
Original result ↗

LMArena

1,531.224

source id
lmarena
leaderboard name
LMArena Text Factuality Chinese
dimension
factuality
metric
Arena rating
rank
17
sample size
3267
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1521.5472219758972
confidence upper
1540.9000400747595
Original result ↗

LMArena

1,487.528

source id
lmarena
leaderboard name
LMArena Text Factuality English
dimension
factuality
metric
Arena rating
rank
17
sample size
28763
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1483.5269090523657
confidence upper
1491.528551372503
Original result ↗

OpenRouter Benchmarks

90.236%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
17
sample size
396
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
gpqa_diamond
name
GPQA Diamond
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
2026-10-01T19:14:23.097Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.902357
accuracy_std_dev
0
cost_per_task_usd
0.1437863712121212
output_tokens_per_task
9456.126262626263
latency_seconds_per_task
149.58563636363635
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
132
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-5.4-20260305
source model id
openai/gpt-5.4-20260305
Original result ↗

OpenRouter Benchmarks

73.111%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Azure
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
17
sample size
300
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
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
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:05:18.005Z
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
300
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7311110000000001
accuracy_std_dev
0.014740588127118051
cost_per_task_usd
0.29708465
output_tokens_per_task
10592.956666666667
latency_seconds_per_task
186.51067
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
40
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-5.4-20260305
source model id
openai/gpt-5.4-20260305
Original result ↗

LMArena

1,512.102

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts English
dimension
factuality
metric
Arena rating
rank
18
sample size
18095
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1507.2972768849081
confidence upper
1516.9066899109264
Original result ↗

LMArena

1,496.681

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
18
sample size
3484
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1486.0072063013627
confidence upper
1507.3555186744375
Original result ↗

LMArena

1,483.776

source id
lmarena
leaderboard name
LMArena Text Factuality Instruction Following
dimension
factuality
metric
Arena rating
rank
18
sample size
20189
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.4 (High)
confidence lower
1479.1527898181566
confidence upper
1488.3988378360184
Original result ↗

Published prices

1–20 / 62

openai/gpt-5.4 ↗

$0.25

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 ↗

$2.50

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 ↗

$15.00

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 ↗

$0.25

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4 ↗

$2.50

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4 ↗

$15.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.4 ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
web_search
Currency
USD
Billing conditions

openai/gpt-5.4:batch ↗

$0.13

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

openai/gpt-5.4:batch ↗

$1.25

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

openai/gpt-5.4:batch ↗

$7.50

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

openai/gpt-5.4:batch ↗

$0.01

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

openai/gpt-5.4 ↗

$0.50

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
min_inclusive
272000
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$0.25

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
max_exclusive
272001
min_inclusive
0
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$5.00

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
min_inclusive
272000
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$2.50

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
max_exclusive
272001
min_inclusive
0
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$22.50

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
min_inclusive
272000
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$15.00

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
max_exclusive
272001
min_inclusive
0
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
request
Currency
USD
Billing conditions
charge
web_search
endpoint
azure | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Web search
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$0.50

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
min_inclusive
272000
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.4 ↗

$0.25

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.4
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
max_exclusive
272000
min_inclusive
0
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–4 / 4

gpt-5.4 ↗

source model id
gpt-5.4
hosting
gateway
platforms
  • Cheaper Inference
context length
1000000
max output tokens
128000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

GPT 5.4 ↗

source model id
openai.gpt-5.4
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    GPT-5.4 ↗

    source model id
    openai/gpt-5.4
    hosting
    third-party
    platforms
    • OpenAI
    context length
    1000000
    max output tokens
    16384
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      GPT 5.4 ↗

      source model id
      openai/gpt-5.4
      hosting
      vercel-gateway
      platforms
      • Vercel AI Gateway
      context length
      1050000
      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-5.4-20260305
      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

      1–9 / 9

      cloudflareWorkersAI ↗

      field
      context_length
      value
      1000000
      normalized value
      1000000
      scope
      source-model
      source id
      cloudflareWorkersAI
      confidence
      1

      openRouter ↗

      field
      context_length
      value
      1050000
      normalized value
      1050000
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      context_length
      value
      1050000
      normalized value
      1050000
      scope
      source-model
      source id
      openRouter
      confidence
      1

      vercelAIGatewayCatalog ↗

      field
      context_length
      value
      1050000
      normalized value
      1050000
      scope
      source-model
      source id
      vercelAIGatewayCatalog
      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

      vercelAIGatewayCatalog ↗

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

      Original sources

      1–14 / 14

      OpenRouter · Model page ↗

      OpenRouter · Model page ↗

      Vercel AI Gateway · Model page ↗

      GitHub · Source snapshot ↗

      api.cheaperinference.com · Source snapshot ↗

      Amazon Web Services · Model page ↗

      Amazon Bedrock · Model documentation ↗

      Amazon Web Services · Catalog ↗

      Cloudflare AI · Catalog ↗

      GitHub · Catalog ↗

      LMArena · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      Vercel AI Gateway · Catalog ↗

      Source links

      1–9 / 9

      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