OpenAI: GPT-5 Mini
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency a…
openai/gpt-5-mini-2025-08-07
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 400000
- Published model ID
- gpt-5-mini-2025-08-07
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
41–60 / 158
158.785
- source id
- kaggleBenchmarks
- leaderboard name
- Game Arena · Score
- dimension
- general
- metric
- Game Arena · Score
- rank
- 38
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 115
- name
- Score
- version
- 1
- sort_order
- DESCENDING
- display_type
- counts
- benchmark
- id
- 45
- name
- Game Arena
- type
- SUITE
- owner
- kaggle
- version
- 1
- version_id
- 31
- maintainer_tier
- Kaggle-published
- candidate
- candidate_class
- modelVersion
- collection
- kaggleGameArena
- record_kind
- aggregate
- game_arena
- true
- attribution
- Kaggle · kaggle · Game Arena
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- Game Arena · Score
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 31/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/kaggle/game-arena/versions/1
- measurements
- name
- Score
- unit
- score
- scale
- 1
- metric
- Game Arena · Score
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 158.78459022435356
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 7.097584426850091
- minus
- 6.787874829005716
- hasUnevenConfidenceInterval
- true
- taskVersionId
- 0
- evaluationDate
- 2026-11-12T17:14:24.8808889Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 158.78459022435356
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 7.097584426850091
- minus
- 6.787874829005716
- hasUnevenConfidenceInterval
- true
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 115
- sort_order
- DESCENDING
- source_name
- Score
- display_type
- counts
- task_version
- 1
- task_display_type
- COUNTS
- normalization_status
- normalized
- published_at
- 2026-04-09T15:30:02.186914800Z
- candidate_class
- modelVersion
- methodology_url
- https://www.kaggle.com/game-arena-faq
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-mini-2025-08-07
- game_arena_rating
- Pooled Bradley–Terry rating; equal total weight per game
- metric_population
- 42
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-11-12T17:14:24.880Z
- source model id
- GPT-5 mini
- confidence lower
- 151.99671539534785
- confidence upper
- 165.88217465120366
Original result ↗17.212
- source id
- kaggleBenchmarks
- leaderboard name
- Ultimate Tic-Tac-Toe · Score
- dimension
- general
- metric
- Ultimate Tic-Tac-Toe · Score
- rank
- 38
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 38391
- name
- Score
- version
- 1
- sort_order
- DESCENDING
- display_type
- counts
- benchmark
- id
- 6202
- name
- Ultimate Tic-Tac-Toe
- type
- GAME
- owner
- kaggle
- version
- 1
- version_id
- 6226
- maintainer_tier
- Kaggle-published
- candidate
- candidate_class
- modelVersion
- collection
- kaggleGameArena
- record_kind
- aggregate
- game_arena
- true
- attribution
- Kaggle · kaggle · Ultimate Tic-Tac-Toe
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- Ultimate Tic-Tac-Toe · Score
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 6226/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/kaggle/ultimate-tic-tac-toe/versions/1
- measurements
- name
- Score
- unit
- score
- scale
- 1
- metric
- Ultimate Tic-Tac-Toe · Score
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 17.21169540267283
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 25.48369013849407
- minus
- 29.776584021199323
- hasUnevenConfidenceInterval
- true
- taskVersionId
- 0
- evaluationDate
- 2026-11-11T19:59:56.7752345Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 17.21169540267283
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 25.48369013849407
- minus
- 29.776584021199323
- hasUnevenConfidenceInterval
- true
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 38391
- sort_order
- DESCENDING
- source_name
- Score
- display_type
- counts
- task_version
- 1
- task_display_type
- COUNTS
- normalization_status
- normalized
- published_at
- 2026-07-28T19:19:16.035653200Z
- candidate_class
- modelVersion
- methodology_url
- https://www.kaggle.com/game-arena-faq
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-mini-2025-08-07
- game_arena_rating
- Game-specific rating; compare within this game and version
- metric_population
- 39
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-11-11T19:59:56.775Z
- source model id
- GPT-5 mini
- confidence lower
- -12.564888618526492
- confidence upper
- 42.6953855411669
Original result ↗0
- source id
- kaggleBenchmarks
- leaderboard name
- Go · Score
- dimension
- general
- metric
- Go · Score
- rank
- 39
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 38797
- name
- Score
- version
- 1
- sort_order
- DESCENDING
- display_type
- counts
- benchmark
- id
- 6234
- name
- Go
- type
- GAME
- owner
- kaggle
- version
- 1
- version_id
- 6258
- maintainer_tier
- Kaggle-published
- candidate
- candidate_class
- modelVersion
- collection
- kaggleGameArena
- record_kind
- aggregate
- game_arena
- true
- attribution
- Kaggle · kaggle · Go
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- Go · Score
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 6258/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/kaggle/go/versions/1
- measurements
- name
- Score
- unit
- score
- scale
- 1
- metric
- Go · Score
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 81.36567484245109
- minus
- 117.35307628503926
- hasUnevenConfidenceInterval
- true
- taskVersionId
- 0
- evaluationDate
- 2026-11-12T17:13:46.623819Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 81.36567484245109
- minus
- 117.35307628503926
- hasUnevenConfidenceInterval
- true
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 38797
- sort_order
- DESCENDING
- source_name
- Score
- display_type
- counts
- task_version
- 1
- task_display_type
- COUNTS
- normalization_status
- normalized
- published_at
- 2026-09-22T18:31:46.229644200Z
- candidate_class
- modelVersion
- methodology_url
- https://www.kaggle.com/game-arena-faq
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-mini-2025-08-07
- game_arena_rating
- Game-specific rating; compare within this game and version
- metric_population
- 39
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-11-12T17:13:46.623Z
- source model id
- GPT-5 mini
- confidence lower
- -117.35307628503926
- confidence upper
- 81.36567484245109
Original result ↗0
- source id
- kaggleBenchmarks
- leaderboard name
- Word Art · Score
- dimension
- general
- metric
- Word Art · Score
- rank
- 39
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 44050
- name
- Score
- version
- 1
- sort_order
- DESCENDING
- display_type
- counts
- benchmark
- id
- 6710
- name
- Word Art
- type
- GAME
- owner
- kaggle
- version
- 1
- version_id
- 6729
- maintainer_tier
- Kaggle-published
- candidate
- candidate_class
- modelVersion
- collection
- kaggleGameArena
- record_kind
- aggregate
- game_arena
- true
- attribution
- Kaggle · kaggle · Word Art
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- Word Art · Score
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 6729/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/kaggle/word-art/versions/1
- measurements
- name
- Score
- unit
- score
- scale
- 1
- metric
- Word Art · Score
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 133.87215946224433
- minus
- 128.7392384415225
- hasUnevenConfidenceInterval
- true
- taskVersionId
- 0
- evaluationDate
- 2026-11-11T20:02:33.211618Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 133.87215946224433
- minus
- 128.7392384415225
- hasUnevenConfidenceInterval
- true
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 44050
- sort_order
- DESCENDING
- source_name
- Score
- display_type
- counts
- task_version
- 1
- task_display_type
- COUNTS
- normalization_status
- normalized
- published_at
- 2026-08-18T17:14:51.483049400Z
- candidate_class
- modelVersion
- methodology_url
- https://www.kaggle.com/game-arena-faq
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-mini-2025-08-07
- game_arena_rating
- Game-specific rating; compare within this game and version
- metric_population
- 39
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-11-11T20:02:33.211Z
- source model id
- GPT-5 mini
- confidence lower
- -128.7392384415225
- confidence upper
- 133.87215946224433
Original result ↗27.5%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 43
Original result ↗0
- source id
- kaggleBenchmarks
- leaderboard name
- Four in a Row · Score
- dimension
- general
- metric
- Four in a Row · Score
- rank
- 43
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 2965
- name
- Score
- version
- 1
- sort_order
- DESCENDING
- display_type
- counts
- benchmark
- id
- 862
- name
- Four in a Row
- type
- GAME
- owner
- kaggle
- version
- 1
- version_id
- 844
- maintainer_tier
- Kaggle-published
- candidate
- candidate_class
- modelVersion
- collection
- kaggleGameArena
- record_kind
- aggregate
- game_arena
- true
- attribution
- Kaggle · kaggle · Four in a Row
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- Four in a Row · Score
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 844/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/kaggle/four-in-a-row/versions/1
- measurements
- name
- Score
- unit
- score
- scale
- 1
- metric
- Four in a Row · Score
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 35.888811136778656
- minus
- 49.10667362028987
- hasUnevenConfidenceInterval
- true
- taskVersionId
- 0
- evaluationDate
- 2026-11-11T20:03:06.5646949Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- unevenConfidenceInterval
- plus
- 35.888811136778656
- minus
- 49.10667362028987
- hasUnevenConfidenceInterval
- true
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 2965
- sort_order
- DESCENDING
- source_name
- Score
- display_type
- counts
- task_version
- 1
- task_display_type
- COUNTS
- normalization_status
- normalized
- published_at
- 2026-02-19T18:00:05.809078100Z
- candidate_class
- modelVersion
- methodology_url
- https://www.kaggle.com/game-arena-faq
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-mini-2025-08-07
- game_arena_rating
- Game-specific rating; compare within this game and version
- metric_population
- 43
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-11-11T20:03:06.564Z
- source model id
- GPT-5 mini
- confidence lower
- -49.10667362028987
- confidence upper
- 35.888811136778656
Original result ↗8.5%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 58
Original result ↗71.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · auto-routing
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 63
- 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
- 2026-10-01T19:04:42.411Z
- 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
- 0.7166669999999999
- accuracy_std_dev
- 0.009999999999999953
- cost_per_task_usd
- 0.1280142
- output_tokens_per_task
- 56970.52
- latency_seconds_per_task
- 531.6470400000001
- 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-mini-2025-08-07
- source model id
- openai/gpt-5-mini-2025-08-07
Original result ↗27.83%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 77
Original result ↗80.976%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · auto-routing
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 78
- 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
- 2026-10-01T19:19:28.473Z
- 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
- 0.8097645
- accuracy_std_dev
- 0.021885500000000002
- cost_per_task_usd
- 0.044968992424242425
- output_tokens_per_task
- 22388.290404040403
- latency_seconds_per_task
- 208.49561616161617
- 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-mini-2025-08-07
- source model id
- openai/gpt-5-mini-2025-08-07
Original result ↗1,204.782
- source id
- lmarena
- leaderboard name
- LMArena Vision Humor
- dimension
- multimodal
- metric
- Arena rating
- rank
- 79
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5 mini (High)
- confidence lower
- 1182.0809727749856
- confidence upper
- 1227.4835616087614
Original result ↗5.5%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 80
Original result ↗62.55%
- source id
- bfcl
- leaderboard name
- BFCL Live
- dimension
- toolUse
- metric
- Live accuracy
- rank
- 82
Original result ↗1,181.768
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Humor
- dimension
- multimodal
- metric
- Arena rating
- rank
- 85
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5 mini (High)
- confidence lower
- 1157.639984276221
- confidence upper
- 1205.895215870969
Original result ↗69.85%
- source id
- bfcl
- leaderboard name
- BFCL Non-Live AST
- dimension
- toolUse
- metric
- Non-live AST accuracy
- rank
- 87
Original result ↗1,238.373
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 88
- sample size
- 975
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5 mini (High)
- confidence lower
- 1218.6413471526598
- confidence upper
- 1258.1042237820652
Original result ↗56.2%
- source id
- sweBench
- leaderboard name
- SWE-bench Verified
- dimension
- coding
- metric
- Resolved tasks
- rank
- 89
- sample size
- 500
- evaluated at
- 2026-02-17T00:00:00.000Z
Original result ↗68.04%
- source id
- bfcl
- leaderboard name
- BFCL Non-Live AST
- dimension
- toolUse
- metric
- Non-live AST accuracy
- rank
- 90
Original result ↗58.62%
- source id
- bfcl
- leaderboard name
- BFCL Live
- dimension
- toolUse
- metric
- Live accuracy
- rank
- 90
Original result ↗1,215.8
- source id
- lmarena
- leaderboard name
- LMArena Vision English
- dimension
- multimodal
- metric
- Arena rating
- rank
- 91
- sample size
- 13405
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5 mini (High)
- confidence lower
- 1205.3059844280726
- confidence upper
- 1226.2939495350183
Original result ↗Published prices
1–20 / 42
$0.02
- 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)
$0.00
- 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)
$0.16
- 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)
$1.30
- 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)
$0.03
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing label
- Cached input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.25
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$2.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.02
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.25
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$2.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.13
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$1.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
- Billing conditions
- mode
- batch
$0.03
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/gpt-5-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.25
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/gpt-5-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/gpt-5-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- azure | openai/gpt-5-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
$0.02
- Inference provider
- vercelAIGatewayCatalog
- Platform
- openai
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- openai | openai/gpt-5-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–4 / 4
- source model id
- azure-openai/gpt-5-mini@2025-08-07
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 400000
- max input tokens
- 272000
- max output tokens
- 128000
- source model id
- gpt-5-mini
- hosting
- gateway
- context length
- 400000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- openai/gpt-5-mini
- hosting
- third-party
- context length
- 128000
- max output tokens
- 16384
- source model id
- openai/gpt-5-mini
- hosting
- vercel-gateway
- context length
- 400000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-5-mini-2025-08-07
- 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
1–15 / 15
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-05-31
- normalized value
- 2024-05-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-05-31
- normalized value
- 2024-05-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-05-31
- normalized value
- 2024-05-31
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_input_tokens
- value
- 272000
- normalized value
- 272000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- June 2024
- normalized value
- 2024-06
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models