OpenAI: GPT Image 1
OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits.
openai/gpt-image-1
OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits.
Specifications & capabilities
- Input
- text, image
- Output
- image
- Context window · tokens
- 400000
- Capabilities
- imageOutput, multimodal, promptCaching, structuredOutputs, visionInput
Evaluations
1–10 / 10
1,126.377
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Multi Image Edit
- dimension
- multimodal
- metric
- Arena rating
- rank
- 40
- sample size
- 1826123
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1122.6381345452758
- confidence upper
- 1130.1154857597362
Original result ↗1,115.066
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Cartoon
- dimension
- multimodal
- metric
- Arena rating
- rank
- 52
- sample size
- 104668
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1110.4099207526413
- confidence upper
- 1119.7228112126434
Original result ↗1,114.961
- source id
- lmarena
- leaderboard name
- LMArena Text To Image 3d Modeling
- dimension
- multimodal
- metric
- Arena rating
- rank
- 52
- sample size
- 23934
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1108.3771196280538
- confidence upper
- 1121.545787245512
Original result ↗1,114.875
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 52
- sample size
- 265925
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1111.6862777274855
- confidence upper
- 1118.0629965138237
Original result ↗1,116.532
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Art
- dimension
- multimodal
- metric
- Arena rating
- rank
- 53
- sample size
- 33532
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1110.384307584369
- confidence upper
- 1122.67881239508
Original result ↗1,114.511
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Commercial Design
- dimension
- multimodal
- metric
- Arena rating
- rank
- 54
- sample size
- 81577
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1110.0220563393923
- confidence upper
- 1119.0008111195693
Original result ↗1,113.996
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Text Rendering
- dimension
- multimodal
- metric
- Arena rating
- rank
- 55
- sample size
- 71560
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1109.267422719432
- confidence upper
- 1118.7246392083898
Original result ↗1,114.09
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Portraits
- dimension
- multimodal
- metric
- Arena rating
- rank
- 57
- sample size
- 65457
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1108.5500306586061
- confidence upper
- 1119.629338877739
Original result ↗1,113.393
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Photorealistic
- dimension
- multimodal
- metric
- Arena rating
- rank
- 57
- sample size
- 118205
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1108.9691765869984
- confidence upper
- 1117.8158606220618
Original result ↗1,138.777
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 59
- sample size
- 2858283
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-1
- confidence lower
- 1136.0295031681123
- confidence upper
- 1141.5235085940894
Original result ↗Published prices
1–4 / 4
$1.25
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$10.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$10.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-image-1
- 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
1–2 / 2
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 360000
- normalized value
- 360000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models