OpenAI: GPT Image 2
OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.
openai/gpt-image-2
OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.
Specifications & capabilities
- Input
- text, image
- Output
- image
- Context window · tokens
- 400000
- Capabilities
- imageOutput, multimodal, promptCaching, structuredOutputs, visionInput
Evaluations
1–17 / 17
1,491.929
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Multi Image Edit Agentic
- dimension
- multimodal
- metric
- Arena rating
- rank
- 2
- sample size
- 5452
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1478.54880873953
- confidence upper
- 1505.3095331066434
Original result ↗1,462.587
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Agentic
- dimension
- multimodal
- metric
- Arena rating
- rank
- 3
- sample size
- 6127
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1450.877034838334
- confidence upper
- 1474.2965108062194
Original result ↗1,454.538
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Multi Image Edit
- dimension
- multimodal
- metric
- Arena rating
- rank
- 3
- sample size
- 158900
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1451.0102407473296
- confidence upper
- 1458.0649983242151
Original result ↗1,424.262
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Text Rendering
- dimension
- multimodal
- metric
- Arena rating
- rank
- 4
- sample size
- 37814
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1418.369334623312
- confidence upper
- 1430.155432691306
Original result ↗1,385.92
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Commercial Design
- dimension
- multimodal
- metric
- Arena rating
- rank
- 4
- sample size
- 38990
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1380.3775818877725
- confidence upper
- 1391.4622818725568
Original result ↗1,366.564
- source id
- lmarena
- leaderboard name
- LMArena Text To Image 3d Modeling
- dimension
- multimodal
- metric
- Arena rating
- rank
- 4
- sample size
- 9996
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1358.4226055419613
- confidence upper
- 1374.7046312960265
Original result ↗1,340.49
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Agentic
- dimension
- multimodal
- metric
- Arena rating
- rank
- 4
- sample size
- 3417
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1326.506300770972
- confidence upper
- 1354.4731040345443
Original result ↗1,460.915
- source id
- lmarena
- leaderboard name
- LMArena Image Edit Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 355469
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1457.8925919681978
- confidence upper
- 1463.9366292839973
Original result ↗1,427.502
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Portraits
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 19525
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1420.2582659439884
- confidence upper
- 1434.7466968174708
Original result ↗1,403.3
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Cartoon
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 42280
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1397.6570774806244
- confidence upper
- 1408.9434839103324
Original result ↗1,381.735
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 106021
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1377.8415865366223
- confidence upper
- 1385.6279324632842
Original result ↗1,379.068
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Photorealistic
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 39135
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1373.4756597818844
- confidence upper
- 1384.660632671601
Original result ↗1,371.685
- source id
- lmarena
- leaderboard name
- LMArena Text To Image Art
- dimension
- multimodal
- metric
- Arena rating
- rank
- 5
- sample size
- 13731
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-Image-2 (Medium)
- confidence lower
- 1364.6538504738285
- confidence upper
- 1378.7157069320156
Original result ↗9.852%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Image Spend Share
- dimension
- popularity
- metric
- Spend
- rank
- 5
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT Image 2
Original result ↗7.428%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Image Tokens Share
- dimension
- popularity
- metric
- Tokens
- rank
- 5
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT Image 2
Original result ↗6.551%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Image Image Count Share
- dimension
- popularity
- metric
- Image Count
- rank
- 5
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT Image 2
Original result ↗6.35%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Image Requests Share
- dimension
- popularity
- metric
- Requests
- rank
- 5
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT Image 2
Original result ↗Published prices
1–16 / 16
$1.25
- 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
$2.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- label
- Cached input image tokens (per 1M)
- Billing label
- Cached input image tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$5.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$8.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- label
- Input image tokens (per 1M)
- Billing label
- Input image tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$10.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$30.00
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- label
- Output image tokens (per 1M)
- Billing label
- Output image tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$2.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$8.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$8.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
$1.25
- Inference provider
- vercelAIGatewayCatalog
- Platform
- openai
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- openai | openai/gpt-image-2
- model_type
- image
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$5.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- openai
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- openai | openai/gpt-image-2
- model_type
- image
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$30.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- openai
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- openai | openai/gpt-image-2
- model_type
- image
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.25
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- image
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$5.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- image
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$30.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- image
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–3 / 3
- source model id
- gpt-image-2
- hosting
- gateway
- context length
- 128000
- max output tokens
- 65536
- source model id
- openai/gpt-image-2
- hosting
- third-party
- source model id
- openai/gpt-image-2
- hosting
- vercel-gateway
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-image-2
- 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