OpenAI · Image model

GPT Image 2 in Twistavo AI Studio

GPT Image 2 is OpenAI's image generation and editing model; GPT Image 2.5 is a later version. Twistavo AI Studio offers GPT Image 2 and GPT Image 2.5. The cheapest run costs 3 credits: GPT Image 2.5 at 1K, quoted before you confirm.

Try GPT Image 2

Facts checked

Credits

Credit quote per run at each variant's default settings: one image, or one clip at the default length and resolution named in the row. Your exact quote appears in AI Studio before you confirm.
VariantCredits
GPT Image 261 credits
GPT Image 2.53 credits

Credits come from monthly plans and one-time extra credits for subscribers: see Pricing.

Versions compared

Versions in Twistavo AI Studio, credits per run as quoted today
VersionTypeResolutionsFrame shapesInputsPrice per runWhat the maker says, and what Twistavo offers
GPT Image 2Image1K, 2K, 4K1:1, 4:3, 3:4, 16:9, 21:9, 9:16, 3:2, 2:3, 4:5, 5:4Prompt + reference images (up to 8)31 credits (1K) · 61 credits (2K) · 103 credits (4K)

OpenAI: a model for fast, high-quality image generation and editing, with flexible image sizes and high-fidelity image inputs. source

On Twistavo: inputs: prompt, reference images; 1K, 2K and 4K

GPT Image 2.5Image1K, 2K, 4K1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4Prompt + reference images (up to 8)3 credits (1K) · 5 credits (2K) · 7 credits (4K)

OpenAI: GPT Image 2.5 comes as Sunburst, for work where editing precision matters most, and Flare, for fast, high-quality everyday image generation. source

On Twistavo: inputs: prompt, reference images; 1K, 2K and 4K

Sources

Samples

AI-generated with GPT Image 2: Hand-painted wooden sign that reads FRESH BREAD above the door of a rustic stone bakery, morning light, flowers in window boxes
AI-generated with GPT Image 2Hand-painted wooden sign that reads FRESH BREAD above the door of a rustic stone bakery, morning light, flowers in window boxesaspectRatio 4:5, quality medium, resolution 1kMade 2026-11-16 · 11 credits at these settingsUse this prompt
AI-generated with GPT Image 2: Watercolor illustration of a red fox reading a book under an oak tree, children's picture book style, soft washes, white paper border
AI-generated with GPT Image 2Watercolor illustration of a red fox reading a book under an oak tree, children's picture book style, soft washes, white paper borderaspectRatio 3:2, quality medium, resolution 1kMade 2026-11-16 · 11 credits at these settingsUse this prompt
AI-generated with GPT Image 2: Premium mobile app icon artwork: a hyper-realistic, playful 3D render in a glossy toy-commercial style. A single hero object fills the square: a glossy 3D golden retriever head with a sly talk-show smile and a tiny chrome microphone in front of its mouth. Extreme close-up — the object occupies about 80% of the frame with a bold simple silhouette, chunky rounded forms, and minimal fine detail, clearly readable even as a tiny thumbnail. Background: deep-charcoal stage tone with warm spotlight vignette. Dramatic cinematic lighting, strong specular highlights and reflections on the object, punchy contrast, crisp studio-quality render. NO text, NO letters, NO logo, NO watermark, NO border, NO rounded-corner mask, NO small scattered elements — full-bleed square composition.
AI-generated with GPT Image 2Premium mobile app icon artwork: a hyper-realistic, playful 3D render in a glossy toy-commercial style. A single hero object fills the square: a glossy 3D golden retriever head with a sly talk-show smile and a tiny chrome microphone in front of its mouth. Extreme close-up — the object occupies about 80% of the frame with a bold simple silhouette, chunky rounded forms, and minimal fine detail, clearly readable even as a tiny thumbnail. Background: deep-charcoal stage tone with warm spotlight vignette. Dramatic cinematic lighting, strong specular highlights and reflections on the object, punchy contrast, crisp studio-quality render. NO text, NO letters, NO logo, NO watermark, NO border, NO rounded-corner mask, NO small scattered elements — full-bleed square composition.aspectRatio 1:1, quality high, resolution 2kMade 2026-09-17 · 61 credits at these settingsUse this prompt
AI-generated with GPT Image 2: behance / dribbble style design, 2026 motion design vibe. pick 4 DIFFERENT random current motion design styles — doesn't have to be 3D, could be 2D flat / kinetic typography / abstract liquid / editorial poster / glassmorphic / brutalist / collage / etc. something that could be made in After Effects. each of the 4 elements is a DIFFERENT random visual language — different palette per frame, different texture register per frame, different energy per frame. 4 distinct random styles across 4 frames, each beautiful in its own way. make a board of 4 elements in one image, 2x2 layout, clean dark background between frames. lean toward dark cinematic energy.
AI-generated with GPT Image 2behance / dribbble style design, 2026 motion design vibe. pick 4 DIFFERENT random current motion design styles — doesn't have to be 3D, could be 2D flat / kinetic typography / abstract liquid / editorial poster / glassmorphic / brutalist / collage / etc. something that could be made in After Effects. each of the 4 elements is a DIFFERENT random visual language — different palette per frame, different texture register per frame, different energy per frame. 4 distinct random styles across 4 frames, each beautiful in its own way. make a board of 4 elements in one image, 2x2 layout, clean dark background between frames. lean toward dark cinematic energy.aspectRatio 3:2, quality high, resolution 2kMade 2026-08-24 · 61 credits at these settingsUse this prompt
AI-generated with GPT Image 2.5: Photorealistic full-body photo of a fictional person (not resembling any real or famous person): an adult woman in her early 30s with short curly black hair and warm brown skin, wearing a bright yellow knit sweater, light blue jeans and white sneakers, natural smile, standing facing the camera, plain light grey studio background, soft even lighting, sharp focus, realistic skin texture
AI-generated with GPT Image 2.5Photorealistic full-body photo of a fictional person (not resembling any real or famous person): an adult woman in her early 30s with short curly black hair and warm brown skin, wearing a bright yellow knit sweater, light blue jeans and white sneakers, natural smile, standing facing the camera, plain light grey studio background, soft even lighting, sharp focus, realistic skin textureaspectRatio 9:16, background auto, quality low, resolution 1k, variant flareMade 2026-11-01 · 3 credits at these settingsUse this prompt
AI-generated with GPT Image 2: Breathtaking cinematic fantasy matte painting, a floating island with a fairy-tale castle and waterfalls pouring into a sea of clouds, golden hour light, epic scale, ultra detailed, vertical composition, no text
AI-generated with GPT Image 2Breathtaking cinematic fantasy matte painting, a floating island with a fairy-tale castle and waterfalls pouring into a sea of clouds, golden hour light, epic scale, ultra detailed, vertical composition, no textaspectRatio 3:4, quality high, resolution 2kMade 2026-10-14 · 61 credits at these settingsUse this prompt
AI-generated with GPT Image 2: Photorealistic casual iPhone-style close-up selfie angle: Bruno, a 4-year-old cream-golden retriever male dog with a soft fluffy coat, warm brown eyes, a small white patch on the chest and slightly floppy ears, face filling the frame, big confident grin, outdoors in a backyard with soft bokeh, natural golden-hour light. No text, no watermark, no logo.
AI-generated with GPT Image 2Photorealistic casual iPhone-style close-up selfie angle: Bruno, a 4-year-old cream-golden retriever male dog with a soft fluffy coat, warm brown eyes, a small white patch on the chest and slightly floppy ears, face filling the frame, big confident grin, outdoors in a backyard with soft bokeh, natural golden-hour light. No text, no watermark, no logo.aspectRatio 4:5, quality high, resolution 2kMade 2026-09-17 · 61 credits at these settingsUse this prompt

Limits and known issues

  • OpenAI marks gpt-image-2 as deprecated in its API. source
  • OpenAI points new integrations to GPT Image 2.6 Sunburst or Flare. source
  • Text in images has improved, but the model can still struggle with precise text placement and clarity (OpenAI). source
  • Recurring characters or brand elements may not stay consistent across several generations (OpenAI). source
  • Elements may not land exactly where asked in structured or layout-sensitive compositions (OpenAI). source
  • Complex prompts may take up to 2 minutes to process (OpenAI). source
  • All prompts and generated images are filtered according to OpenAI's content policy. source

How to get good results

  1. Name the subject and what the image is for, such as a product photograph, an advertisement or a diagram, then the composition and frame shape (from OpenAI's GPT Image 2.6 and 2.5 prompting guide). source
  2. Describe what can be seen: materials, lighting, colours and medium; ask for photorealistic explicitly when that is the goal (from OpenAI's GPT Image 2.6 and 2.5 prompting guide). source
  3. Put required wording in quotes, say where it goes and in which lettering, spell unusual words letter by letter, then check the spelling in the result (from OpenAI's GPT Image 2.6 and 2.5 prompting guide). source
  4. For an edit, say change only one thing and list what must stay: identity, geometry, layout, lighting or labels (from OpenAI's GPT Image 2.6 and 2.5 prompting guide). source
  5. With several reference images, refer to each by its number and give it one role: subject, style, clothing or background (from OpenAI's GPT Image 2.6 and 2.5 prompting guide). source
  6. Use a low quality level for quick drafts, then compare higher levels for the final image (OpenAI). source

Video tutorial

GPT Image 2: Price per Image and How to Use It (2026)

Questions

Where is the newest GPT Image version?

It has its own page, linked from the model list, with a comparison against the version listed here.

Can it make a transparent PNG?

Yes, the background setting offers a transparent option alongside automatic and opaque.

Which inputs does it take?

A prompt plus reference images.

Which sizes are available?

The composer offers 1k, 2k and 4k, and frame shapes including 1:1, 4:3, 3:4, 16:9, 21:9, 9:16, 3:2, 2:3, 4:5, 5:4, 27:16, 16:27, 9:8 and 8:9.

Can I lower the cost of a run?

Choose a lower quality level or a smaller size, then rerun only the images you keep at a higher setting. The quote updates as you change each setting.

How much does GPT Image 2 cost?

Prices per image in Twistavo AI Studio: GPT Image 2: 31 credits at 1K, 61 credits at 2K and 103 credits at 4K. GPT Image 2.5: 3 credits at 1K, 5 credits at 2K and 7 credits at 4K.

Is GPT Image 2 available for free?

GPT Image 2 runs are paid in credits in Twistavo AI Studio. 1 free image after signup, no card (GPT Image 2.6, 1k). Videos need a plan. Plans from $3.99/month. Credits never expire and every generation is quoted before it starts.

How do I get GPT Image 2?

Developers call it through OpenAI's Image API as gpt-image-2, for generations and edits; OpenAI now marks that model deprecated. In Twistavo AI Studio, open the image composer, pick GPT Image 2 or GPT Image 2.5 in the model list, write the prompt, add reference images if you want, then confirm the quote.

Can GPT Image 2 make 4K images?

Yes. OpenAI lists 3840x2160 and 2160x3840 among the popular gpt-image-2 sizes, and in Twistavo AI Studio both versions offer 1K, 2K and 4K. GPT Image 2: 31 credits at 1K, 61 credits at 2K and 103 credits at 4K.

GPT Image 2 is a trademark of OpenAI. Twistavo is an independent product, not affiliated with or endorsed by OpenAI; it offers the model through its AI provider. Facts on this page come from the AI Studio catalogue and may change with the provider.