Image model for prompt-driven generation, editing, and visual design workflows
- Released
- 5mo ago
- Image input / 1M tokens
- $8
- Text input / 1M tokens
- $5
- Image output / 1M tokens
- $30
- Cached input / 1M tokens
- $2.00
Sources:models.devOpenRouter
Image prices are listed in the billing units published by each provider; resolution and quality can affect the final cost.
Provider pricing
Rates are shown in each provider's published units. Resolution, quality, audio, and other settings may change the final charge.
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- OpenAI
- Model family
- GPT
- Type
- Image generation
- Predecessor
- —
- Successor
- —
- Released
- April 21, 2026
- Model ID
openai/gpt-image-2- Openness
- Closed
- License
- —
- Input modalities
- text, image
- Output modalities
- image
- Modality
- text+image->image
- Aspect ratios
- 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, auto
- Quality
- auto, low, medium, high
- Images per request
- 1–10
- Reference images
- 0–16
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- openai/gpt-image-2
- Source family
- gpt-image
- Last updated
- 2026-04-21
- Model context
- —
- Model output limit
- —
- Open weights
- No
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "openai/gpt-image-2",
"name": "GPT-Image-2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"family": "gpt-image",
"last_updated": "2026-04-21",
"attachment": true,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"release_date": "2026-04-21",
"open_weights": false
}Infrastructure
Provider availability
| Provider | Endpoint | Pricing (published units) | Uptime 1d | Data handling |
|---|---|---|---|---|
| openai | $8 (Image input / 1M tokens); $5 (Text input / 1M tokens); $30 (Image output / 1M tokens) | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Text provenance
EU · product-scopedOpenAI textGrain watermarking
In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.
Official explanation