aiml/openai/gpt-image-2
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsaiml/openai/gpt-image-2
AI model
- API mode
- Image generation*
No matched benchmark results are available for this entry yet.
Run it locally
Capabilities
- API mode
- Image generation*
- Image input
- Yes*
System configuration
Detailed specifications
Specifications · 6 fields
- litellm provider
- aiml*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- metadata
- notes
- OpenAI gpt-image-2 via AI/ML API - flagship multimodal image generation and editing model with reasoning and 2K output. output_cost_per_image is AI/ML's published medium-quality rate; like the other aiml image entries it is billed as a flat per-image price*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- mode
- image_generation*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per image
- 0.054*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported endpoints
- /v1/images/generations*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports vision
- Yes*
Scope and conditions
- native_context
- provider
- aiml*
- mode
- image_generation*
- full_native_model_id
- aiml/openai/gpt-image-2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
0 selected Compare 0
* Provisional data