fal_ai/openai/gpt-image-2

AI model

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Not enough verified architecture information for a reliable VRAM estimate.

Specifications · 6 fields

litellm provider

fal_ai^*

Scope and conditions

native_context

provider: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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 served through fal.ai. fal bills by token but publishes deterministic per-image prices per size and quality, mirrored here as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2 that litellm's fal_ai cost calculator picks from the request params. This flat entry is the fallback when no keyed entry matches and carries the default request rate (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high^*

Scope and conditions

native_context

provider: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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

0.145^*

Scope and conditions

native_context

provider: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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

Scope and conditions

native_context

provider: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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: fal_ai^*
mode: image_generation^*
full_native_model_id: fal_ai/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.^*

* Provisional data