# GPT: Image 2

## Facts

- Model name: gpt-image-2
- Maker: OpenAI
- Context window: 1,024 tokens
- Price: $0.012 per image
- Providers: 1 independent provider
- Regions: global

## Providers

- [EmpirioLabs AI](https://liquidinference.ai/providers/4f49f07c-0d26-44bd-88a8-34f3f5fbd3b7.md): global, $0.012 per image, 1,024 tokens of context

## Scores

- HLE: 37.7, #61 of 273
- GPQA: 90.3, #43 of 250
- AA-LCR: 82.7, #21 of 237
- Terminal-Bench Hard: 47.0, #14 of 166
- LiveCodeBench: 88.9, #3 of 130
- AIME 2025: 99.0, #1 of 100
- MMLU-Pro: 87.4, #5 of 133
- τ²-Bench: 84.8, #52 of 169
- IFBench: 75.4, #19 of 178
- SimpleQA Verified: 34.3, #61 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## Request

```sh
curl https://router.inference.ai.exchange/v1/images/generations \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "a cat on a bicycle"
  }'
```

## Questions

### What is GPT: Image 2?

GPT: Image 2 is a model from OpenAI.

### How much does GPT: Image 2 cost?

Offers now ask $0.012 image.

### What is the context length of GPT: Image 2?

The largest offer takes 1,024 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can GPT: Image 2 do?

Its providers list Text.

### What inputs and outputs does GPT: Image 2 support?

Text → Text · Images.

### Which providers serve GPT: Image 2?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call GPT: Image 2?

Send "gpt-image-2" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was GPT: Image 2 listed?

The exchange first listed it on 10/17/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/gpt-image-2)
- [Set up a client](https://liquidinference.ai/connect/gpt-image-2)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)
