openai/gpt-image-2

openai/gpt-image-2
by openai

OpenAI's gpt-image-2 is the next generation of the gpt-image series — a token-billed image model accessed through the standard OpenAI Images API. It's a drop-in upgrade from gpt-image-1: same SDK, same call shape, same parameters. Point your existing OpenAI client at OrcaRouter's base URL and set the model to `openai/gpt-image-2`. Pricing is $5.00 input / $30.00 output per 1M tokens, billed at cost — zero markup, zero migration.

p50 TTFT10.21 s
INPUT$8.00/ 1M tokens
OUTPUT$30.00/ 1M tokens
p50 TTFT10.21 s7d
p95 TTFT10.21 s7d
TRAFFIC2.3Mtokens / 7d

OpenAI GPT-Image-2 is a multimodal model from OpenAI that specializes in generating and editing images. It accepts text prompts and optional image inputs to produce modified or entirely new visual…

What is OpenAI GPT-Image-2?

Who is GPT-Image-2 designed for?

How does GPT-Image-2 differ from standard GPT-4o?

What are the key limitations of GPT-Image-2?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1

Pricing

Pricing
Input / 1M tokens$8.00
Output / 1M tokens$30.00
Cache read / 1M$1.25
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $146 · With prompt caching $122

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.0152

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
10.21 s
Output speed
4908 tok/s
p95 TTFT
10.21 s
Error rate
38.6%

Public benchmarks

AA Image Arena Elo
1338
LM Arena Image Edit Elo
1467
LM Arena Text-to-Image Elo
1393
Source: artificialanalysis.ai, lmarena.ai

Community buzz

What developers are saying this week

Hacker News3 mentions · 7d

How it compares

openai/gpt-image-2GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$8.00$21.00$60.00$5.00
Output $/M$30.00$168.00$270.00$30.00
Context400K1.1M
Quality10/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to run GPT-Image-2 via OrcaRouter?
The cost is $8.00 per million input tokens and $30.00 per million output tokens. OrcaRouter adds zero markup; you are billed exactly the provider rate.
What context window does GPT-Image-2 support?
OpenAI has not publicly disclosed a specific context window for GPT-Image-2. The model processes prompts and images as tokens; the effective input token limit depends on the combined size of the text and image. For practical purposes, prompts should be concise and image sizes should not exceed recommended limits from OpenAI's API documentation.
What are the main strengths of GPT-Image-2?
Its main strength is image editing, as demonstrated by an LM Arena Image Edit Elo score of 1467.0. It accurately modifies objects, styles, and compositions based on text instructions while preserving image coherence.
How does GPT-Image-2 compare to DALL-E 3?
DALL-E 3 excels at generating images from scratch, while GPT-Image-2 is optimized for editing existing images. The LM Arena benchmark indicates GPT-Image-2 has superior editing capability, but DALL-E 3 may be preferred for pure text-to-image generation.
How does OrcaRouter handle data when using GPT-Image-2?
OrcaRouter acts as a relay and does not store your prompts or images. Data is forwarded to OpenAI's API for processing, subject to OpenAI's privacy and data handling policies. You should review OpenAI's data policy to understand how they handle your data.
Can I call GPT-Image-2 using the same code as OpenAI's API?
Yes, OrcaRouter provides an OpenAI-compatible API. Simply change the base URL to https://api.orcarouter.ai/v1 and set the model to "openai/gpt-image-2". The request and response formats are identical.
What is the model ID for GPT-Image-2 on OrcaRouter?
The model ID is exactly "openai/gpt-image-2". Use this string in the model parameter of your API request.
Are there any rate limits for GPT-Image-2 through OrcaRouter?
Rate limits are determined by both OrcaRouter and OpenAI. OrcaRouter applies reasonable limits to ensure fair usage, while OpenAI enforces its own tier-based limits. You can monitor usage via the OrcaRouter dashboard and adjust request frequency accordingly.

Embed this badge

openai/gpt-image-2$8.00/M in10211ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-image-2" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-image-2.svg" alt="openai/gpt-image-2 on OrcaRouter" /> </a>
Markdown [![openai/gpt-image-2](https://www.orcarouter.ai/embed/openai/gpt-image-2.svg)](https://www.orcarouter.ai/models/openai/gpt-image-2)

Model card as data

GET /api/public/models/openai/gpt-image-2Open
Machine-readable:/llms.txt/llms-full.txt