Amux AI

OpenAI: GPT-Image-2

Active

OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.

By:
OpenAI
Input:
Output:
Context length:
10K
Published:
2026-04-22
streamingvisioncaching

Providers

Same model, different providers. Automatic routing spreads requests across healthy providers by default, or ranks them by price, latency and more.

Provider
20% offLowestazure
Input$5$4/1M tokensImage input (tokens)$8$6.4/1M tokens
Image output (tokens)$30$24/1M tokens
Read$1.25$1/1M tokensWrite—Cached image input$2$1.6/1M tokens
10K0.00%——
amux-special—
1K$0.015/image2K$0.015/image4K$0.015/image
Read—Write—
10K0.00%——

Availability

24 hours · 10/19–10/22

Success rate of requests sent by the Amux AI gateway to each provider. Client errors are excluded.

Activity

24 hours · 10/19–10/22

Relative request activity over time, broken down by serving provider. Indexed to the peak within the selected range (= 100); reflects trends and provider share, not absolute volume.

Related models

More models from OpenAI

OpenAI: GPT Image 2.5 Flare10K contextfrom $4 / M tokens2 providersGPT Image 2.5 Flare is an image generation and editing model from OpenAI, positioned as the speed-oriented tier of the GPT Image 2.5 series. It is suited to high-volume everyday generation, creator content, and rapid prototyping via the dedicated Images API.
OpenAI: GPT Image 2.5 Sunburst10K contextfrom $4 / M tokens2 providersGPT Image 2.5 Sunburst is an image generation and editing model from OpenAI, positioned as the precision-oriented tier of the GPT Image 2.5 series. It is suited to detailed creative work where editing accuracy matters more than generation speed, via the dedicated Images API.
OpenAI: GPT-6.1 Sol1.05M contextfrom $0.1 / M tokens2 providersGPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.