Image model proxy

GPT-image-2 API Proxy Providers

Compare AI proxy platforms that offer GPT-image-2 image generation, image editing, and high-resolution output routes. The directory covers platforms with GPT-image-2 image generation access through third-party API providers, with model IDs, Base URL access, 4K/2K labels, pricing notes, and payment methods collected in one place.

gpt-image-2中转站 gpt-image-2中转站接口 gpt-image-2 api gpt-image-2 proxy gpt image 2 api GPT Image 2 4K GPT Image 2 2K

Quick filters

By model

Site list(14)

derouter.ai logo

derouter.ai

Public model pricing is shown in USD per 1M tokens: Claude Fable 5 at $2.45 input and $12.23 output; Claude Opus 4.8 / 4.7 / 4.6 at $1.22 input and $6.11 output; Claude Sonnet 5 / 4.6 at $0.73 input and $3.67 output; and Claude Haiku 4.5 at $0.24 input and $1.22 output. GPT tiers range from $0.071-$0.48 input and $0.43-$2.85 output. GPT Image 2 costs $0.0084 at 1K, $0.0126 at 2K, and $0.0168 at 4K. Minimum top-up is $10.

2.99KAbout 24% of official rates, saving about 76%$102
kukuai logo

kukuai

Public model pricing is shown per million tokens. Examples include gpt-5.4-mini at ¥0.1950 input / ¥0.8325 output, gpt-5.3-codex at ¥0.3300 input / ¥3.3000 output, claude-sonnet-4-6 at ¥0.8580 input / ¥3.9600 output, and gemini-3.1-pro at ¥1.5400 input / ¥9.2400 output. The packages page lists seven one-time plans priced at ¥6.8, ¥13.6, ¥68, ¥136, ¥272, ¥340, and ¥680, including ¥8, ¥15, ¥80, ¥149, ¥300, ¥374, and ¥800 in site credit respectively. The first six are valid for 30 days, while the ¥680 plan is valid for 90 days; official-equivalent credit varies by model.

$0.01 ≈ $1¥6.850
DeepKey logo

DeepKey

Top-ups are settled at ¥1 = $1 credit, with a ¥5 minimum. Model usage is charged by group multipliers or fixed prices. The comparable cost is recorded from the gpt group, mainly Pro accounts, at 0.2x, or about ¥0.20 per $1 list-price usage. Stable groups recorded here include: gpt 0.2x, gpt-enterprise 0.6x, gpt-azure 1.2x, gpt-image 0.1x; cx2cc 0.2x; gemini 0.3x, gemini-t3 1.8x; claude 0.4x, claude-anti 0.3x, claude-copilot 0.5x, claude-free 0.25x, claude-pro 1.2x, claude-ai / claude-api 3x, claude-aws-platform 2.2x, claude-max 1.8x, claude-max-any-client 1.6x, claude-kiro 0.45x, and claude-windsurf 0.35x. Limited-time, special-price, discount, sale, and out-of-stock-prone groups are excluded.

28.93K$0.02 ≈ $1¥515
XAI XAPI logo

XAI XAPI

The current featured Codex programming plans support Codex CLI/App/API access and Claude API mapping for Claude Code; plans are valid for 31 days. The lightweight trial is ¥59 for ¥800 card balance, about ¥0.517 per $1; the starter plan is ¥99 for ¥2000 card balance, about ¥0.347 per $1; the ¥198/¥396/¥792 plans provide ¥4000/¥8000/¥16000 card balance, all about ¥0.347 per $1; the enterprise exclusive plan is ¥2000 for ¥100000 card balance, with gpt-image-2, a 20x Pro account, 16 subaccounts, and an enterprise service group, about ¥0.140 per $1.

4.82K$0.05 ≈ $1¥10

Call GPT-image-2 with a proxy Base URL

Use a provider API key, replace the Base URL with the gateway shown in that provider's dashboard, and start with a minimal image generation request before testing 2K, 4K, or edit routes.

Compatibility varies by provider. Some routes rename size, quality, or edit parameters, so verify the provider docs and billing page before sending large batches.

curl <BASE_URL>/images/generations \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A minimal app icon.",
    "size": "1024x1024",
    "n": 1
  }'

Related guides

Related topics

FAQ

GPT-image-2 API, 4K/2K, and Base URL

What can a GPT-image-2 API proxy do?

A GPT-image-2 API proxy is usually used for image generation and image editing through a third-party AI proxy service. Provider pages commonly expose an API key, Base URL, model ID, image generation endpoint, and image edit endpoint.

How do GPT Image 2 4K and 2K sizes work?

GPT Image 2 4K and 2K usually refer to high-resolution image output routes, such as 2048px-level 2K images or 3840 x 2160 4K images. Provider pages often list supported sizes, quality levels, and whether custom sizes are accepted.

How is GPT-image-2 connected through an OpenAI-compatible Base URL?

Many GPT-image-2 API proxy providers describe OpenAI-compatible access: set the SDK base URL to the provider gateway, use the provider API key, and call an image generation or image edit route with the model ID gpt-image-2.

How is GPT-image-2 API pricing usually shown?

GPT-image-2 API proxy pricing is often shown by image, credit balance, model route, quality level, or token usage. 2K and 4K images may use different pricing rules from standard 1024px images, depending on the provider.