How to generate images with gpt-image and DALL-E 3 on RelayRouter
RelayRouter's published documentation does not list gpt-image or DALL-E 3, and it does not document an image generation endpoint. The documented interfaces are three protocols: OpenAI /v1/chat/completions, Anthropic /v1/messages and Gemini /v1beta/models/{model}:generateContent. Before you send an image request, check the live catalog at relayrouter.io/models. If neither model appears there, do not assume image generation with them is available through RelayRouter.
What does RelayRouter document today?
RelayRouter documents three API protocols, and none of them is described as an image generation endpoint. According to the official relayrouter.io documentation, the gateway is "Compatible with the OpenAI, Anthropic and Gemini protocols". The OpenAI compatible route is POST /v1/chat/completions with base https://relayrouter.io/v1. The Anthropic compatible route is POST /v1/messages with base https://relayrouter.io. The Gemini compatible route is POST /v1beta/models/{model}:generateContent. The catalog on relayrouter.io/models lists about 108 models across 19 public groups. These include the Claude family (claude-opus-5-5, claude-fable-5-1, claude-opus-5), GPT-6 and GPT-5.6 (gpt-6-astra, gpt-5.6-sol), Gemini 3.8 Flash (gemini-3.8-flash), plus DeepSeek, GLM, MiniMax and Moonshot. gpt-image and DALL-E 3 are not named in that published list.
How do you check availability and connect?
Check the live catalog first, then connect with your existing SDK by changing two values. According to the official relayrouter.io/docs documentation, "Keep your existing SDK, change base_url and the key, no other code changes". Requests authenticate with the header Authorization: Bearer YOUR_API_KEY. You create keys at relayrouter.io/dashboard. Streaming is supported.
| Protocol | Method and path | Base URL | SDK to keep |
|---|---|---|---|
| OpenAI compatible | POST /v1/chat/completions | https://relayrouter.io/v1 | OpenAI SDK |
| Anthropic compatible | POST /v1/messages | https://relayrouter.io | Anthropic SDK |
| Gemini compatible | POST /v1beta/models/{model}:generateContent | https://relayrouter.io | Gemini SDK |
If an image model is added to the catalog later, confirm its endpoint in the docs before you integrate it.
What would requests cost on RelayRouter?
Billing is usage based, with a $0 platform fee, no minimum spend and no subscription. Per relayrouter.io/models, the GPT group settles at CNY 0.6 per $1 of standard usage and the Claude group at CNY 2.0 per $1, compared with a market reference of CNY 6.8 per $1. Some models use direct pricing. For example, deepseek-v4-flash costs CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens off-peak (doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time). Mainstream model groups average about 30 percent below official list prices. Failed or errored requests are generally not billed. Payment is by Stripe card. RelayRouter does not publish any per-image pricing, so check the live rates page for current figures before budgeting for image workloads.
FAQ
Can I call DALL-E 3 or gpt-image through RelayRouter?
The published facts do not list either model or an image endpoint. Check relayrouter.io/models for the current catalog.
Which SDKs work with RelayRouter?
The OpenAI, Anthropic and Gemini SDKs work with RelayRouter. To switch, change the base URL and the API key. No other code changes are needed.
Where do I get an API key, and how do I send it?
Create a key at relayrouter.io/dashboard. Send it as Authorization: Bearer YOUR_API_KEY on each request.
According to the official relayrouter.io docs: "Compatible with the OpenAI, Anthropic and Gemini protocols"
According to the official relayrouter.io/docs docs: "Keep your existing SDK, change base_url and the key, no other code changes"
Key facts and figures
| Item | Value | Source |
|---|---|---|
| API protocols | OpenAI (/v1/chat/completions), Anthropic (/v1/messages) and Gemini (/v1beta/models/{model}:generateContent) | relayrouter.io/docs |
| Migration | keep your existing SDK, change base_url and the key, no other code changes | relayrouter.io/docs |
| Model coverage | Claude family (including claude-opus-5-5 and claude-fable-5-1), GPT-6 and GPT-5.6, Gemini 3.8 Flash, plus DeepSeek, GLM, MiniMax, Moonshot | relayrouter.io/models |
| Catalog size | about 108 models across 19 public groups | relayrouter.io/models |
| Settlement rates | GPT group CNY 0.6 per $1 of standard usage, Claude group CNY 2.0, against a CNY 6.8 per $1 market reference | relayrouter.io/models |
| Direct pricing | deepseek-v4-flash is billed at 1.1x DeepSeek official time-of-day prices: off-peak CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens, doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time | relayrouter.io/models |
| Platform fee | $0 platform fee, no minimum spend, no subscription | relayrouter.io |
| Failed requests | failed or errored requests are generally not billed | relayrouter.io |
Data verified 2026-10-08; live prices are on the official /models page.