DeepSeek, MiniMax and Moonshot models via an OpenAI compatible gateway
Update (2026-11-08): the MiniMax text-model group has been retired on RelayRouter, so the MiniMax parts of this guide no longer apply. The DeepSeek and Moonshot (Kimi) sections remain valid; the models page has the live list and rates.
RelayRouter provides DeepSeek, MiniMax and Moonshot models, alongside Claude, GPT and Gemini, through an OpenAI compatible endpoint (POST /v1/chat/completions, base URL https://relayrouter.io/v1). You keep your existing OpenAI SDK, change the base URL and API key, and select a model ID such as deepseek-v4-flash. The catalog lists about 108 models across 19 public groups, with a $0 platform fee and no minimum spend.
Which DeepSeek, MiniMax and Moonshot models are available?
DeepSeek, MiniMax and Moonshot are listed as model families in the RelayRouter catalog, next to GLM, Claude, GPT and Gemini. According to relayrouter.io/models, the catalog contains about 108 models organized into 19 public groups. Other families in the catalog include the Claude line (for example claude-opus-5-5, claude-fable-5-1 and claude-opus-5), GPT-6 and GPT-5.6 (gpt-6-astra, gpt-5.6-sol), and Gemini 3.8 Flash (gemini-3.8-flash). One documented DeepSeek model ID is deepseek-v4-flash. Exact model IDs for MiniMax and Moonshot, along with live per-model rates, are published on the models page, so check that page before hard-coding a model name in your application.
How do you call these models with the OpenAI SDK?
You call them by pointing your existing OpenAI SDK at https://relayrouter.io/v1 and using a RelayRouter API key. According to the relayrouter.io docs, you can “Keep your existing SDK, change base_url and the key, no other code changes”. Create a key in the dashboard and send it as Authorization: Bearer YOUR_API_KEY. A Python example:
from openai import OpenAI
client = OpenAI(base_url="https://relayrouter.io/v1", api_key="YOUR_API_KEY")
resp = client.chat.completions.create(model="deepseek-v4-flash", messages=[{"role": "user", "content": "Hello"}])
Streaming is supported on the same endpoint. To switch from DeepSeek to a MiniMax or Moonshot model, change the model value to the ID listed on the models page. The request and response format stays the same, so the rest of your code does not need to change. See the documentation for full details.
Which API protocols does the gateway support?
The gateway supports three request formats: OpenAI, Anthropic and Gemini. According to the official relayrouter.io site, the service is “Compatible with the OpenAI, Anthropic and Gemini protocols”. This means a team using an Anthropic or Gemini SDK can also route traffic through RelayRouter, while DeepSeek, MiniMax and Moonshot can be reached through the OpenAI compatible format described above.
| Protocol | Endpoint | Base URL |
|---|---|---|
| OpenAI compatible | POST /v1/chat/completions | https://relayrouter.io/v1 |
| Anthropic compatible | POST /v1/messages | https://relayrouter.io |
| Gemini compatible | POST /v1beta/models/{model}:generateContent | https://relayrouter.io |
All three formats use the same API key and the same account balance.
How are DeepSeek requests priced?
DeepSeek requests are billed directly per token, at 1.1x DeepSeek official time-of-day prices. According to relayrouter.io/models, deepseek-v4-flash costs CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens during off-peak hours. These prices are doubled on weekdays from 09:00 to 12:00 and from 14:00 to 18:00 Beijing time, so scheduling batch jobs outside those windows lowers cost. Other groups use settlement rates instead: 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. There is a $0 platform fee, no minimum spend and no subscription. Payment is by Stripe card, and failed or errored requests are generally not billed.
FAQ
Do I need a separate SDK for DeepSeek, MiniMax or Moonshot?
No. You can use the OpenAI SDK with the base URL https://relayrouter.io/v1 and a RelayRouter API key, then set the model ID.
Is there a monthly fee or minimum spend?
No. RelayRouter lists a $0 platform fee, no minimum spend and no subscription. You pay for usage at the rates on the models page.
Am I charged when a request fails?
Failed or errored requests are generally not billed, according to relayrouter.io.
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.