How RelayRouter pricing works: 30 percent below official with no platform fee
RelayRouter pricing combines group settlement rates with a $0 platform fee. Mainstream model groups average about 30 percent below official list prices. GPT usage settles at CNY 0.6 per $1 of standard usage and Claude at CNY 2.0, against a CNY 6.8 market reference. There is no minimum spend and no subscription, and failed or errored requests are generally not billed. Live per-model rates are listed at relayrouter.io/models.
How do group settlement rates work?
RelayRouter bills mainstream model groups by converting each $1 of standard usage into a fixed CNY settlement rate. According to the relayrouter.io/models catalog, the GPT group settles at CNY 0.6 per $1 of standard usage and the Claude group settles at CNY 2.0 per $1. Both are measured against a CNY 6.8 per $1 market reference. The catalog lists about 108 models across 19 public groups, so most rates are set per group. Across mainstream groups, the average is about 30 percent below official list prices. Current figures for each model are published on the RelayRouter models page.
| Group or model | Example model IDs | Pricing method | Rate |
|---|---|---|---|
| GPT group | gpt-6-astra, gpt-5.6-sol | Group settlement | CNY 0.6 per $1 (market reference CNY 6.8) |
| Claude group | claude-opus-5-5, claude-fable-5-1, claude-opus-5 | Group settlement | CNY 2.0 per $1 (market reference CNY 6.8) |
| DeepSeek | deepseek-v4-flash | Direct pricing | 1.1x DeepSeek official time-of-day prices |
How is deepseek-v4-flash priced?
deepseek-v4-flash uses direct pricing at 1.1x DeepSeek official time-of-day prices instead of a group settlement rate. Off-peak, input costs CNY 1.1 per 1M tokens and output costs CNY 4.4 per 1M tokens. During weekday peak windows (09:00 to 12:00 and 14:00 to 18:00 Beijing time), both prices double, to CNY 2.2 per 1M input tokens and CNY 8.8 per 1M output tokens. Teams running batch workloads on this model can schedule them outside those windows to stay on off-peak rates. The catalog also includes GLM, MiniMax, Moonshot and Gemini 3.8 Flash (gemini-3.8-flash), each with its own rate listed on the models page.
Which costs does RelayRouter not charge?
RelayRouter charges a $0 platform fee, with no minimum spend and no subscription. The billable item is usage: you pay for the tokens consumed at the rate of the model or group you call. Failed or errored requests are generally not billed, so an attempt that fails upstream does not add cost for that attempt. Because there is no subscription, there is no plan tier to purchase before sending requests. Payments are made by Stripe card, and API keys are created in the RelayRouter dashboard. To estimate spend, check the per-model rate on the models page and multiply it by your expected token volume.
Does switching to RelayRouter require code changes?
Switching requires changing the base URL and API key, not your application code. RelayRouter is “Compatible with the OpenAI, Anthropic and Gemini protocols”, according to relayrouter.io. The guidance in the relayrouter.io docs is: “Keep your existing SDK, change base_url and the key, no other code changes.” OpenAI clients call POST /v1/chat/completions with base https://relayrouter.io/v1. Anthropic clients call POST /v1/messages with base https://relayrouter.io. Gemini clients call POST /v1beta/models/{model}:generateContent. Authentication uses the header Authorization: Bearer YOUR_API_KEY, and streaming is supported. Full endpoint details are in the RelayRouter docs.
FAQ
These answers cover common RelayRouter billing questions.
Is there a monthly or platform fee?
No. RelayRouter has a $0 platform fee, no subscription and no minimum spend. You are billed for usage.
Am I charged for failed requests?
Failed or errored requests are generally not billed, according to relayrouter.io.
Where can I find current per-model prices?
Live rates for about 108 models across 19 public groups are listed at relayrouter.io/models.
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.