Models & Pricing

Listing models

Retrieve the current list of available models at any time:

curl https://api.ru-llm.relay2.xyz/v1/models \
  -H "Authorization: Bearer sk-ru-YOUR_KEY"

The response follows the OpenAI models list format:

{
  "object": "list",
  "data": [
    {"id": "gpt-5.5", "object": "model", "owned_by": "openai"},
    {"id": "claude-sonnet-4-6", "object": "model", "owned_by": "anthropic"},
    {"id": "gemini-3.1-pro-preview", "object": "model", "owned_by": "google"}
  ]
}

Illustrative model table

The table below shows a representative set of seeded models. See the console Pricing page for live, up-to-date rates.

Model ID	Provider	Input (per 1k tokens)	Output (per 1k tokens)
gpt-5.5	OpenAI	$0.005	$0.030
claude-sonnet-4-6	Anthropic	$0.003	$0.015
claude-opus-4-8	Anthropic	$0.010	$0.050
gemini-3.1-pro-preview	Google	$0.006	$0.030

Image & video models

Model ID	Provider	Billing
gpt-image-2	OpenAI	per token (input/output)
gemini-3.1-flash-image	Google	per image
doubao-seedance-2-0-260128	ByteDance	per token

Note

Prices shown are illustrative retail rates in USD. Actual billing uses the rates shown in the console, which reflect upstream provider pricing. Cache read tokens are billed at a reduced rate for models that support prompt caching.

How billing works

• Prepaid balance — your account holds a USD balance topped up via crypto/USDT.
• Actual token billing — you are charged only for the tokens consumed (input + output).
• Cache-aware — for models with prompt caching support, cache read tokens are billed at a reduced rate. The usage field in API responses reports cache token counts separately.
• No subscription — there is no monthly fee; unused balance carries over indefinitely.

See Billing & Top-ups for details on how to add funds.