Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ruapi.ai/llms.txt

Use this file to discover all available pages before exploring further.

RuAPI aggregates models from major AI providers behind a single endpoint. One API key — dozens of models, no separate accounts at each vendor.

​
Major providers

OpenAI

GPT-4o, GPT-4o-mini, o1, o3 and the rest of the family.

Anthropic Claude

Claude 3.5/3.7 Sonnet, Claude Haiku, Claude Opus.

Google Gemini

Gemini 2.0 Flash, Gemini 1.5 Pro and experimental models.

xAI Grok

Grok 2, Grok 3 — models from xAI.

DeepSeek

DeepSeek V3, DeepSeek R1 — strong reasoning at affordable prices.

And more

Qwen, Yi, Mistral, Llama and new models as they ship.

​
Model capabilities

The catalog covers different use cases:
  • Chat & text: classic LLMs for conversation, code, analysis.
  • Multimodal (vision): models that understand images.
  • Tool use / function calling: invoke external tools from model output.
  • Reasoning: chain-of-thought models (o1, R1, Claude thinking).
  • Embeddings: vector representations for search and RAG.
  • Audio: speech recognition and synthesis (where supported).

​
Why RuAPI

No VPN required

Direct access from anywhere — models are called through our infrastructure.

One API key

No separate vendor accounts. One key — every frontier model worldwide.

Vendor pricing

You pay the same per-token rate as on the provider’s own site. No hidden markup.

Low latency

Optimized request routing for fast response times.

​
Full catalog and pricing

The list of available models, current per-token prices and supported capabilities lives in your dashboard → Models at www.ruapi.ai.
The catalog auto-updates whenever providers ship new models. Prices update automatically as vendors change them — we don’t add markup.

​
Choosing a model

  • Simple tasks (classification, short answers): gpt-4o-mini, gemini-2.0-flash, claude-haiku — most cost-efficient.
  • Complex tasks (long-form analysis, coding, reasoning): gpt-4o, claude-3-5-sonnet, gemini-1.5-pro.
  • Reasoning (math, logic, multi-step thinking): o1, o3-mini, deepseek-r1, claude-3-7-sonnet (with thinking).
  • Vision (images): gpt-4o, claude-3-5-sonnet, gemini-2.0-flash — all support vision.
See Quickstart for call examples and API Reference for OpenAI vs Claude protocol details.