DOCSEARCHbyAlgolia
Submit Docs

HypersHub AI Gateway

website·Indexed 30 days ago

https://apiclaw.cc/

A unified AI model access gateway service platform providing API interfaces to various third-party large language models (LLM) and AI services.

Tokens
755
Snippets
1
Records
8
Agent score
58%

What's inside HypersHub

  1. Understand HypersHub service capabilities

    HypersHub is a unified AI model access gateway service platform. It provides API interfaces to access various third-party Large Language Models (LLMs) and AI services. HypersHub acts as an intermediary layer connecting to upstream AI service providers and does not provide its own AI model training or inference capabilities.

  2. Contact HypersHub support

    For questions regarding the service agreement or technical issues, users can contact the platform via the ticket system in the console or through official customer service channels.

  3. Manage personal data and exercise user rights in HypersHub

    Users have the following rights regarding their data: access to personal information, correction of inaccurate data, request for account and data deletion (subject to legal requirements), and data portability (exporting usage records and billing data). To exercise these rights or ask questions about privacy, users should use the ticket system in the console or official customer service channels.

  4. Comply with HypersHub API usage specifications

    When using the HypersHub API, developers must adhere to the following constraints:

    • Do not use the API for activities that violate the laws of the People's Republic of China.
    • Do not generate or propagate illegal, obscene, violent, or terrorist content.
    • Reverse engineering, cracking, or attempting to bypass access restrictions is prohibited.
    • Respect the rate limits and concurrency limits set by the platform.
    • Keep API Keys secure and do not leak them to unauthorized third parties.

  5. Understand HypersHub billing and payment

    HypersHub uses a prepaid billing model based on the actual number of Tokens consumed. Pricing is published in the platform console. If the account balance is insufficient, services may be interrupted. The platform reserves the right to adjust pricing with prior notice to users.

  6. Understand HypersHub data collection and storage policies

    HypersHub collects account information (username, phone, email), usage data (API call logs, Token consumption, timestamps), device information (IP, browser, OS), and payment records.

    Crucially, HypersHub does not store conversation content. The platform does not store the Prompt text sent via API or the content returned by the model; it only records metadata for billing and monitoring (request time, model ID, Token usage).

  7. Understand HypersHub data sharing and third-party processing

    HypersHub does not sell personal information to third parties. However, it shares data in specific scenarios: forwarding requests to upstream AI service providers (e.g., OpenAI, Anthropic) to complete API calls, complying with legal/government mandates, protecting platform/public safety, or with explicit user consent.

  8. Pricing for DeepSeek-V4-Flash model

    The DeepSeek-V4-Flash model (ID: deepseek-v4-flash) uses a tiered pricing structure based on token type (input vs output) and cache status, with different rates for normal and peak hours. All prices are per million tokens.
    {
  "model": "deepseek-v4-flash",
  "pricing": {
    "input_cache_hit": {
      "normal": "¥0.05 / 1M tokens",
      "peak": "¥0.1 / 1M tokens"
    },
    "input_cache_miss": {
      "normal": "¥1.5 / 1M tokens",
      "peak": "¥3 / 1M tokens"
    },
    "output": {
      "normal": "¥4.5 / 1M tokens",
      "peak": "¥9 / 1M tokens"
    }
  }
}