Scales efficient language processing with open-source accessibility.
357M visits/mo+1%#2 Coding & Development
$0.0018 per 1M input tokensStarting price
About Hashference
Hashference provides an OpenAI- and Anthropic-compatible API for accessing large language models through a single interface. Users can pay for inference using three methods: mining compute with CPUs, GPUs, or ASICs; purchasing credits with cryptocurrencies such as QUAI, Qi, USDT, or USDC; or paying per request with x402 proof-of-work. The service supports over 60 models from providers including Qwen, DeepSeek, and Z, with pricing listed per million input and output tokens. It is designed to integrate with development tools like Claude Code, Cursor, VS Code, and LangChain without requiring email verification or KYC. Hashference operates on the Quai Network and offers a fallback rate limit mechanism to prevent token exhaustion. The platform also provides a calculator for estimating costs based on model selection and usage.
Key features
- OpenAI- and Anthropic-compatible API
- Mining integration for CPUs, GPUs, and ASICs
- Crypto payment support for QUAI, Qi, USDT, USDC
- Per-request payment with x402 proof-of-work
- Rate limit fallback mechanism
- Calculator for cost estimation
- 60+ models from multiple providers
- Staking plan option for funding
Use cases
- Developing AI-powered applications with variable token costs
- Integrating large language models into existing workflows
- Paying for AI inference using idle compute resources
Pros
- Supports multiple payment methods including mining, crypto, and per-request work
- Compatible with OpenAI and Anthropic APIs for broad tool integration
- No email or KYC required for access
- Operates on Quai Network for decentralized infrastructure
- Offers rate limit fallback to maintain service continuity
Cons
- Limited to models available on the platform
- Payment via mining requires compatible hardware
- Per-request payment method may introduce latency
- No free tier or trial credits mentioned
Frequently asked questions about Hashference
What is Hashference and what does it do?
Hashference is an OpenAI- and Anthropic-compatible API that provides access to large language models through a single interface. It allows users to pay for inference using mining compute, cryptocurrency credits, or per-request proof-of-work.
Who is Hashference designed for?
Hashference is designed for developers and teams who need an affordable, flexible way to integrate AI models into their workflows without requiring email verification or KYC. It suits users comfortable with cryptocurrency or mining.
How does the pricing model work?
Users can pay for inference through mining compute, purchasing credits with cryptocurrencies like QUAI, Qi, USDT, or USDC, or paying per request with x402 proof-of-work. Pricing is listed per million input and output tokens.
What models does Hashference support?
Hashference supports over 60 models from providers including Qwen, DeepSeek, and Z.ai. Each model has its own pricing structure for input and output tokens.
Can Hashference integrate with development tools?
Yes, Hashference works with tools like Claude Code, Cursor, VS Code, LangChain, and other apps that support OpenAI or Anthropic APIs. No additional setup is required beyond pointing the SDK at Hashference.
How do I get started with Hashference?
Users can obtain an API key, fund it with crypto, mining, or staking, and then point their SDK at Hashference. The platform provides a quickstart guide and calculator to estimate costs based on model selection and usage.
