Models

Llama3 8B Instruct

OpenLM 1B

OpenLM Score 7B, aka. (A.I.)location Oracle

OpenLM Chat 7B

Stable Diffusion v2-1

Stable Diffusion v3

ORA RMS API Models

ORA RMS API Models are supported on Ethereum mainnet and Base networks.

| Model Name                                  | Price per Call in $ORA |
|---------------------------------------------|------------------------|
| meta-llama/Llama-3.3-70B-Instruct           | 0.18                   |
| Qwen/QwQ-32B-Preview                        | 0.24                   |
| Qwen/Qwen2.5-Coder-32B-Instruct             | 0.16                   |
| meta-llama/Llama-3.2-3B-Instruct            | 0.01                   |
| mistralai/Mixtral-8x22B-Instruct-v0.1       | 0.24                   |
| meta-llama/Meta-Llama-3-70B-Instruct        | 0.18                   |
| Qwen/Qwen2-72B-Instruct                     | 0.18                   |
| google/gemma-2-27b-it                       | 0.16                   |
| google/gemma-2-9b-it                        | 0.06                   |
| mistralai/Mistral-7B-Instruct-v0.3          | 0.04                   |
| google/gemma-2b-it                          | 0.02                   |
| mistralai/Mistral-7B-Instruct-v0.2          | 0.04                   |
| mistralai/Mixtral-8x7B-Instruct-v0.1        | 0.12                   |
| mistralai/Mistral-7B-Instruct-v0.1          | 0.04                   |
| meta-llama/Llama-2-13b-chat-hf              | 0.04                   |
| meta-llama/Llama-2-7b-chat-hf               | 0.04                   |
| meta-llama/Llama-3.1-405B-Instruct          | 0.7                    |
| Qwen/Qwen2.5-72B-Instruct                   | 0.24                   |
| meta-llama/Llama-3.2-1B-Instruct            | 0.01                   |
| meta-llama/Meta-Llama-3-8B-Instruct         | 0.04                   |
| black-forest-labs/FLUX.1-dev                | 0.09                   |
| black-forest-labs/FLUX.1-canny              | 0.09                   |
| black-forest-labs/FLUX.1-redux-dev          | 0.09                   |
| black-forest-labs/FLUX.1-schnell            | 0.01                   |
| deepseek-ai/DeepSeek-V3                     | 0.25                   |
| stabilityai/stable-diffusion-3.5-medium     | 0.13                   |
| stabilityai/stable-diffusion-3-medium       | 0.13                   |
| stabilityai/stable-diffusion-3.5-large      | 0.24                   |
| stabilityai/stable-diffusion-3.5-large-turbo| 0.15                   |

To determine the model ID of a specific model, please refer to the code below:

// solidity
function calcModelIdByName(string calldata modelName) public pure returns (uint256) {
    return uint256(uint160(uint256(keccak256(bytes(modelName)))));
}

// JavaScript
// example modelIdString: 'openai/gpt-4o'
function modelIdStringToBigInt(modelIdString) {
  const hashedValue = ethers.keccak256(ethers.toUtf8Bytes(modelIdString));
  const addressValue = `0x${hashedValue.slice(26)}`;
  return BigInt(addressValue);
}

Deployed Addresses

Prompt and SimplePrompt are both example smart contracts interacted with AI Oracle.

For simpler application scenarios (eg. Prompt Engineering based AI like GPTs), you can directly use Prompt or SimplePrompt.

SimplePrompt saves gas by only emitting the event without storing historical data.

Ethereum Mainnet

Ethereum Sepolia

Deprecated contracts: AIOracle, Prompt.

Optimism Mainnet

Optimism Sepolia

Arbitrum Mainnet

Arbitrum Sepolia Testnet

Manta Mainnet

Manta Sepolia Testnet

Linea Mainnet

Base Mainnet

Base Sepolia

Polygon PoS Mainnet

Mantle Mainnet

Morph Mainnet

Introduction

The AI Settlement Oracle is the first AI-powered truth machine, leveraging verifiable AI to resolve and settle factual questions onchain. It offers a trustless, autonomous system for information resolution, eliminating human error and manipulation.

Advantages

• Autonomous Operation: Powered by ORA’s Optimistic Machine Learning (OPML) and AI Oracle.

• Accuracy & Fairness: Immune to economic manipulation and herd behaviour typical of traditional systems.

• Trustless Settlement: Ensures unbiased outcomes for any factual query.

Try it out!

• Live Demo

• Github Repo

• Research Post

Architecture

Workflow

The AI Settlement Oracle contains two parts of interaction:

• Parse Context: The initial interaction processes a question by analyzing web sources and summarizing them into a coherent "truth context." This provides a reliable foundation for further reasoning.

• Onchain Settlement: In the second interaction, the truth context and helper prompts are integrated into an input for the AI Oracle. The Oracle uses this input to generate a verified outcome, enabling decentralized and transparent truth settlement onchain.

To showcase how AI Oracle can enhance consumer-facing products, we introduce Fortune Teller.

About Fortune Teller

Fortune Teller leverages the NestedInference smart contract, as discussed in the Advanced Usages of AI Oracle. This application aims to onboard new users to Web3 and demonstrate the capabilities of AI Oracle.

Application Flow

1. User Interaction: The application prompts users to answer specific questions posed by the Magic Wizard.

2. Fortune Telling: The Wizard casts its spells by requesting inferences from AI Oracle.

3. Response Generation: The Llama3 model generates a textual response, which is then used as a prompt for image creation via StableDiffusion.

4. NFT Minting: Users can mint AI-generated NFTs if they are satisfied with their fortune image.

The image on the right represents user's fortune result generated by AI Oracle:

• Text: Generated by Llama3 (onchain tx)

• Image: Generated by Stable Diffusion v3 (onchain tx)

Benefits of using AI Oracle in Various Applications

• Objective AI-Generated Insights: AI provides neutral and unbiased outputs, ensuring a fair experience across diverse use cases.

• Immutable Onchain Data: Information generated is securely stored on the blockchain, making it tamper-proof and easily verifiable.

• Transparent Data Generation: Utilizing opML, the entire generation process is transparent, fostering trust in the system across different applications.

Build your own AI dapps!

💡 If you're interested in creating your own frame, check out our AI Oracle Frame Template repository. This template can help you bootstrap your application, but you'll need to modify it based on your specific use case.

We encourage you to develop your own applications. Explore ideas in the awesome-ora repository, whether it’s a Farcaster frame, a Telegram mini app, or any other client application that interacts with AI Oracle.