References

Supported AI Models and Deployment Addresses of ORA's AI Oracle.

Models

Llama3 8B Instruct

Model ID

Deployed Network

Ethereum & Ethereum Sepolia, Optimism & Optimism Sepolia, Arbitrum & Arbitrum Sepolia, Manta & Manta Sepolia, Linea, Base, Mantle, Polygon PoS

Fee

Mainnet: 0.0003 ETH / 3 MATIC / 3 MNT Testnet: 0.01 ETH

Usage

Input: Prompt (example tx). Output: Inference result (example tx).

OpenLM 1B

Model ID

Deployed Network

Ethereum & Ethereum Sepolia

Fee

Mainnet: 0.0003 ETH Testnet: 0.01 ETH

Usage

Input: Prompt (example tx). Output: Inference result (example tx).

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

Model ID

Deployed Network

Arbitrum & Arbitrum Sepolia, Ethereum Sepolia

Fee

Mainnet: 0.0003 ETH Testnet: 0.01 ETH

Usage

Input: Instruction and prompt with the format of JSON String: {"instruction":"${instruction}","input":"${prompt}"} (example tx). Default instruction (if sending raw prompt only) is You are a helpful assistant. Output: Inference result (example tx).

Note

Input exceeds 7000 characters won't receive callback.

OpenLM Chat 7B

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

Model ID

Deployed Network

Arbitrum & Arbitrum Sepolia, Ethereum Sepolia

Fee

Mainnet: 0.0003 ETH Testnet: 0.01 ETH

Usage

Stable Diffusion v2-1

Model ID

Deployed Network

Ethereum & Ethereum Sepolia, Optimism & Optimism Sepolia, Arbitrum & Arbitrum Sepolia, Manta & Manta Sepolia, Linea, Base, Mantle, Polygon PoS

Fee

Mainnet: 0.0003 ETH / 3 MATIC / 3 MNT Testnet: 0.01 ETH

Usage

Input: Prompt (example tx). Output: IPFS hash of inference result (example tx). Access with IPFS gateway, see example.

Stable Diffusion v3

Stable Diffusion v3 Medium

Model ID

503

Deployed Network

Ethereum & Ethereum Sepolia, Optimism & Optimism Sepolia, Arbitrum & Arbitrum Sepolia, Manta & Manta Sepolia, Linea, Base, Mantle, Polygon PoS

Fee

Mainnet: 0.0003 ETH / 3 MATIC / 3 MNT Testnet: 0.01 ETH

Usage

Input: Prompt (example tx). Output: IPFS hash of inference result (example tx). Access with IPFS gateway, see example.

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);
}