Skip to main content

​
Run SDK

OpenAI-compatible inference (chat completions) and model listing

​
Operations

MethodDescription
inferenceRun inference (optionally streaming via SSE)
chatCompletionsOpenAI-compatible chat completions

​
Generated Reference

​
Overview

OpenAI-compatible inference (chat completions) and model listing

​
Available Operations

​
inference

Execute inference through the LucidLayer execution gateway. Supports both streaming (SSE) and non-streaming responses. A cryptographic receipt is generated for each successful inference.

​
Example Usage

import { RaijinLabsLucidAi } from "raijin-labs-lucid-ai";

const raijinLabsLucidAi = new RaijinLabsLucidAi();

async function run() {
  const result = await raijinLabsLucidAi.run.inference({});

  console.log(result);
}

run();

​
Standalone function

The standalone function version of this method: 
import { RaijinLabsLucidAiCore } from "raijin-labs-lucid-ai/core.js";
import { runInference } from "raijin-labs-lucid-ai/funcs/runInference.js";

// Use `RaijinLabsLucidAiCore` for best tree-shaking performance.
// You can create one instance of it to use across an application.
const raijinLabsLucidAi = new RaijinLabsLucidAiCore();

async function run() {
  const res = await runInference(raijinLabsLucidAi, {});
  if (res.ok) {
    const { value: result } = res;
    console.log(result);
  } else {
    console.log("runInference failed:", res.error);
  }
}

run();

​
Parameters

ParameterTypeRequiredDescription
requestmodels.InferenceRequest:heavy_check_mark:The request object to use for the request.
optionsRequestOptions:heavy_minus_sign:Used to set various options for making HTTP requests.
options.fetchOptionsRequestInit:heavy_minus_sign:Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed.
options.retriesRetryConfig:heavy_minus_sign:Enables retrying HTTP requests under certain failure conditions.

​
Response

Promise<models.InferenceResult>

​
Errors

Error TypeStatus CodeContent Type
errors.ErrorResponse422application/json
errors.ErrorResponse500, 503application/json
errors.RaijinLabsLucidAiDefaultError4XX, 5XX*/*

​
chatCompletions

x402-gated with dynamic pricing. If X402_ENABLED=true, requests without a valid X-Payment-Proof header receive HTTP 402 with payment instructions. Pricing is resolved per-model from the asset_pricing table.

​
Example Usage

import { RaijinLabsLucidAi } from "raijin-labs-lucid-ai";

const raijinLabsLucidAi = new RaijinLabsLucidAi();

async function run() {
  const result = await raijinLabsLucidAi.run.chatCompletions({
    body: {
      model: "mistral-7b-instruct",
      messages: [
        {
          role: "system",
          content: "You are a helpful AI assistant.",
        },
        {
          role: "user",
          content: "Explain how MMR proofs work in one paragraph.",
        },
      ],
      maxTokens: 256,
      temperature: 0.7,
    },
  });

  console.log(result);
}

run();

​
Standalone function

The standalone function version of this method: 
import { RaijinLabsLucidAiCore } from "raijin-labs-lucid-ai/core.js";
import { runChatCompletions } from "raijin-labs-lucid-ai/funcs/runChatCompletions.js";

// Use `RaijinLabsLucidAiCore` for best tree-shaking performance.
// You can create one instance of it to use across an application.
const raijinLabsLucidAi = new RaijinLabsLucidAiCore();

async function run() {
  const res = await runChatCompletions(raijinLabsLucidAi, {
    body: {
      model: "mistral-7b-instruct",
      messages: [
        {
          role: "system",
          content: "You are a helpful AI assistant.",
        },
        {
          role: "user",
          content: "Explain how MMR proofs work in one paragraph.",
        },
      ],
      maxTokens: 256,
      temperature: 0.7,
    },
  });
  if (res.ok) {
    const { value: result } = res;
    console.log(result);
  } else {
    console.log("runChatCompletions failed:", res.error);
  }
}

run();

​
Parameters

ParameterTypeRequiredDescription
requestoperations.LucidChatCompletionsRequest:heavy_check_mark:The request object to use for the request.
optionsRequestOptions:heavy_minus_sign:Used to set various options for making HTTP requests.
options.fetchOptionsRequestInit:heavy_minus_sign:Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed.
options.retriesRetryConfig:heavy_minus_sign:Enables retrying HTTP requests under certain failure conditions.

​
Response

Promise<models.ChatCompletionResponse>

​
Errors

Error TypeStatus CodeContent Type
errors.ErrorResponse400application/json
errors.X402PaymentRequiredError402application/json
errors.ErrorResponse500application/json
errors.RaijinLabsLucidAiDefaultError4XX, 5XX*/*