nexusify-sdk

v1.0.3

Published

8 days ago

Official Node.js SDK for the Nexusify API — unified access to 84+ AI models including GPT, Gemini, Grok, Llama, Mistral, DeepSeek, and more

0High
0Medium
0Low

darknessdevv

nexusify ai llm openai gpt gemini grok llama mistral deepseek sdk chat completions image-generation streaming

nexusify

Official Node.js SDK for the Nexusify API — unified access to 84 AI models including GPT-5, Gemini, Grok, Llama, Mistral, DeepSeek, and more, through a single OpenAI-compatible interface.

Features

84 AI text models from OpenAI, Google, xAI, Meta, Mistral, DeepSeek, Cohere, and more
5 image generation models including Flux, Klein, and GPT Image
100% OpenAI-compatible — drop-in replacement for existing OpenAI SDK integrations
Streaming support for all text endpoints via async generators
Vision support — send images alongside text to multimodal models
Tool calling / function calling on supported models
Reasoning models with chain-of-thought output (Grok, DeepSeek, Qwen, and more)
Image auto-download — save generated images directly to disk
Full TypeScript support with strict types for all inputs and outputs
CommonJS, ESM, and TypeScript compatible out of the box

Installation

npm install nexusify-sdk

yarn add nexusify-sdk

pnpm add nexusify-sdk

Getting an API Key

Visit nexusify.co and click Start building.
Sign in via the portal at login.nexusify.co using Google, Discord, or CAPTCHA.
Open your dashboard at dash.nexusify.co/dashboard.
Scroll to API Credentials and click Copy Secret Key.

New accounts receive $25 in free credits every week, renewed automatically every Monday — no credit card required.

Security notice: Never expose your API key in client-side code, browser extensions, or public repositories. Always use environment variables and server-side requests.

export NEXUS_API_KEY="your_api_key_here"

Quick Start

CommonJS

const { Nexusify } = require("nexusify-sdk");

const client = new Nexusify({ apiKey: process.env.NEXUS_API_KEY });

async function main() {
  const completion = await client.chat.completions.create({
    model: "gemini-2.5-flash",
    messages: [{ role: "user", content: "Hello!" }],
  });

  console.log(completion.choices[0].message.content);
}

main();

ESM

import Nexusify from "nexusify-sdk";

const client = new Nexusify({ apiKey: process.env.NEXUS_API_KEY });

const completion = await client.chat.completions.create({
  model: "gemini-2.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

TypeScript

import Nexusify, { type ChatCompletion } from "nexusify-sdk";

const client = new Nexusify({ apiKey: process.env.NEXUS_API_KEY as string });

const completion: ChatCompletion = await client.chat.completions.create({
  model: "gemini-2.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0]?.message.content);

Client Configuration

const client = new Nexusify({
  apiKey: "your_api_key",   // Required
  baseURL: "https://api.nexusify.co/v1",  // Optional. Default shown.
  timeout: 60000,           // Optional. Request timeout in ms. Default: 60000
  maxRetries: 2,            // Optional. Reserved for future use.
});

Chat Completions

The primary endpoint — fully compatible with the OpenAI Chat Completions format.

Endpoint: POST /v1/chat/completions

Basic Request

const completion = await client.chat.completions.create({
  model: "gemini-2.5-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain black holes in simple terms." },
  ],
  temperature: 0.7,
  max_tokens: 300,
});

console.log(completion.choices[0].message.content);
console.log(completion.usage.total_tokens);

Parameters:

| Name | Type | Required | Description | |------|------|----------|-------------| | model | NexusifyModel | Yes | Model ID, e.g. "gemini-2.5-flash". | | messages | Message[] | Yes | Array of { role, content } objects. | | temperature | number | No | Sampling temperature 0.0–2.0. Default: 0.7. | | max_tokens | number | No | Maximum tokens to generate. | | top_p | number | No | Nucleus sampling threshold. | | stop | string \| string[] | No | Stop sequences. | | tools | Tool[] | No | Tool/function definitions. | | tool_choice | ToolChoice | No | "auto", "none", or { type: "function", function: { name } }. | | stream | boolean | No | Enable streaming via SSE. |

Streaming Chat

When stream: true, the method returns an async generator that yields ChatCompletionChunk objects.

const stream = await client.chat.completions.create({
  model: "gpt-5-mini",
  messages: [{ role: "user", content: "Write a poem about the ocean." }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

Vision (Image Input)

Send images alongside text to any model marked with the 🖼️ Vision capability.

const completion = await client.chat.completions.create({
  model: "gemini-3-flash-preview",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What is in this image?" },
        { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
      ],
    },
  ],
});

To send a local image, encode it as a base64 data URI:

import { readFileSync } from "fs";

const imageData = readFileSync("./photo.jpg").toString("base64");

const completion = await client.chat.completions.create({
  model: "kimi-k2.5",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Describe this image." },
        { type: "image_url", image_url: { url: `data:image/jpeg;base64,${imageData}` } },
      ],
    },
  ],
});

Graceful degradation: If you send an image to a model that does not support vision (e.g. deepseek-v3.2), the image content is silently dropped and only the text portion is forwarded. No error is returned.

Tool Calling

Supported on kimi-k2, kimi-k2.5, minimax-m2, and gemini-3-flash-preview.

const completion = await client.chat.completions.create({
  model: "kimi-k2",
  messages: [{ role: "user", content: "What is the weather in Madrid?" }],
  tools: [
    {
      type: "function",
      function: {
        name: "get_weather",
        description: "Get the current weather for a city",
        parameters: {
          type: "object",
          properties: {
            city: { type: "string", description: "The city name" },
          },
          required: ["city"],
        },
      },
    },
  ],
  tool_choice: "auto",
});

const message = completion.choices[0].message;

if (message.tool_calls) {
  const call = message.tool_calls[0];
  console.log("Function:", call.function.name);
  console.log("Args:", JSON.parse(call.function.arguments));
}

Graceful degradation: If you pass tools to a model that does not support tool calling, the parameter is silently dropped and the model responds as normal text generation.

Responses API

The modern OpenAI-style Responses API returns a structured output array with typed items, making it ideal for agentic workflows and multi-step applications.

Endpoint: POST /v1/responses

Responses Basic Request

const response = await client.responses.create({
  model: "grok-4",
  input: "What is the difference between TCP and UDP?",
  instructions: "You are a concise networking expert.",
  max_output_tokens: 200,
  temperature: 0.5,
});

console.log(client.responses.getOutputText(response));

Parameters:

| Name | Type | Required | Description | |------|------|----------|-------------| | model | NexusifyModel | Yes | Model ID. | | input | string \| Message[] | Yes | A string prompt or an array of conversation messages. | | instructions | string | No | System-level instruction prepended to the conversation. | | max_output_tokens | number | No | Maximum tokens to generate. | | temperature | number | No | Sampling temperature. Default: 1.0. | | top_p | number | No | Nucleus sampling. Default: 1.0. | | stream | boolean | No | Enable SSE streaming. | | tools | Tool[] | No | Tool definitions. | | tool_choice | ToolChoice | No | Tool selection strategy. | | store | boolean | No | Whether to store the response. Default: true. | | metadata | Record<string, string> | No | Arbitrary key/value pairs returned with the response. | | previous_response_id | string | No | ID of a prior response to continue from. | | user | string | No | End-user identifier for auditing. |

Helper methods:

client.responses.getOutputText(response);
client.responses.getReasoningText(response);

Reasoning Models

Models such as grok-4-thinking, grok-4.1-thinking, and grok-3-thinking include a chain-of-thought trace in the response.

const response = await client.responses.create({
  model: "grok-4-thinking",
  input: "Prove that the square root of 2 is irrational.",
});

const reasoning = client.responses.getReasoningText(response);
const answer = client.responses.getOutputText(response);

console.log("Reasoning:", reasoning);
console.log("Answer:", answer);

Streaming Responses

When stream: true, the method returns an async generator of ResponseStreamEvent objects, each with an event name and a data payload following the OpenAI Responses API event lifecycle.

const stream = await client.responses.create({
  model: "grok-4.1-fast",
  input: "Write a haiku about winter.",
  stream: true,
});

for await (const event of stream) {
  if (event.event === "response.output_text.delta") {
    const delta = event.data?.delta;
    if (typeof delta === "string") process.stdout.write(delta);
  }
  if (event.event === "response.done") break;
}

Streaming event reference:

| Event | Description | |-------|-------------| | response.created | Fired immediately before token generation begins. | | response.in_progress | Generation has started. | | response.output_item.added | A new output item has been opened. | | response.content_part.added | A content part has been opened inside an output item. | | response.reasoning_text.delta | A reasoning trace chunk (reasoning models only). | | response.output_text.delta | A text response chunk. | | response.output_text.done | Full text response has been delivered. | | response.content_part.done | Content part is closed. | | response.output_item.done | Output item has been fully delivered. | | response.completed | Full response is ready. Contains the final response object with usage. | | response.done | Terminal event — stream closes after this. |

Multi-turn Conversations

const response = await client.responses.create({
  model: "gemini-2.5-flash",
  instructions: "You are a helpful assistant.",
  input: [
    { role: "user", content: "My name is Alex." },
    { role: "assistant", content: "Nice to meet you, Alex!" },
    { role: "user", content: "What is my name?" },
  ],
});

console.log(client.responses.getOutputText(response));

Text Generate (Legacy)

A simpler, flat alternative to Chat Completions. Pass a plain string as prompt and receive a plain string completion. Supports all 84 models, streaming, conversation history, and all generation parameters.

Endpoint: POST /v1/text/generate

Use this for quick prototypes and simple bots. For production integrations and OpenAI SDK compatibility, prefer /chat/completions.

Text Generate Basic Request

const result = await client.text.generate({
  model: "deepseek-v3.2",
  prompt: "Explain how neural networks learn.",
  temperature: 0.7,
  max_tokens: 200,
});

console.log(result.completion);
console.log(result.usage.total_tokens);

Parameters:

| Name | Type | Required | Description | |------|------|----------|-------------| | model | NexusifyModel | Yes | Model ID. | | prompt | string | * | Plain text prompt. Required if messages is not provided. | | messages | Message[] | * | Full conversation history. Use instead of prompt for multi-turn. | | systemInstruction | string | No | System-level instruction that defines model behavior. | | temperature | number | No | Sampling temperature 0.0–2.0. Default: 0.7. | | max_tokens | number | No | Maximum tokens to generate. Default: 300. | | top_p | number | No | Nucleus sampling threshold. Default: 1.0. | | stop | string \| string[] | No | Stop sequences. | | stream | boolean | No | Stream response as SSE. Default: false. | | userid | string | No | User ID for persistent conversation history. |

Streaming Text Generate

const stream = await client.text.generate({
  model: "gpt-5-mini",
  prompt: "Write a short story about a robot learning to paint.",
  stream: true,
  max_tokens: 400,
});

for await (const chunk of stream) {
  process.stdout.write(chunk);
}

Persistent Conversation History

Pass a userid string to enable server-side memory. The API stores each exchange and automatically includes the history in subsequent requests with the same userid and model.

await client.text.generate({
  model: "gpt-5-mini",
  prompt: "My name is Alice.",
  userid: "user_alice_001",
});

const second = await client.text.generate({
  model: "gpt-5-mini",
  prompt: "What is my name?",
  userid: "user_alice_001",
});

console.log(second.completion);

await client.text.deleteHistory("user_alice_001");

Image Generation

Generate images from text prompts using five state-of-the-art diffusion and synthesis models.

Endpoint: POST /v1/generate-image

Generated images are hosted temporarily and expire after 2 hours. Use the auto-download feature to save them locally.

Image Basic Request

const image = await client.images.generate({
  prompt: "A cyberpunk city at night with neon lights, cinematic lighting",
  model: "flux",
  width: 1024,
  height: 1024,
});

console.log(image.imageUrl);
console.log(image.size);
console.log(image.expiresIn);
console.log(image.user.usageRemaining);

Parameters:

| Name | Type | Default | Description | |------|------|---------|-------------| | prompt | string | — | Text description of the image. Required. | | model | NexusifyImageModel | "flux" | Image model ID. | | width | number | 512 | Output width in pixels. Max 2048. | | height | number | 512 | Output height in pixels. Max 2048. | | saveTo | string | — | Directory path to save the image locally. | | saveToRoot | boolean | — | If true, saves the image in the project root (process.cwd()). |

Auto-Download Images

The SDK can automatically download and save generated images without any extra setup.

Save to a specific folder:

const image = await client.images.generate({
  prompt: "A minimalist logo, clean vector design, blue and white",
  model: "klein",
  width: 1024,
  height: 1024,
  saveTo: "./generated-images",
});

console.log("Remote URL:", image.imageUrl);
console.log("Local path:", image.localPath);

Save to the project root:

const image = await client.images.generate({
  prompt: "A photorealistic mountain at dawn",
  model: "klein-large",
  saveToRoot: true,
});

console.log("Saved to:", image.localPath);

The local filename is generated automatically using a sanitized prompt slug and a timestamp, e.g. nexusify-a-photorealistic-mountain-at-dawn-1735000000000.png.

Models

List and Filter

The models resource exposes methods to browse, search, and filter the full catalog of available models.

const all = client.models.listLocal();
console.log(`${all.data.length} models available`);

const model = client.models.findById("gemini-2.5-flash");
console.log(model?.provider, model?.pricing);

const visionModels = client.models.filterByCapability("vision");
const reasoningModels = client.models.filterByCapability("reasoning");
const codeModels = client.models.filterByCapability("code");
const fastModels = client.models.filterByCapability("fast");
const toolModels = client.models.filterByCapability("tools");

const xaiModels = client.models.filterByProvider("xAI");
const googleModels = client.models.filterByProvider("Google");
const mistralModels = client.models.filterByProvider("Mistral AI");

const imageModels = client.models.listImageModels();
console.log(imageModels);

const liveList = await client.models.list();

Error Handling

All errors thrown by the SDK extend the base NexusifyError class, which exposes a status (HTTP code), code (string), and raw (original response body).

import {
  NexusifyError,
  AuthenticationError,
  InsufficientCreditsError,
  RateLimitError,
  BadRequestError,
  InternalServerError,
  StreamingError,
  TimeoutError,
} from "nexusify-sdk";

try {
  const completion = await client.chat.completions.create({
    model: "gemini-2.5-flash",
    messages: [{ role: "user", content: "Hello" }],
  });
} catch (error) {
  if (error instanceof AuthenticationError) {
    console.error("Invalid API key — get yours at https://dash.nexusify.co");
  } else if (error instanceof InsufficientCreditsError) {
    console.error("Not enough credits — top up at https://dash.nexusify.co");
  } else if (error instanceof RateLimitError) {
    console.error("Rate limit hit — max 130 requests/min");
  } else if (error instanceof BadRequestError) {
    console.error("Bad request:", error.message);
  } else if (error instanceof InternalServerError) {
    console.error("Server error — try again shortly");
  } else if (error instanceof TimeoutError) {
    console.error("Request timed out");
  } else if (error instanceof NexusifyError) {
    console.error(`[${error.status}] ${error.code}: ${error.message}`);
  }
}

Error classes:

| Class | HTTP Status | Code | |-------|-------------|------| | BadRequestError | 400 | bad_request | | AuthenticationError | 401 | authentication_error | | InsufficientCreditsError | 402 | insufficient_credits | | RateLimitError | 429 | rate_limit_exceeded | | InternalServerError | 500 | internal_server_error | | StreamingError | — | streaming_error | | TimeoutError | — | timeout_error |

Model List

All 84 text models available through the Nexusify API.

Capability tags: 🖼️ Vision · 🔧 Tools · 🧠 Reasoning · ⚡ Fast · 💻 Code

| Provider | Model ID | Capabilities | Input ($/1M) | Output ($/1M) | |----------|----------|-------------|-------------|--------------| | Meta AI | llama-4-maverick-17b-128e-instruct | — | $0.20 | $0.60 | | Meta AI | llama-3.2-90b-vision-instruct | 🖼️ | $0.35 | $0.40 | | Meta AI | llama-3.1-405b-instruct | — | $5.00 | $15.00 | | Meta AI | llama-3.3-70b-instruct | — | $0.40 | $0.60 | | Mistral AI | mistral-small-24b-instruct | 💻 | $0.10 | $0.30 | | Mistral AI | mixtral-8x22b | — | $0.90 | $0.90 | | Mistral AI | mistral-small-3.1 | 🖼️ 🔧 | $0.10 | $0.30 | | Mistral AI | mistral-small-3.2 | 🔧 | $0.10 | $0.30 | | Mistral AI | mistral-medium-3 | 🖼️ | $0.40 | $1.20 | | Mistral AI | mistral-nemotron | 🔧 | $0.20 | $0.60 | | Mistral AI | magistral-small | 🧠 | $0.50 | $1.50 | | Mistral AI | devstral-2 | 💻 | $0.70 | $2.00 | | Mistral AI | mamba-codestral | 💻 | $0.15 | $0.30 | | Mistral AI | mistral-large-3 | 🖼️ 🔧 | $2.00 | $6.00 | | Mistral AI | ministral-3-8b | 🖼️ | $0.10 | $0.10 | | Mistral AI | ministral-3-14b | 🖼️ | $0.15 | $0.15 | | Alibaba | qwen3-235b-a22b | — | $0.20 | $0.60 | | Alibaba | qwen2.5-coder-32b | 💻 | $0.30 | $0.50 | | Alibaba | qwen3-next-80b | 🧠 | $0.40 | $1.50 | | Alibaba | qwen3.5 | 🧠 | $1.30 | $5.50 | | Alibaba | qwen3-coder | 💻 | $0.85 | $4.00 | | Alibaba | qwen3-vl | 🖼️ | $0.50 | $2.00 | | Alibaba | qwen3-coder-next | 💻 | $0.33 | $0.85 | | Google | gemini-2.5-flash | 🖼️ ⚡ | $0.15 | $0.60 | | Google | gemini-2.5-flash-lite | ⚡ | $0.08 | $0.30 | | Google | gemini-2.0-flash | — | $0.10 | $0.40 | | Google | gemini-2.0-flash-lite | — | $0.08 | $0.30 | | Google | gemma-7b | — | $0.07 | $0.07 | | Google | gemma-2-9b | — | $0.07 | $0.07 | | Google | gemini-3-flash-preview | 🖼️ 🔧 | $0.15 | $0.60 | | OpenAI | gpt-4 | — | $30.00 | $60.00 | | OpenAI | gpt-4o-mini | ⚡ | $0.15 | $0.60 | | OpenAI | gpt-5-nano | ⚡ | $0.15 | $0.60 | | OpenAI | gpt-5-mini | — | $0.40 | $1.60 | | OpenAI | gpt-5 | — | $1.50 | $6.00 | | OpenAI | gpt-5-codex | 💻 | $2.50 | $10.00 | | OpenAI | gpt-5-codex-mini | 💻 | $0.60 | $2.50 | | OpenAI | gpt-5.1 | — | $2.00 | $8.00 | | OpenAI | gpt-5.1-codex | 💻 | $3.00 | $12.00 | | OpenAI | gpt-5.1-codex-max | 💻 | $5.00 | $20.00 | | OpenAI | gpt-5.1-codex-mini | 💻 | $0.80 | $3.00 | | OpenAI | gpt-5.2 | — | $3.00 | $12.00 | | OpenAI | gpt-5.2-codex | 💻 | $4.00 | $16.00 | | OpenAI | gpt-5.3-codex | 💻 | $5.00 | $20.00 | | OpenAI | gpt-5.4 | — | $6.00 | $24.00 | | Open Source | gpt-oss-120b | — | $1.50 | $4.00 | | Open Source | gpt-oss-20b | — | $0.30 | $0.80 | | xAI | grok-3 | — | $3.00 | $15.00 | | xAI | grok-3-mini | ⚡ | $0.30 | $0.50 | | xAI | grok-3-thinking | 🧠 | $1.00 | $5.00 | | xAI | grok-4 | 🧠 | $5.00 | $20.00 | | xAI | grok-4-thinking | 🧠 | $3.00 | $15.00 | | xAI | grok-4.1-mini | ⚡ | $0.40 | $1.20 | | xAI | grok-4.1-fast | ⚡ | $1.00 | $3.00 | | xAI | grok-4.1-expert | 🧠 | $3.00 | $12.00 | | xAI | grok-4.1-thinking | 🧠 | $2.00 | $8.00 | | xAI | grok-4.20-beta | 🧠 | $2.00 | $6.00 | | DeepSeek | deepseek-v3.2 | 🧠 | $0.27 | $1.10 | | DeepSeek | deepseek-v3.1 | 🧠 | $0.27 | $1.10 | | Moonshot | kimi-k2 | 🔧 | $0.60 | $2.50 | | Moonshot | kimi-k2.5 | 🖼️ 🧠 🔧 | $0.80 | $3.00 | | MiniMax | minimax-m2 | 🔧 | $0.80 | $2.00 | | MiniMax | minimax-m2.1 | — | $1.00 | $3.00 | | MiniMax | minimax-m2.5 | — | $0.30 | $1.20 | | NVIDIA | nemotron-3-nano | — | $0.05 | $0.10 | | NVIDIA | nemotron-super-49b-v1.5 | — | $0.30 | $1.00 | | Zhipu AI | glm-4.6 | — | $0.20 | $0.60 | | Zhipu AI | glm-4.7 | — | $0.30 | $0.90 | | Zhipu AI | glm5 | 🧠 | $3.00 | $9.00 | | StepFun | step-3.5-flash | 🧠 | $0.10 | $0.30 | | Cohere | command-a-3 | — | $2.50 | $10.00 | | Cohere | command-a-vision | 🖼️ | $2.50 | $10.00 | | Cohere | command-a-reasoning | 🧠 | $2.50 | $10.00 | | Cohere | command-r | — | $0.15 | $0.60 | | Cohere | command-r-plus | — | $2.50 | $10.00 | | Cohere | command-r7b | ⚡ | $0.10 | $0.20 | | Cohere | command-r7b-arabic | — | $0.10 | $0.20 | | Cohere | aya-expanse-8b | — | $0.15 | $0.30 | | Cohere | aya-expanse-32b | — | $0.40 | $1.20 | | Cohere | aya-vision-8b | 🖼️ | $0.20 | $0.40 | | Cohere | aya-vision-32b | 🖼️ | $0.50 | $1.50 | | Phind | phind-90b | 💻 | $0.70 | $2.00 | | Cogito AI | cogito-2.1 | 🧠 | $1.50 | $2.50 | | RNJ AI | rnj-1 | — | $0.15 | $0.15 |

Image Model Pricing

| Model | Best For | 512×512 | 1024×1024 | |-------|----------|---------|-----------| | flux | General | $0.003 | $0.012 | | zimage | General | $0.005 | $0.020 | | klein | Art | $0.006 | $0.024 | | klein-large | Pro / High Detail | $0.012 | $0.048 | | gptimage | General | $0.040 | $0.160 |

Credits & Billing

Nexusify uses a credit-based system. All prices are in USD.

New accounts receive $25 in free credits every Monday, renewed automatically — no credit card required. Paid credits are available at any time from the dashboard and never expire; they are only drawn after free credits are exhausted.

When your credit balance is insufficient, the API returns a 402 status and the SDK throws an InsufficientCreditsError.

Rate Limits

The Nexusify API allows up to 130 requests per minute. Exceeding this limit returns a 429 status and the SDK throws a RateLimitError. Credits for failed requests are returned automatically.

Links

| Resource | URL | |----------|-----| | Website | nexusify.co | | Dashboard | dash.nexusify.co/dashboard | | Login | login.nexusify.co | | Discord | discord.com/invite/4NXbPtYuHW | | Docs | docs.nexusify.co | | API Base URL | https://api.nexusify.co/v1 |

nexusify · v1.0.0 · MIT License

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

nexusify

Features

Installation

Getting an API Key

Quick Start

CommonJS

ESM

TypeScript

Client Configuration

Chat Completions

Basic Request

Streaming Chat

Vision (Image Input)

Tool Calling

Responses API

Responses Basic Request

Reasoning Models

Streaming Responses

Multi-turn Conversations

Text Generate (Legacy)

Text Generate Basic Request

Streaming Text Generate

Persistent Conversation History

Image Generation

Image Basic Request

Auto-Download Images

Models

List and Filter

Error Handling

Model List

Image Model Pricing

Credits & Billing

Rate Limits

Links