Skip to content

    Use case

    Multimodal generation.One key, many models

    Agents that generate images and reason over what they produce.

    Get an API keyBrowse models

    Why open models fit

    An open image model and a vision checker on one key let an agent generate and self-review in a single loop.

    The pipeline

    One OpenAI-compatible key runs the whole pipeline. Swap any step's model without touching your loop.

    1. 1 Serving
      Generate imageFLUX.1 [schnell]

      Few-step image generation for fast iterations.

      $0.00045 / image

    2. 2 Serving
      Describe & QAGemma 4 31B IT

      A vision chat model to caption and quality-check outputs.

      256K ctx · $0.108 / $0.315 per M

    Call the whole pipeline

    Point the OpenAI SDK at FlexAI once. Every step names its own model on the same key: no per-model clients, endpoints, or keys to juggle.

    import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://tokens.flex.ai/v1",
  apiKey: process.env.FLEXAI_API_KEY,
});

const prompt = "A product photo on a seamless background.";

// 1. Generate image: same key, swap the model anytime
const generateImage = await client.images.generate({
  model: "FLUX.1-schnell",
  prompt: prompt,
});

// 2. Describe & QA: same key, swap the model anytime
const describeQA = await client.chat.completions.create({
  model: "gemma-4-31b-it",
  messages: [{ role: "user", content: [{ type: "image_url", image_url: { url: `data:image/png;base64,${generateImage.data[0].b64_json}` } }] }],
});

    Start serverless and pay per token. When a step becomes steady production traffic, move it to a dedicated endpoint on the same key.

    Build your multimodal generation on FlexAI

    Every model in the pipeline behind one OpenAI-compatible key, with source-linked pricing.

    Get an API keyTalk to us

    $10/month in free credits for your first 3 months

    See how much you could save