flux-2

Quick example

curl https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2",
    "prompt": "an infographic poster titled OPENING SOON, clean layout",
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/images/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "flux-2",
        "prompt": "an infographic poster titled OPENING SOON, clean layout",
        "aspect_ratio": "3:4",
        "resolution": "2K",
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "flux-2",
    prompt: "an infographic poster titled OPENING SOON, clean layout",
    aspect_ratio: "3:4",
    resolution: "2K",
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":        "flux-2",
        "prompt":       "an infographic poster titled OPENING SOON, clean layout",
        "aspect_ratio": "3:4",
        "resolution":   "2K",
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/images/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "flux-2",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed". The completed payload's output.image_urls holds the generated image URL.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/images/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.

Tiers

Two customer model ids share one parameter shape:

Modes

There is no mode field — the modality is implicit in the request shape:

• Text-to-image — no input_urls.
• Image-to-image / multi-reference editing — pass input_urls (1–8 reference images). FLUX.2 keeps characters, products, and styles consistent across the result.

Request body

model — string, required

One of flux-2 (Pro) or flux-2-flex (Flex).

prompt — string, required

3–5,000 characters. Put any text you want rendered in the image in quotes.

input_urls — array, optional

1–8 reference images for image-to-image / multi-reference editing. Public HTTPS URLs only — base64 / data: URIs are rejected at the gateway. Passing any image switches the request to editing mode.

aspect_ratio — string, default 1:1

One of 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3. The value auto (match the first reference image) is available only for image-to-image.

resolution — string, default 1K

1K or 2K. The 2K tier renders up to 4MP.

nsfw_checker — boolean, optional, default false

Enables upstream content moderation. Off by default.

Pricing

FLUX.2 bills a flat rate per generated image, by tier (flux-2 / flux-2-flex) and resolution (1K / 2K). Text-to-image and image-to-image cost the same within a tier:

credits = ceil(per_image_usd × 1000)

where 1 credit = $0.001 USD. Each request produces one image. Failed and rejected requests are not charged.

The exact per-image credit cost for each tier/resolution surfaces on the model page and through the playground estimator before submit.

Response

The poll envelope returns the image URL in output.image_urls:

{
  "id": "task_019dfd44b7fd74168541552a3260a623",
  "model": "flux-2",
  "status": "completed",
  "output": {
    "image_urls": [
      "https://cdn.reapi.ai/...jpg"
    ]
  }
}

Generated URLs expire — mirror them to your own storage if you need long-term retention.

Errors

Failures return the standard reAPI envelope { error: { code, message, request_id } }. Common cases:

• Invalid input (prompt outside 3–5000 chars, more than 8 input_urls, auto aspect without reference images, a non-HTTPS URL) → 400.
• Insufficient credits → 402.
• Rate limited → 429.

See the full catalog at /docs/api/errors.

Tips

• Put the literal text you want rendered in the prompt, in quotes — FLUX.2 is tuned for legible typography, ad headlines, and infographics.
• For consistency across a campaign, pass the same reference image(s) in input_urls and let FLUX.2 keep the character/style on-model.
• Use flux-2 (Pro) for fast, cost-efficient production and flux-2-flex (Flex) when a hero shot needs maximum quality.
• Reach for resolution: "2K" (up to 4MP) only when the asset needs the detail.

Related

• Image generation models
• Qwen Image 2
• Tasks API
• Error codes