What Is reAPI? Models, Pricing, and How to Use It in 2026

reAPI is one API for generative AI across every modality. A single key and base URL reach 200+ image, video, audio, and chat models, the chat side speaks the OpenAI format, and every model is priced 20-50% below the providers' official rates. Instead of opening an account with each vendor, wiring up four billing systems, and maintaining four SDKs, you integrate once.

This guide covers what reAPI is, the models it carries, what it costs, and how to make your first call. Every endpoint and code sample below is the real API; you can paste them and run them after creating a key.

What is reAPI?

reAPI is a unified API gateway for AI models. One endpoint, https://reapi.ai/api/v1, serves text and reasoning models, image generation, video generation, and audio, billed from a single pay-as-you-go credit balance.

Two request styles sit behind that one base URL:

• Chat models are synchronous and OpenAI-compatible. Point an OpenAI client at reAPI's base URL and your existing code works.
• Image, video, and audio are asynchronous. You submit a job, get a task id back immediately, and poll until it finishes.

The result is one integration that covers GPT-5, Claude Opus 4.8, and Gemini for text, plus Veo 3.1, Seedance 2.0, and GPT-Image-2 for media, without four separate vendor relationships.

Core features and benefits

• One key for 200+ models. Switch models by changing a string, not by onboarding a new vendor.
• OpenAI-compatible chat. A drop-in for existing OpenAI code; change the base URL and key.
• 20-50% below official rates. The same frontier models, priced under what the providers charge directly.
• Every modality. Text, image, video, and audio under one balance.
• Pay-as-you-go credits. No subscription, no minimum spend; 1 credit equals $0.001, and new accounts start with free credits.
• Automatic refunds on failure. A failed generation refunds its credits the moment the job ends in failure, with no support ticket.

How reAPI works

Authentication is a Bearer token on every request:

Authorization: Bearer rk_live_xxxxxxxxxxxx

Create a key in the reAPI dashboard under API Keys. The key works across chat and media, so one credential covers the whole platform.

Chat requests return in one round trip, the same as calling OpenAI. Media requests are asynchronous because image and video take seconds to minutes to render:

POST /api/v1/images/generations   →   { task_id, status: "processing" }
        │
        ▼
GET  /api/v1/tasks/{task_id}       →   processing → completed / failed
                                          │
                                          ▼
                                   output.image_urls

reAPI calls the upstream model exactly once per request you send. There is no idempotency deduplication: every successful POST creates a task and charges credits, so a request is never silently skipped, and a failed task is refunded automatically.

Call a chat model in the OpenAI format

Because the chat surface is OpenAI-compatible, the official OpenAI SDK works with two changes, the base URL and the key:

from openai import OpenAI

client = OpenAI(
    base_url="https://reapi.ai/api/v1",
    api_key="rk_live_xxx",
)

resp = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {"role": "user", "content": "Tell me what reAPI does in one sentence."},
    ],
)
print(resp.choices[0].message.content)

Swap model for claude-opus-4-8 or a Gemini model and the rest of the call is identical. The same pattern works in the Node SDK and any OpenAI-compatible tooling.

Generate an image

Submit the job, then poll the task:

curl https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "a cute red panda eating bamboo, photorealistic",
    "size": "1:1"
  }'

The response comes back immediately with a task id and status: "processing". Poll until it is done:

curl https://reapi.ai/api/v1/tasks/task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e \
  -H "Authorization: Bearer rk_live_xxx"

When status is completed, the image is at output.image_urls[0], rehosted on reAPI's CDN. Poll about once every one to two seconds; image tasks usually finish within seconds.

Generate a video

Video uses the same submit-then-poll pattern, on the videos endpoint:

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0",
    "prompt": "a drone shot flying over a coastal city at sunset",
    "resolution": "720p"
  }'

Video runs longer than image, so pace polling accordingly; the task reaches completed with the result at output.video_urls[0]. Per-model request fields are documented on each model's page.

What reAPI costs

reAPI is pay-as-you-go with no subscription and no minimum spend. Credits are the unit: 1 credit equals $0.001, and you spend them per call. New accounts start with free credits, so the first request costs nothing.

Media is billed at a flat rate per output, which means a render costs the same whether the GPU was warm or cold:

Chat models bill per token at the same 20-50% discount below official rates. A failed task is refunded automatically and in full, so you only ever pay for output you actually receive.

Reliability and billing, in plain terms

A few platform rules are worth knowing before you build on reAPI.

Billing is one credit equals $0.001, deducted per call from a single balance, with no monthly fee and no minimum spend. A failed task is refunded automatically and atomically the moment the job ends in failure, before any poll sees the failed status, and the refund happens once and only once.

reAPI calls the upstream model exactly once for every request you send, with no idempotency deduplication. That keeps billing honest: you are charged for the calls you make, never silently double-charged and never silently skipped. If you need retry safety, send each payload once on your side, or lean on the automatic refund and resubmit.

Requests are rate-limited per user at five per second, polling included, so pace polling to about once every one to two seconds. Generated files are rehosted on reAPI's CDN; copy anything you need long-term into your own storage once a task completes.

reAPI vs calling each provider direct

Going direct means one account, key, SDK, and invoice per vendor. reAPI collapses that into one of each, at a lower rate.

Models on reAPI

The catalog spans every modality. A sample of what is live:

• Chat and reasoning: GPT-5.5, GPT-5.4, Claude Opus 4.8, Claude Sonnet 4.6, Gemini.
• Image: GPT-Image-2, Gemini 3 Pro Image, Imagen 4, Seedream 5.0.
• Video: Veo 3.1, Seedance 2.0, Wan 2.7, Kling, HappyHorse 1.0, PixVerse V6, Vidu Q3.
• Audio and music: Mureka V9, plus voice tools for cleanup, separation, and conversion.

Browse the full set on the reapi.ai/models directory, each with its request schema and pricing.

Who uses reAPI

The platform fits any team that touches more than one model:

• SaaS products adding AI features without standing up a vendor integration per capability.
• Content and marketing teams generating images and video at a flat per-output cost.
• Agencies billing client work against one predictable balance.
• Researchers A/B testing models by changing a string instead of an account.

FAQ

Is reAPI OpenAI-compatible?

Yes, for chat. Point an OpenAI client at https://reapi.ai/api/v1 with your reAPI key and existing code works. Image and video use reAPI's asynchronous task endpoints under the same base URL and key.

How much does reAPI cost?

It is pay-as-you-go with no subscription. Credits are 1 credit = $0.001, models run 20-50% below the providers' official rates, and new accounts start with free credits. Media is flat per output, for example GPT-Image-2 from $0.0066 per image.

What models does reAPI support?

200+ models across chat, image, video, and audio, including GPT-5, Claude Opus 4.8, Gemini, Veo 3.1, Seedance 2.0, Wan 2.7, and GPT-Image-2. The full list is on reapi.ai/models.

Do I need separate keys for chat and media?

No. One reAPI key works across chat, image, video, and audio, billed from a single credit balance.

What happens if a generation fails?

The credits are refunded automatically, in full, the moment the task ends in failure. The refund is one-shot and happens before any poll observes the failure, so you never pay for a failed render.

Does reAPI deduplicate repeated requests?

No. Every successful POST to a generation endpoint creates a new task and charges credits, by design, so no upstream call is ever silently skipped. Handle retry safety on your side.

How do I get started?

Create an account at reapi.ai, make a key under API Keys, and send the chat or image request above. The first call runs on your free starting credits.

Further reading

• reapi.ai/docs/api — full API conventions and the task reference.
• What can reAPI do for you? — use cases across image, video, and LLMs.
• Best fal.ai alternatives — how reAPI compares to a media-only API.

Getting started with reAPI

reAPI exists to remove the busywork between you and a model: one key, one balance, and one base URL for 200+ image, video, audio, and chat models, priced below what the providers charge directly. Create a key, point your OpenAI client at https://reapi.ai/api/v1, and the first request runs on free credits. That is the whole of what it takes to start using reAPI.