Hailuo 2.3 is video generation AI model developed by Minimax. Minimax model for realistic human motion and VFX Access it through Railwail's unified, OpenAI-compatible API at €0.000 per 1M input tokens.

How much does Hailuo 2.3 cost via Railwail?

Per-call: €0.50. No monthly minimum, no subscription. Start with €5 free credits.

What is the context window of Hailuo 2.3?

Hailuo 2.3 supports a unknown context window — enough for typical AI workloads.

How fast is Hailuo 2.3?

Average response latency: 60.0s (p50 across recent Railwail traffic). See live p50/p95 metrics on /rankings.

Is Hailuo 2.3 better than Google Veo 2?

It depends on your use case. Hailuo 2.3 (Minimax) and Google Veo 2 (Google DeepMind) are both strong choices in video generation. Compare them side-by-side at /compare/hailuo-23-vs-google-veo-2.

Hailuo 2.3

Name: Hailuo 2.3
Brand: Replicate
SKU: hailuo-23
Price: 0.5 EUR
Availability: InStock

New

Minimax

Video Generation

Minimax model for realistic human motion and VFX

Queue video with Hailuo 2.3

Video generation runs asynchronously — we'll queue a job and you can track it in your history.

Generates as an async job — typically 30 s to 2 min.

TL;DR·Last updated March 25, 2026

Hailuo 2.3 is video generation AI model from Minimax, priced at €0.000 per 1M input tokens with a unknown context window.

Try Hailuo 2.3

Prompt

Image References

Start Image

Upload

Subject Reference

Add

Duration

Aspect Ratio

Examples

See what Hailuo 2.3 can generate

0:06

Dance

"Dancer in empty warehouse, dramatic lighting"

Pricing

Price per Generation

Per generation€0.50

API Integration

Use our OpenAI-compatible API to integrate Hailuo 2.3 into your application.

Install

npm install railwail

JavaScript / TypeScript

import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

// Simple — just pass a string
const reply = await rw.run("hailuo-23", "Hello! What can you do?");
console.log(reply);

// With message history
const reply2 = await rw.run("hailuo-23", [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);

// Full response with usage info
const res = await rw.chat("hailuo-23", [
  { role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);

Specifications

Price

€0.50

Avg. latency

60.0s

Est. duration

1min

Developer

Minimax

Deep dive — MiniMax's Hailuo 2.3

About MiniMax

Founded 2021 · Shanghai, China

MiniMax (Shanghai Xiyu Technology) was founded in December 2021 by Yan Junjie (former SenseTime general manager) along with co-founders from SenseTime and Microsoft Research Asia. It is one of China's four AI tigers alongside Zhipu, Moonshot and Baichuan. MiniMax developed the abab LLM family, the Hailuo AI consumer chat app and the Hailuo video generator (launched September 2024). The company has raised over $1B from investors including Tencent, Alibaba, HongShan (Sequoia China) and Mihoyo, valuing it at $2.5B+ in 2024. Hailuo Video gained early international traction as one of the first Chinese consumer video AIs available outside China.

Visit MiniMax →

Architecture

Latent video diffusion model (Diffusion Transformer)

Hailuo 2.3 is MiniMax's third-generation video model, building on Hailuo Video-01 and 02. It is a closed-source diffusion-transformer (DiT) operating on a learned spatio-temporal latent space, conditioned on bilingual (Chinese/English) text embeddings and optional image embeddings. Version 2.3 advertises substantial improvements over earlier versions in motion coherence, prompt adherence on complex actions and 'cinematic' control. MiniMax publish no architectural details beyond marketing material, but the product behaviour and reported throughput suggest a multi-billion-parameter DiT trained on a large curated video corpus with synthetic dense captions and reward-model post-training for aesthetics. Hailuo 2.3 supports 6-10 second clips at up to 1080p and a director-style control vocabulary (camera moves, shot scale).

Parameters: Undisclosed
Context: unknown

What it can do