PROVIDER

MiniMax AI Models

Q: Is this an official MiniMax integration?

RunAPI exposes a managed API surface with transparent per-call pricing, fully documented capability and parameters, and clear error behavior. You get the same model output quality without managing a direct provider relationship or provider-side account.

Q: Do I need a MiniMax account?

No. Your RunAPI API key is enough for managed access to all MiniMax models. You do not need to create a separate account, manage provider-specific credentials, or handle provider-side billing.

Q: What's the latency overhead from proxying through RunAPI?

Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions to minimize added latency. Media generation time is dominated by the model itself, not the proxy.

Q: Are images / videos cached?

Generated outputs are stored and retrievable by task ID. You can fetch completed results at any time using the task status endpoint or the RunAPI dashboard. Output URLs remain accessible for the retention period shown in the API docs. Inputs are not cached or stored.

Q: Can I bring my own key?

Not currently. Calls use RunAPI-managed access, which simplifies authentication and lets RunAPI handle rate limiting, retries, and billing consolidation on your behalf.

Q: How is billing consolidated?

All API calls across all providers appear on a single monthly USD invoice. There is no per-provider billing, no subscription, and no minimum spend. Failed generations are never charged.

Q: What SDKs can I use with MiniMax models?

Official SDKs are available for Python, Node.js, PHP, Java, Ruby, and Go. Each SDK handles authentication, async task polling, and typed responses. For LLM models, the OpenAI and Anthropic SDKs also work by pointing the base URL to RunAPI.

Q: What are model skills and how do they work?

Model skills are installable packages that load a model's docs, typed schemas, pricing notes, and setup steps directly into your coding workspace. Install a skill with one command and your agent has the right context before you write integration code. Skills work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code.

Q: How do I switch between MiniMax models?

Change the model parameter in your API request. All MiniMax models share the same API key, the same request shape, and the same billing. No code changes, no re-authentication, and no separate billing setup are required when switching between models or between variants of the same model. You can also switch to models from other providers by changing the same parameter — the API surface is unified across the entire catalog.

Hailuo video generation at native 1080p with accurate physics simulation and complex motion.

2 models · 13 variants · from $0.010

Browse all models API docs →

All MiniMax models available through RunAPI 2 models

Hailuo Video

6 variants · from $0.300

MiniMax Text

7 variants · from $0.010

OVERVIEW

MiniMax develops Hailuo, a video generation model producing text-to-video and image-to-video at native 1080p with accurate physics simulation, complex motion, and human pose fidelity.

Single API key shared across all providers
No separate %{provider} account required
Model skills carry docs, schemas, and setup steps into your workspace
Per-call billing in USD, no subscription or minimum spend
Failed generations are never charged
Switch models by changing one parameter
Billing consolidated into one monthly invoice

FEATURES

What stands out

FASTEST

Hailuo

P50 ~ <1s

One of the most-used model APIs from MiniMax, chosen by developers for its balance of output quality, speed, and pricing.

FRONTIER

Hailuo

Frontier tier

One of the most-used model APIs from MiniMax, chosen by developers for its balance of output quality, speed, and pricing.

CHEAPEST

MiniMax

from $0.010

Lowest starting price across the MiniMax catalog, suited for high-volume workflows and cost-sensitive production pipelines.

MODELS

All MiniMax models available through RunAPI

Hailuo

MiniMax

Video

Hailuo API access for text and image-to-video at native 1080p with accurate physics simulation and motion.

from $0.300 / call View →

MiniMax

Text

MiniMax text API access via RunAPI — 230B MoE models from 200K to 1M context, up to 80.5% SWE-bench Verified.

/v1/chat/completions endpoint

from $0.010 / 1K tokens View →

QUICKSTART

Install a MiniMax model skill for your app.

Pick a model and add its skill so your coding tool has docs, schemas, pricing notes, and setup steps. Skills work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code. Install once, then switch models by changing one parameter.

runapi.ai

curl -X POST https://runapi.ai/api/v1/hailuo/image_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "hailuo-2.3-image-to-video-standard",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
}'

import { HailuoClient } from "@runapi.ai/hailuo";

const client = new HailuoClient();
const result = await client.imageToVideo.run({
    model: "hailuo-2.3-image-to-video-standard",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge.",
});

<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\Hailuo\HailuoClient;

$client = new HailuoClient();
$result = $client->imageToVideo->run([
        'model' => 'hailuo-2.3-image-to-video-standard',
        'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
        'prompt' => 'Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge.',
]);

require "runapi/hailuo"

client = RunApi::Hailuo::Client.new
result = client.image_to_video.run(
    model: "hailuo-2.3-image-to-video-standard",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
)

npx skills add runapi-ai/hailuo -g

# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor

@runapi.ai/hailuo v1

REFERENCE

Every MiniMax variant with pricing and model IDs

Full pricing table →

Model	Variant	Billing	From
Hailuo	hailuo-02-image-to-video-pro	call	$0.570	View →
	hailuo-02-image-to-video-standard	call	$0.300	View →
	hailuo-02-text-to-video-pro	call	$0.570	View →
	hailuo-02-text-to-video-standard	call	$0.500	View →
	hailuo-2.3-image-to-video-pro	call	$0.900	View →
	hailuo-2.3-image-to-video-standard	call	$0.500	View →
MiniMax	MiniMax-M2	1K tokens	$0.010	View →
	MiniMax-M2.1	1K tokens	$0.010	View →
	MiniMax-M2.5	1K tokens	$0.010	View →
	MiniMax-M2.5-highspeed	1K tokens	$0.020	View →
	MiniMax-M2.7	1K tokens	$0.010	View →
	MiniMax-M2.7-highspeed	1K tokens	$0.020	View →
	MiniMax-M3	1K tokens	$0.010	View →

FAQ

Frequently asked questions about MiniMax

Is this an official MiniMax integration?

RunAPI exposes a managed API surface with transparent per-call pricing, fully documented capability and parameters, and clear error behavior. You get the same model output quality without managing a direct provider relationship or provider-side account.

Do I need a MiniMax account?

No. Your RunAPI API key is enough for managed access to all MiniMax models. You do not need to create a separate account, manage provider-specific credentials, or handle provider-side billing.

What's the latency overhead from proxying through RunAPI?

Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions to minimize added latency. Media generation time is dominated by the model itself, not the proxy.

Are images / videos cached?

Generated outputs are stored and retrievable by task ID. You can fetch completed results at any time using the task status endpoint or the RunAPI dashboard. Output URLs remain accessible for the retention period shown in the API docs. Inputs are not cached or stored.

Can I bring my own key?

Not currently. Calls use RunAPI-managed access, which simplifies authentication and lets RunAPI handle rate limiting, retries, and billing consolidation on your behalf.

How is billing consolidated?

All API calls across all providers appear on a single monthly USD invoice. There is no per-provider billing, no subscription, and no minimum spend. Failed generations are never charged.

What SDKs can I use with MiniMax models?

Official SDKs are available for Python, Node.js, PHP, Java, Ruby, and Go. Each SDK handles authentication, async task polling, and typed responses. For LLM models, the OpenAI and Anthropic SDKs also work by pointing the base URL to RunAPI.

What are model skills and how do they work?

Model skills are installable packages that load a model's docs, typed schemas, pricing notes, and setup steps directly into your coding workspace. Install a skill with one command and your agent has the right context before you write integration code. Skills work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code.

How do I switch between MiniMax models?

Change the model parameter in your API request. All MiniMax models share the same API key, the same request shape, and the same billing. No code changes, no re-authentication, and no separate billing setup are required when switching between models or between variants of the same model. You can also switch to models from other providers by changing the same parameter — the API surface is unified across the entire catalog.