# AI Video Generator API

> Generate videos from text prompts using 20+ AI models — Veo 3, Kling, Seedance, Hunyuan, Runway, Pixverse, Vidu, Hailuo — through one MuApi.ai endpoint.

## Overview

MuApi unifies every leading text-to-video model behind a single API. Submit a prompt, optionally a reference image and duration, get a request ID, then poll for an `outputs[]` array of MP4 URLs. Veo 3 and Kling Master deliver cinematic quality at high cost; Seedance Lite and Hunyuan are the fastest and cheapest; Runway and Pixverse fit the social-content pipeline; Hailuo and Vidu offer specialty motion controls. One integration, twenty providers — switch models by changing the URL path, not the SDK.

- 20+ text-to-video models — Veo 3 / Veo 3 Fast, Kling Master, Seedance Pro/Lite, Hunyuan, Runway, Pixverse, Vidu, Hailuo, Wan 2.1/2.2
- Same submit-and-poll pattern as image models — one client handles every modality
- Per-call credits with dynamic cost based on duration / resolution
- Webhook callbacks for long jobs (videos can take 60-300s)
- Optional reference image input on most models

## API Pattern

Every model in this category uses the same submit-then-poll API:

```http
POST https://api.muapi.ai/api/v1/{model}
x-api-key: YOUR_API_KEY
Content-Type: application/json
```

Response: `{ "request_id": "abc123", "status": "processing" }`. Poll `GET https://api.muapi.ai/api/v1/predictions/{request_id}/result` until `status` is `completed` — the result URLs are in the `outputs[]` array. Optionally pass `?webhook=https://your-server` on the submit call to receive a callback instead of polling.

Get an API key at https://muapi.ai/access-keys.

## Quick Start

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/veo3-fast-text-to-video \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a cinematic shot of a city at night with neon reflections"}' | jq -r .request_id)

# 2. Poll
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

## Models in This Category

- [openai-sora-2-text-to-video](https://muapi.ai/playground/openai-sora-2-text-to-video): Sora 2 T2V converts text prompts into short, dynamic 10-second video clips with synchronized audio. Users can describe scenes, motion, camera angles, and sound…
  - Endpoint: `POST https://api.muapi.ai/api/v1/openai-sora-2-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/openai-sora-2-text-to-video/llms.txt
  - Cost: 0.800 credits per call
- [sd-2-t2v](https://muapi.ai/playground/sd-2-t2v): SD 2.0 is the latest multimodal video generation model by ByteDance, offering advanced camera control, native audio-video sync, and high-resolution output.
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-t2v/llms.txt
  - Cost: 0.750 credits per call
- [seedance-lite-t2v](https://muapi.ai/playground/seedance-lite-t2v): Seedance Lite T2V offers quick video generation from text with decent visual quality and motion. Ideal for fast previews, prototyping, or lightweight use cases…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedance-lite-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/seedance-lite-t2v/llms.txt
  - Cost: 0.100 credits per call
- [veo3-fast-text-to-video](https://muapi.ai/playground/veo3-fast-text-to-video): VEO3 Fast T2V creates short videos from text instantly, balancing speed and quality for quick content generation and prototyping.
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3-fast-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3-fast-text-to-video/llms.txt
  - Cost: 0.600 credits per call
- [grok-imagine-text-to-video](https://muapi.ai/playground/grok-imagine-text-to-video): Grok Imagine is xAI’s fast, creative text-to-video model that generates cinematic clips from 6 to 30 seconds with smooth motion, expressive lighting, and ambie…
  - Endpoint: `POST https://api.muapi.ai/api/v1/grok-imagine-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/grok-imagine-text-to-video/llms.txt
  - Cost: 0.150 credits per call
- [veo3.1-fast-text-to-video](https://muapi.ai/playground/veo3.1-fast-text-to-video): Veo 3.1 Fast T2V is a high-speed AI video model that transforms text prompts into realistic 8-second videos. It emphasizes rapid generation while maintaining v…
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3.1-fast-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3.1-fast-text-to-video/llms.txt
  - Cost: 0.600 credits per call
- [sd-2-extend](https://muapi.ai/playground/sd-2-extend): SD 2.0 Extend Video continues an existing SD 2.0 generated video seamlessly. Provide the original request ID and an optional prompt to guide the extension — th…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-extend`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-extend/llms.txt
  - Cost: 1.050 credits per call
- [seedance-pro-t2v](https://muapi.ai/playground/seedance-pro-t2v): Seedance Pro delivers high-fidelity video generation from text, producing rich visuals, smooth camera movement, and realistic scenes. Best for storytelling, co…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedance-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/seedance-pro-t2v/llms.txt
  - Cost: 0.180 credits per call
- [kling-v3.0-pro-text-to-video](https://muapi.ai/playground/kling-v3.0-pro-text-to-video): Kling 3.0 Pro is a high-end video generation model capable of producing longer, smoother, and more realistic cinematic videos with strong motion consistency. I…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-pro-text-to-video/llms.txt
  - Cost: 0.720 credits per call
- [openai-sora-2-pro-text-to-video](https://muapi.ai/playground/openai-sora-2-pro-text-to-video): Sora 2 Pro T2V is the high-fidelity version of OpenAI’s video generation model. It converts your text prompts into cinematic, richly detailed video clips with…
  - Endpoint: `POST https://api.muapi.ai/api/v1/openai-sora-2-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/openai-sora-2-pro-text-to-video/llms.txt
  - Cost: 2.400 credits per call
- [veo3.1-text-to-video](https://muapi.ai/playground/veo3.1-text-to-video): Veo 3.1 is Google's advanced AI video generation model that transforms text prompts into high-quality videos. This model offers enhanced realism, richer audio,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3.1-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3.1-text-to-video/llms.txt
  - Cost: 2.500 credits per call
- [veo3-text-to-video](https://muapi.ai/playground/veo3-text-to-video): VEO3 T2V generates cinematic videos from text prompts, capturing dynamic motion, rich scenes, and storytelling visuals in stunning detail.
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3-text-to-video/llms.txt
  - Cost: 2.500 credits per call
- [kling-v2.6-pro-t2v](https://muapi.ai/playground/kling-v2.6-pro-t2v): Kling-v2.6-Pro Text-to-Video generates high-fidelity cinematic videos directly from text prompts. It excels at complex compositions, dramatic lighting, fluid c…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v2.6-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v2.6-pro-t2v/llms.txt
  - Cost: 0.900 credits per call
- [sd-2-text-to-video-fast](https://muapi.ai/playground/sd-2-text-to-video-fast): SD 2 Text-to-Video (Fast) by ByteDance. Generates video from text at faster speeds with 4–15 second duration and 2K resolution.
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-text-to-video-fast`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-text-to-video-fast/llms.txt
  - Cost: 0.750 credits per call
- [kling-v2.5-turbo-pro-t2v](https://muapi.ai/playground/kling-v2.5-turbo-pro-t2v): Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v2.5-turbo-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v2.5-turbo-pro-t2v/llms.txt
  - Cost: 0.450 credits per call
- [kling-v2.1-master-t2v](https://muapi.ai/playground/kling-v2.1-master-t2v): Kling 2.1 Master’s T2V mode allows users to generate vivid, high-quality videos from detailed text prompts. It supports dynamic scenes, natural motion, and cin…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v2.1-master-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v2.1-master-t2v/llms.txt
  - Cost: 1.200 credits per call
- [sd-2-t2v-480p](https://muapi.ai/playground/sd-2-t2v-480p): SD 2.0 480p text-to-video generation. Faster and more cost-effective than the 720p variant, ideal for previews and drafts.
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-t2v-480p`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-t2v-480p/llms.txt
  - Cost: 0.600 credits per call
- [seedance-v1.5-pro-t2v-fast](https://muapi.ai/playground/seedance-v1.5-pro-t2v-fast): Seedance v1.5 Pro Text-to-Video Fast generates short cinematic videos directly from text with an emphasis on speed and stability. It produces coherent scenes w…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedance-v1.5-pro-t2v-fast`
  - Per-model llms.txt: https://muapi.ai/playground/seedance-v1.5-pro-t2v-fast/llms.txt
  - Cost: 0.260 credits per call
- [kling-v3.0-standard-text-to-video](https://muapi.ai/playground/kling-v3.0-standard-text-to-video): Kling 3.0 Standard Text-to-Video generates smooth, realistic videos from text with stable motion and natural behavior. It works best with clear subjects, simpl…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-standard-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-standard-text-to-video/llms.txt
  - Cost: 0.720 credits per call
- [seedance-pro-t2v-fast](https://muapi.ai/playground/seedance-pro-t2v-fast): Seedance Pro Fast is ByteDance’s advanced text-to-video model that turns natural-language prompts into short, cinematic video clips with realistic motion, came…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedance-pro-t2v-fast`
  - Per-model llms.txt: https://muapi.ai/playground/seedance-pro-t2v-fast/llms.txt
  - Cost: 0.060 credits per call
- [runway-text-to-video](https://muapi.ai/playground/runway-text-to-video): Generate short, high-quality videos from plain text prompts. RunwayML’s text-to-video model interprets your written description and animates it into a moving v…
  - Endpoint: `POST https://api.muapi.ai/api/v1/runway-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/runway-text-to-video/llms.txt
  - Cost: 0.090 credits per call
- [wan2.2-text-to-video](https://muapi.ai/playground/wan2.2-text-to-video): Wan 2.2’s T2V mode transforms descriptive text prompts into high-quality, stylized video sequences. It excels at generating anime-style or cinematic visuals wi…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.2-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.2-text-to-video/llms.txt
  - Cost: 0.300 credits per call
- [sd-2-text-to-video](https://muapi.ai/playground/sd-2-text-to-video): SD 2 Text-to-Video (Pro) by ByteDance. Generates high-quality cinematic video from a text prompt with native audio-visual sync, up to 2K resolution, and 4–15 s…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-text-to-video/llms.txt
  - Cost: 1.250 credits per call
- [seedance-v1.5-pro-t2v](https://muapi.ai/playground/seedance-v1.5-pro-t2v): Seedance v1.5 Pro Text-to-Video generates high-quality cinematic videos directly from text prompts. It focuses on smooth motion, rich atmosphere, and coherent…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedance-v1.5-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/seedance-v1.5-pro-t2v/llms.txt
  - Cost: 0.340 credits per call
- [openai-sora-2-pro-storyboard](https://muapi.ai/playground/openai-sora-2-pro-storyboard): Sora 2 Pro enables creators to structure video narratives by chaining multiple scenes through storyboard “cards.” Each card defines a segment of the video—sett…
  - Endpoint: `POST https://api.muapi.ai/api/v1/openai-sora-2-pro-storyboard`
  - Per-model llms.txt: https://muapi.ai/playground/openai-sora-2-pro-storyboard/llms.txt
  - Cost: 0.580 credits per call
- [wan2.1-text-to-video](https://muapi.ai/playground/wan2.1-text-to-video): WAN 2.1 turns your written prompts into vivid, cinematic video clips. Ideal for storytelling, content creation, and visualizing abstract ideas, it supports det…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.1-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.1-text-to-video/llms.txt
  - Cost: 0.300 credits per call
- [wan2.6-text-to-video](https://muapi.ai/playground/wan2.6-text-to-video): WAN 2.6 Text-to-Video generates smooth, cinematic videos directly from text prompts. It’s designed for strong scene coherence, atmospheric depth, and fluid cam…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.6-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.6-text-to-video/llms.txt
  - Cost: 0.650 credits per call
- [pixverse-v6-t2v](https://muapi.ai/playground/pixverse-v6-t2v): Generate high-quality videos from text prompts using PixVerse V6. Supports resolutions up to 1080p, durations up to 15 seconds, and optional AI-generated audio.
  - Endpoint: `POST https://api.muapi.ai/api/v1/pixverse-v6-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/pixverse-v6-t2v/llms.txt
  - Cost: 0.295 credits per call
- [wan2.5-text-to-video](https://muapi.ai/playground/wan2.5-text-to-video): WAN 2.5 Text-to-Video transforms written prompts into cinematic video clips with dynamic motion, realistic physics, and natural animation. It can also generate…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.5-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.5-text-to-video/llms.txt
  - Cost: 0.650 credits per call
- [sd-2-vip-text-to-video](https://muapi.ai/playground/sd-2-vip-text-to-video): SD 2 Text-to-Video VIP (Pro) by ByteDance. Generates high-quality cinematic video from a text prompt with priority routing, native audio-visual sync, up to 2K…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-vip-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-vip-text-to-video/llms.txt
  - Cost: 1.500 credits per call
- [openai-sora](https://muapi.ai/playground/openai-sora): Sora is a text-to-video generative AI model developed by OpenAI. It can generate short video clips based on descriptive text inputs, producing content that ran…
  - Endpoint: `POST https://api.muapi.ai/api/v1/openai-sora`
  - Per-model llms.txt: https://muapi.ai/playground/openai-sora/llms.txt
  - Cost: 0.500 credits per call
- [kling-o1-text-to-video](https://muapi.ai/playground/kling-o1-text-to-video): Kling O1 is a unified, multi-modal video generation engine that transforms natural language prompts into short cinematic video clips. It supports text-to-video…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-o1-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-o1-text-to-video/llms.txt
  - Cost: 0.720 credits per call
- [wan2.2-5b-fast-t2v](https://muapi.ai/playground/wan2.2-5b-fast-t2v): Wan 2.2 Fast is a lightweight, high-speed version of the Wan 2.2 model, optimized for quick text-to-video generation. It trades some cinematic detail for rapid…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.2-5b-fast-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.2-5b-fast-t2v/llms.txt
  - Cost: 0.016 credits per call
- [wan2.5-text-to-video-fast](https://muapi.ai/playground/wan2.5-text-to-video-fast): Transform text prompts into short, cinematic videos with natural motion, realistic environments, and dynamic camera perspectives. Fast mode delivers quick, hig…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.5-text-to-video-fast`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.5-text-to-video-fast/llms.txt
  - Cost: 0.440 credits per call
- [sd-2-vip-text-to-video-fast](https://muapi.ai/playground/sd-2-vip-text-to-video-fast): SD 2 Text-to-Video VIP Fast by ByteDance. Faster generation with priority routing from a text prompt, 4–15 second duration and 2K resolution.
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-vip-text-to-video-fast`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-vip-text-to-video-fast/llms.txt
  - Cost: 1.050 credits per call
- [veo3.1-lite-text-to-video](https://muapi.ai/playground/veo3.1-lite-text-to-video): Veo 3.1 Lite is a lightweight variant of Google's Veo 3.1 model designed for faster, more accessible video generation.
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3.1-lite-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3.1-lite-text-to-video/llms.txt
  - Cost: 0.300 credits per call
- [openai-sora-2-standard-text-to-video](https://muapi.ai/playground/openai-sora-2-standard-text-to-video): OpenAI Sora 2 Standard Text to Video model (High Priority). Generate stunning 10s videos from text prompts.
  - Endpoint: `POST https://api.muapi.ai/api/v1/openai-sora-2-standard-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/openai-sora-2-standard-text-to-video/llms.txt
  - Cost: 0.300 credits per call
- [hunyuan-text-to-video](https://muapi.ai/playground/hunyuan-text-to-video): Hunyuan T2V generates detailed and dynamic videos from text prompts with a focus on realism and coherent motion. It handles multi-object scenes, human actions,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hunyuan-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/hunyuan-text-to-video/llms.txt
  - Cost: 0.150 credits per call
- [minimax-hailuo-2.3-pro-t2v](https://muapi.ai/playground/minimax-hailuo-2.3-pro-t2v): Hailuo 2.3 Pro T2V turns your imagination into motion-picture realism. It interprets natural language prompts and generates visually stunning cinematic sequenc…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-hailuo-2.3-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-hailuo-2.3-pro-t2v/llms.txt
  - Cost: 0.630 credits per call
- [ltx-2-pro-text-to-video](https://muapi.ai/playground/ltx-2-pro-text-to-video): LTX-2 Pro is the high-fidelity video-generation engine by Lightricks designed for professional workflows, supporting both text-to-video and image-to-video inpu…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ltx-2-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/ltx-2-pro-text-to-video/llms.txt
  - Cost: 0.460 credits per call
- [wan2.7-text-to-video](https://muapi.ai/playground/wan2.7-text-to-video): Alibaba WAN 2.7 Text-to-Video turns plain prompts into coherent, cinematic clips.
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.7-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.7-text-to-video/llms.txt
  - Cost: 0.100 credits per call
- [happy-horse-1-text-to-video-720p](https://muapi.ai/playground/happy-horse-1-text-to-video-720p): Happy Horse 1.0 Text to Video (720p) — generate expressive, stylized video clips from text prompts at 720p output resolution.
  - Endpoint: `POST https://api.muapi.ai/api/v1/happy-horse-1-text-to-video-720p`
  - Per-model llms.txt: https://muapi.ai/playground/happy-horse-1-text-to-video-720p/llms.txt
  - Cost: 0.900 credits per call
- [hunyuan-fast-text-to-video](https://muapi.ai/playground/hunyuan-fast-text-to-video): Hunyuan Fast T2V provides accelerated video generation from text prompts with slightly reduced detail but excellent speed. Ideal for rapid prototyping, concept…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hunyuan-fast-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/hunyuan-fast-text-to-video/llms.txt
  - Cost: 0.050 credits per call
- [minimax-hailuo-02-standard-t2v](https://muapi.ai/playground/minimax-hailuo-02-standard-t2v): Fast and lightweight text-to-video generation. Ideal for quick drafts, previews, or playful content where speed matters more than cinematic quality.
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-hailuo-02-standard-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-hailuo-02-standard-t2v/llms.txt
  - Cost: 0.300 credits per call
- [ltx-2-19b-text-to-video](https://muapi.ai/playground/ltx-2-19b-text-to-video): LTX-2-19B Text-to-Video generates coherent cinematic videos directly from text, with an emphasis on temporal stability, natural motion, and conceptual clarity.…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ltx-2-19b-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/ltx-2-19b-text-to-video/llms.txt
  - Cost: 0.600 credits per call
- [minimax-hailuo-02-pro-t2v](https://muapi.ai/playground/minimax-hailuo-02-pro-t2v): High-fidelity text-to-video with cinematic rendering. Best for storytelling, cinematic clips, or realistic visuals with depth, atmosphere, and detail.
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-hailuo-02-pro-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-hailuo-02-pro-t2v/llms.txt
  - Cost: 0.600 credits per call
- [pixverse-v5-t2v](https://muapi.ai/playground/pixverse-v5-t2v): PixVerse V5 delivers a major leap forward in AI-powered video creation — now featuring smoother motion, ultra-high resolution, and expanded visual effects.
  - Endpoint: `POST https://api.muapi.ai/api/v1/pixverse-v5-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/pixverse-v5-t2v/llms.txt
  - Cost: 0.300 credits per call
- [ltx-2-fast-text-to-video](https://muapi.ai/playground/ltx-2-fast-text-to-video): LTX Video Fast is a speed-optimised mode of Lightricks’ video-generation engine, supporting text-to-video workflows. It allows you to input a descriptive promp…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ltx-2-fast-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/ltx-2-fast-text-to-video/llms.txt
  - Cost: 0.460 credits per call
- [minimax-hailuo-2.3-standard-t2v](https://muapi.ai/playground/minimax-hailuo-2.3-standard-t2v): Hailuo 2.3 Standard T2V transforms pure imagination into moving cinematic visuals. Simply describe a scene, and this model generates a coherent, high-quality v…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-hailuo-2.3-standard-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-hailuo-2.3-standard-t2v/llms.txt
  - Cost: 0.360 credits per call
- [ltx-2.3-text-to-video](https://muapi.ai/playground/ltx-2.3-text-to-video): LTX-2.3 Text-to-Video generates cinematic video clips directly from text prompts. Built on an upgraded 2.3B architecture, it delivers sharper temporal consiste…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ltx-2.3-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/ltx-2.3-text-to-video/llms.txt
  - Cost: 0.104 credits per call
- [ovi-text-to-video](https://muapi.ai/playground/ovi-text-to-video): Ovi is a unified model that generates synchronized video and audio from textual input. You write a scene description, including dialogue and ambient sounds, an…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ovi-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/ovi-text-to-video/llms.txt
  - Cost: 0.200 credits per call
- [pixverse-v5.5-t2v](https://muapi.ai/playground/pixverse-v5.5-t2v): PixVerse v5.5 T2V generates cinematic short videos directly from text. It excels at stylized fantasy, anime, surreal worlds, atmospheric environments, and flui…
  - Endpoint: `POST https://api.muapi.ai/api/v1/pixverse-v5.5-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/pixverse-v5.5-t2v/llms.txt
  - Cost: 0.100 credits per call
- [happy-horse-1-text-to-video-1080p](https://muapi.ai/playground/happy-horse-1-text-to-video-1080p): Happy Horse 1.0 Text to Video — generate expressive, stylized video clips from text prompts with vivid character motion and dynamic scene storytelling.
  - Endpoint: `POST https://api.muapi.ai/api/v1/happy-horse-1-text-to-video-1080p`
  - Per-model llms.txt: https://muapi.ai/playground/happy-horse-1-text-to-video-1080p/llms.txt
  - Cost: 1.800 credits per call
- [grok-imagine-extend](https://muapi.ai/playground/grok-imagine-extend): Grok Imagine Extend lets you continue and expand existing Grok Imagine video generations seamlessly. Starting from a previously generated video, you can extend…
  - Endpoint: `POST https://api.muapi.ai/api/v1/grok-imagine-extend`
  - Per-model llms.txt: https://muapi.ai/playground/grok-imagine-extend/llms.txt
  - Cost: 0.050 credits per call
- [veo3.1-extend-video](https://muapi.ai/playground/veo3.1-extend-video): Veo 3.1’s Extend Video mode lets you continue or expand an existing video clip seamlessly. Starting from a short generated video, you can prompt the model to e…
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3.1-extend-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3.1-extend-video/llms.txt
  - Cost: 0.600 credits per call
- [pixverse-v4.5-t2v](https://muapi.ai/playground/pixverse-v4.5-t2v): PixVerse v4.5 transforms descriptive text into vivid, high-resolution video clips. It understands complex scenes, human motion, and cinematic camera angles — g…
  - Endpoint: `POST https://api.muapi.ai/api/v1/pixverse-v4.5-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/pixverse-v4.5-t2v/llms.txt
  - Cost: 0.300 credits per call
- [sd-2-vip-text-to-video-1080p](https://muapi.ai/playground/sd-2-vip-text-to-video-1080p): SD 2 Text-to-Video VIP 1080p by ByteDance. Generates cinematic 1080p video from a text prompt with priority routing, native audio-visual sync, and 4–15 second…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-vip-text-to-video-1080p`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-vip-text-to-video-1080p/llms.txt
  - Cost: 3.375 credits per call
- [kling-v3.0-4k-text-to-video](https://muapi.ai/playground/kling-v3.0-4k-text-to-video): Kling 3.0 4K Text-to-Video generates ultra-high-resolution 3840×2160 cinematic video directly from text prompts with smooth, realistic motion and strong tempor…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-4k-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-4k-text-to-video/llms.txt
  - Cost: 2.000 credits per call
- [vidu-q2-pro-text-to-video](https://muapi.ai/playground/vidu-q2-pro-text-to-video): Vidu Q2 Pro Text-to-Video generates cinematic, prompt-faithful clips from text alone with strong temporal consistency and rich detail at up to 1080p. Pick this…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q2-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q2-pro-text-to-video/llms.txt
  - Cost: 0.200 credits per call
- [vidu-q3-turbo-text-to-video](https://muapi.ai/playground/vidu-q3-turbo-text-to-video): Vidu Q3 Turbo Text-to-Video is the fast, affordable tier of Vidu Q3 — same prompt understanding and motion quality, optimised for rapid iteration. Use it for s…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q3-turbo-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q3-turbo-text-to-video/llms.txt
  - Cost: 0.300 credits per call
- [vidu-q3-pro-text-to-video](https://muapi.ai/playground/vidu-q3-pro-text-to-video): Vidu Q3 Pro Text-to-Video generates cinematic, prompt-faithful clips with strong temporal consistency, accurate motion, and rich detail across resolutions up t…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q3-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q3-pro-text-to-video/llms.txt
  - Cost: 0.750 credits per call
- [veo3.1-4k-video](https://muapi.ai/playground/veo3.1-4k-video): Get the ultra-high-definition 4K version of a Veo3.1 video generation task. This model is optimized for producing crisp, detailed videos suitable for professio…
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo3.1-4k-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo3.1-4k-video/llms.txt
  - Cost: 0.600 credits per call
- [vidu-q2-turbo-text-to-video](https://muapi.ai/playground/vidu-q2-turbo-text-to-video): Vidu Q2 Turbo Text-to-Video is the fast, affordable Q2 tier for prompt-only generation. Use it for storyboards, social cuts, and high-volume work where speed a…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q2-turbo-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q2-turbo-text-to-video/llms.txt
  - Cost: 0.130 credits per call
- [sd-2-vip-extend](https://muapi.ai/playground/sd-2-vip-extend): SD 2.0 VIP Extend Video continues an existing SD 2.0 generated video seamlessly at 720p. Provide the original request ID and an optional prompt to guide the ex…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-vip-extend`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-vip-extend/llms.txt
  - Cost: 1.050 credits per call
- [sd-2-vip-extend-1080p](https://muapi.ai/playground/sd-2-vip-extend-1080p): SD 2.0 VIP Extend Video 1080p continues an existing SD 2.0 generated video seamlessly at 1080p resolution. Provide the original request ID and an optional prom…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-vip-extend-1080p`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-vip-extend-1080p/llms.txt
  - Cost: 2.362 credits per call
- [kling-v3.0-omni-4k-text-to-video](https://muapi.ai/playground/kling-v3.0-omni-4k-text-to-video): Kling v3 Omni at 4K. Multi-image reference video generation — supply up to 4 images and reference them in your prompt with <<<image_N>>>. Apimart-backed.
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-omni-4k-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-omni-4k-text-to-video/llms.txt
  - Cost: 2.679 credits per call
- [kling-v3.0-omni-pro-text-to-video](https://muapi.ai/playground/kling-v3.0-omni-pro-text-to-video): Kling v3 Omni at 1080P. Multi-image reference video generation — supply up to 4 images and reference them in your prompt with <<<image_N>>>. Apimart-backed.
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-omni-pro-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-omni-pro-text-to-video/llms.txt
  - Cost: 0.560 credits per call
- [kling-v3.0-omni-standard-text-to-video](https://muapi.ai/playground/kling-v3.0-omni-standard-text-to-video): Kling v3 Omni at 720P. Multi-image reference video generation — supply up to 4 images and reference them in your prompt with <<<image_N>>>. Apimart-backed.
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-v3.0-omni-standard-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/kling-v3.0-omni-standard-text-to-video/llms.txt
  - Cost: 0.420 credits per call
- [veo-4-text-to-video](https://muapi.ai/playground/veo-4-text-to-video): Veo 4 Text to Video — Google DeepMind's fourth-generation model delivering photorealistic, high-fidelity 1080p videos with exceptional prompt adherence and cin…
  - Endpoint: `POST https://api.muapi.ai/api/v1/veo-4-text-to-video`
  - Per-model llms.txt: https://muapi.ai/playground/veo-4-text-to-video/llms.txt
  - Cost: 3.000 credits per call
- [vidu-v2.0-t2v](https://muapi.ai/playground/vidu-v2.0-t2v): Vidu's 2.0 model offers enhanced visual quality and comprehensive workflow support across multiple resolution options for versatile content creation.
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-v2.0-t2v`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-v2.0-t2v/llms.txt
  - Cost: 0.300 credits per call

## FAQ

**Which AI video generator API is the best?**

Veo 3 and Kling Master produce the highest-quality cinematic output but cost more credits. Seedance Lite and Hunyuan are the fastest and cheapest for social-format content. Runway delivers the strongest motion fidelity and brand-friendly outputs. The right pick depends on quality vs. cost vs. latency — MuApi gives you all three to evaluate without rewriting your code.

**How long does a video take?**

Anywhere from 30 seconds (Seedance Lite, 5s clip) to 4-5 minutes (Veo 3, 8s clip). Use the polling endpoint or pass `?webhook=https://your-server/path` on the submit call to receive a callback when it finishes.

**Can I generate longer videos?**

Most models cap individual clips at 5-10 seconds. For longer sequences, chain multiple clips together using the workflow builder or generate keyframes with image models and stitch them via image-to-video models.

**What format do I get back?**

An MP4 URL in the `outputs[]` array of the polling response. URLs are hosted on MuApi's CDN and remain available for 30 days.

**Do I need to handle retries?**

MuApi automatically retries transient provider failures up to 3 times. For client errors (invalid prompt, content moderation), the polling endpoint returns `status: failed` with an `error` message — no retry will help.

## Agent Integration

MuApi ships an MCP server so agents (Claude Code, Cursor, custom) can call every model in this category as a tool:

```bash
npm install -g muapi-cli
muapi auth login
muapi mcp serve  # exposes all MuApi models as MCP tools
```

## Resources

- Category page: https://muapi.ai/playground/group/text-to-video
- Global llms.txt: https://muapi.ai/llms.txt
- API docs: https://muapi.ai/docs
- OpenAPI spec: https://api.muapi.ai/openapi.json