Models

Every model, and what it costs.

26 generative models across Video, Image, Voice, and Music — the frontier models you already know, plus 5 we run on our own GPUs so the same job costs a fraction. One credit wallet pays for all of them.

Video Generation8Image Generation7Voice & Speech4Music Generation4

Video Generation

  • Selecting Google Veo 3.1 in the AutorunX Cam Talk model picker

    Veo 3.1

    Veo 3.1

    Google's flagship text-to-video and image-to-video model with native synced audio.

    40 credits / sec (Fast) · 60 credits / sec (Pro) — an 8s clip is 320 / 480 credits

    OpenCreate
  • An example generation rendered with Kling 3.0 on AutorunX

    Kling 3.0

    Kling 3.0

    Kuaishou's flagship video model with native multi-lingual audio, in-video editing, and clips up to native 4K.

    80 credits / sec (Kling 3.0/o3) — an 8s clip is 640 credits

    OpenCreate
  • An example generation rendered with Hailuo 2.3 on AutorunX

    Hailuo 2.3

    Hailuo 2.3

    MiniMax's Hailuo 2.3 delivers high-motion, physics-aware video clips with subject reference and flat per-clip billing.

    27 credits / sec (flat — always billed at max clip length)

    OpenCreate
  • An example generation rendered with Seedance 2.0 on AutorunX

    Seedance 2.0

    Seedance 2.0

    ByteDance's default AutorunX video engine for Short Film, Movie Maker, and Ad Remake — identity-preserving reference-to-video at up to 4K.

    162 credits / sec (Fast, Short Film/Movie Maker default) · 200 credits / sec (2.0/Identity, Ad Remake/Sync Motion default)

    OpenCreate
  • An example generation rendered with OmniHuman 1.5 on AutorunX

    OmniHuman

    OmniHuman

    ByteDance's audio-driven human video model that animates a photo to speak and move in sync with a given audio track.

    168 credits / sec (Music Video/Explainer/Brand Story default)

    OpenCreate
  • An example generation rendered with Wan on AutorunX

    Wan

    Wan

    Alibaba's open Wan model family, run two ways on AutorunX: self-hosted Wan 2.2 for cost-efficient generation, and cloud Wan 3.0 for up to 30-second clips.

    3 credits / sec (owned Wan 2.2) · 75 credits / sec (cloud Wan 3.0 @ 720p)

    OpenCreate
  • An example generation rendered with Grok Imagine Video on AutorunX

    Grok Imagine

    Grok Imagine

    xAI's image-to-video model that brings a still image to life with realistic motion over 30-second clips.

    13 credits / sec

    OpenCreate
  • An example generation rendered with Happy Horse on AutorunX

    Happy Horse

    Happy Horse

    An Alibaba-built image-to-video model offering 15-second clips at up to 1080p, available on AutorunX.

    125 credits / sec

    OpenCreate

Image Generation

  • A real AutorunX photo generated with OpenAI GPT Image 2

    GPT Image 2

    GPT Image 2

    OpenAI's natively multimodal image model — the default engine behind Face / Identity.

    48 credits / image

    OpenCreate
  • An example generation rendered with Nano Banana on AutorunX

    Nano Banana

    Nano Banana

    Google's Gemini-family image model, nicknamed Nano Banana for its viral photorealistic edits, generates and edits images up to a 4K-capable tier.

    37 credits / image (Nano Banana 2) · 80 credits / image (Nano Banana Pro)

    OpenCreate
  • An example generation rendered with Seedream on AutorunX

    Seedream

    Seedream

    ByteDance's Seedream generates and edits images from up to ten reference photos, holding identity and composition steady across a full shoot.

    35 credits / image (4.5, Product Shots default) · 47 credits / image (5.0 Pro, Storyboard default)

    OpenCreate
  • An example generation rendered with Qwen-Image-Edit on AutorunX

    Qwen-Image

    Qwen-Image

    Alibaba's open-weight 20B image editor, self-hosted by AutorunX as AX-QWN, preserves identity through fine-grained edits at near-zero marginal cost.

    20 credits / image (AX-QWN owned, and Qwen-Image-Edit-Plus hosted tier)

    OpenCreate
  • An example generation rendered with Krea 2 Turbo on AutorunX

    Krea 2

    Krea 2

    Krea's fast-distilled image model trades a step of top-end fidelity for low latency and low cost, built for high-volume lightweight content.

    40 credits / image

    OpenCreate
  • An example generation rendered with Z-Image Turbo on AutorunX

    Z-Image

    Z-Image

    Alibaba Tongyi Lab's 6B open-weight model generates photorealistic images in as few as 8 steps, making it AutorunX's cheapest image option.

    5 credits / image (cheapest image option on AutorunX)

    OpenCreate
  • An example generation rendered with FLUX.2 Klein on AutorunX

    FLUX.2 Klein

    FLUX.2 Klein

    Black Forest Labs' compact, Apache 2.0 FLUX model, self-hosted by AutorunX as AX-KLN, delivers sub-second exact-identity generation at the platform's lowest cost.

    5 credits / image — the cheapest image option on AutorunX alongside Z-Image Turbo, and roughly 10x cheaper than GPT Image 2's per-image cost

    OpenCreate

Voice & Speech

  • ElevenLabs cinematic cover still

    ElevenLabs

    ElevenLabs

    Industry-leading neural TTS and instant voice cloning — planned as a premium cloud voice lane on AutorunX.

    Coming soon

    OpenCreate
  • OpenAI TTS cinematic cover still

    OpenAI TTS

    OpenAI TTS

    OpenAI's cloud text-to-speech models — planned premium narration lane for AutorunX Voice.

    Coming soon

    OpenCreate
  • Cartesia Sonic cinematic cover still

    Cartesia Sonic

    Cartesia Sonic

    Low-latency streaming TTS from Cartesia — planned real-time cloud voice lane for AutorunX.

    Coming soon

    OpenCreate
  • PlayAI cinematic cover still

    PlayAI

    PlayAI

    PlayAI (PlayHT) cloud voices — planned expressive TTS and cloning option on AutorunX.

    Coming soon

    OpenCreate

Music Generation

  • Selecting Suno v5 in the AutorunX Song Builder model picker

    Suno v5

    Suno v5

    Suno's song-generation model — full arranged tracks with vocals from a prompt.

    86 credits / song

    OpenCreate
  • An example generation rendered with Musicful on AutorunX

    Musicful

    Musicful

    A cloud prompt-to-song API that turns text prompts or lyrics into fully produced tracks, selectable in Song Builder.

    122 credits / song

    OpenCreate
  • An example generation rendered with Lyria 3 on AutorunX

    Lyria 3

    Lyria 3

    Google DeepMind's latent-diffusion music model, reached via OpenRouter, as a selectable song-generation engine in AutorunX.

    86 credits / song

    OpenCreate
  • Udio cinematic cover still

    Udio

    Udio

    Udio AI music generation — planned additional cloud song engine for AutorunX Music.

    Coming soon

    OpenCreate
AutorunX owned

Why we run our own models

5 of these run on GPUs we operate, under commercial licences we hold. That is why an owned-lane image costs 3 credits where a frontier model costs 38 — same wallet, same panel, you pick per job.

Pick a model and generate.

Every model here is one click from a create panel. Start on the free plan — no card required.

Start freeSee pricing