Skip to content

What are Models

Models are the AI systems that do the actual generation. Get3W exposes models from 25 providers behind one API and one addressing scheme.

Model Slugs

Every model is addressed by a three-part slug:

{provider_id}/{model_id}/{run_type}

Examples:

  • google/nano-banana-pro/text-to-image
  • bytedance/seedance-2/reference-to-video
  • minimax/music-2.6/text-to-music
  • tripo/p1/image-to-3d

The slug is also the request path, so the model you want is the endpoint you call:

POST /v1/google/nano-banana-pro/text-to-image

The same model_id can support several run types. alibaba/wan-3 for instance handles text-to-video, first-to-video, first-last-to-video, and reference-to-video — the run type you pick determines which inputs are required.

Run Types

Run typeInput → Output
text-to-imagePrompt → image
image-to-imageImage + prompt → image (edit, upscale, restyle)
text-to-videoPrompt → video
first-to-videoFirst frame + prompt → video
first-last-to-videoFirst and last frame + prompt → video
reference-to-videoReference images + prompt → video
video-to-videoVideo + prompt → video
digital-humanPortrait + audio → talking avatar video
text-to-speechText → audio
text-to-musicPrompt → music
speech-to-textAudio → transcribed text
text-to-3dPrompt → 3D model
image-to-3dImage → 3D model
text-to-panoramaPrompt → 360° panorama
image-to-panoramaImage → 360° panorama
chatMessages → text (OpenAI-compatible)

Providers

Models come from Alibaba, Anthropic, Bilibili, Black Forest Labs, ByteDance, ElevenLabs, Google, Ideogram, JD, Kling, Lightricks, Midjourney, MiniMax, OpenAI, PixVerse, Recraft, Runway, SkyReels, Tencent, Topaz, Tripo, Vidu, xAI, Ace Step, and Get3W's own models.

The provider_id in a slug identifies who made the model, not which infrastructure serves it. A single slug can be served by several upstream platforms, and Get3W fails over between them within one task — see How Get3W Works.

Channels

Many models accept a channel in the request body to select a service tier:

json
{
  "prompt": "A sunset over mountains",
  "channel": "stable"
}

The common set:

ChannelTrade-off
economyCheapest, best for bulk work
stableBalanced speed and reliability
officialDirect official provider access

Some model families use their own values instead — for example turbo / balanced / quality on Ideogram, turbo / pro on Vidu, pro / fast on Lightricks, and standard / human where a real-person path exists. Omit channel and Get3W applies that model's default.

Channel affects price, latency, and which upstream providers are eligible, so it is worth benchmarking before settling on one.

Parameters

Each model has its own input schema. Parameters that recur across many:

ParameterDescriptionTypical use
promptText description of the outputMost models
image_url / image_urlsInput image(s)Image and video models
video_url / video_urlsInput video(s)Video-to-video, reference-to-video
aspect_ratioOutput framing, e.g. 16:9Image and video models
resolutionOutput resolution, e.g. 1k, 720pImage and video models
durationVideo length in secondsVideo models
output_formatFile format, e.g. pngImage models
seedSeed for reproducibilityMany models
channelService tierWhere supported

TIP

Parameter names, allowed values, and defaults vary per model. Each model's page on get3w.com/models lists its full schema. Sending an unsupported value returns 1401 Invalid Parameter in the task result.

Pricing

Price depends on the model, the channel, and output characteristics such as resolution and video duration. Your account tier can discount it further, per model. Every request is priced before it is queued and your balance is checked, so an underfunded call fails fast with 402 rather than running and overdrawing. See How Pricing Works.

Finding Models

Browse the full catalog with filters at get3w.com/models. Each model page shows its slug, supported run types, channels, parameters, and price.

For chat models specifically, there is an OpenAI-compatible listing endpoint:

bash
curl "https://api.get3w.com/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

This returns only the chat models, matching what OpenAI clients expect from /v1/models. Generation models are not included — use the models catalog on the website for those.

Next Steps

Released under the MIT License.