Topaz Video Upscale

Name: Topaz Video Upscale
Author: Topaz Labs

topaz/upscale/video

Upscale Video is Topaz Labs's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Use in agent Get API key

Base price: $0.05 / run
Execution: async
Model type: video
Input fields: 9

Try the model

Playground

Open playground

Input

Video Url(string)

URL of the video to upscale

Noise(number)

Noise reduction level (0.0-1.0). Default varies by model. Range: 0 to 1.

Upscale Factor(number)

Factor to upscale the video by (e.g. 2.0 doubles width and height) Range: 1 to 4.

Halo(number)

Halo reduction level (0.0-1.0). Default varies by model. Range: 0 to 1.

Compression(number)

Compression artifact removal level (0.0-1.0). Default varies by model. Range: 0 to 1.

Grain(number)

00.1

Film grain amount (0.0-0.1). Default varies by model. Range: 0 to 0.1.

Recover Detail(number)

Recover original detail level (0.0-1.0). Higher values preserve more original detail. Range: 0 to 1.

Target Fps(integer)

1660

Target FPS for frame interpolation. If set, frame interpolation will be enabled. Range: 16 to 60.

H264 Output(boolean)

Whether to use H264 codec for output video. Default is H265.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.05 / run
Billing formula: Math.max((usage.duration ?? 0.0), 5.0) * (((usage.width ?? 0.0) * (usage.height ?? 0.0)) <= 0.0 ? 0.08 : ((usage.width * usage.height) <= 921600.0 ? 0.01 : ((usage.width * usage.height) <= 2073600.0 ? 0.02 : 0.08))) * ((usage.fps ?? (params.target_fps ?? 30.0)) >= 60.0 ? 2.0 : 1.0) * ((params.model ?? "") == "Gaia 2" ? 0.5 : 1.0)

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Topaz Labs
Model ID: topaz/upscale/video
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Topaz Video Upscale

topaz/upscale/video is documented for video to video tasks in the upscale family.

topaz/upscale/video can use the documented H264 output to produce the documented result for video to video tasks within the upscale family.

Highlights

topaz/upscale/video is documented for video to video tasks in the upscale family.
topaz/upscale/video can use the documented H264 output to produce the documented result for video to video tasks within the upscale family.

Pricing

Local price formula: Math.max((usage.duration ?? 0.0), 5.0) * (((usage.width ?? 0.0) * (usage.height ?? 0.0)) <= 0.0 ? 0.08 : ((usage.width * usage.height) <= 921600.0 ? 0.01 : ((usage.width * usage.height) <= 2073600.0 ? 0.02 : 0.08))) * ((usage.fps ?? (params.target_fps ?? 30.0)) >= 60.0 ? 2.0 : 1.0) * ((params.model ?? "") == "Gaia 2" ? 0.5 : 1.0)

Technical Specs

Model ID: topaz/upscale/video
Request fields: H264_output (boolean, optional); compression (number, optional, min 0, max 1); grain (number, optional, min 0, max 0.1); halo (number, optional, min 0, max 1); noise (number, optional, min 0, max 1); recover_detail (number, optional, min 0, max 1); target_fps (integer, optional, min 16, max 60); upscale_factor (number, optional, min 1, max 4); video (string, optional)
Required fields: none marked required
Output fields: content_type (string, optional); url (string, required)
Execution mode: async

When to Use

Choose topaz/upscale/video when the upscale workflow needs video to video tasks.
Use topaz/upscale/video in the upscale workflow for projects with the documented H264 output that require generated output.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Endpoint

https://api.sandbase.ai/v1/run

Model ID

topaz/upscale/video

# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJ0b3Bhei91cHNjYWxlL3ZpZGVvIiwKICAidmlkZW8iOiAiaHR0cHM6Ly9zdGF0aWMuc2FuZGJhc2UuYWkvZXhhbXBsZXMvdG9wYXovdXBzY2FsZS92aWRlby9pbnB1dF92aWRlb18wLm1wNCIsCiAgIkgyNjRfb3V0cHV0IjogZmFsc2UsCiAgInVwc2NhbGVfZmFjdG9yIjogMgp9' \
  | base64 --decode \
  | curl --fail-with-body --silent \
      -X POST "https://api.sandbase.ai/v1/run" \
      -H "Authorization: Bearer $SANDBASE_API_KEY" \
      -H "Content-Type: application/json" \
      --data-binary @-)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
Topaz Video UpscaleThis model `Topaz Labs`	—	—	—	Mar 4, 2025