Compare model

Video

Topaz Labs logoStarlight Fast 2

starlight-fast-2

Best for: Restoring and upscaling existing footage to a 1080p or 4K tier

Share

Catalog status

Enabled

Research checked

2026-11-11

Benchmark results

No recorded results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

Published benchmark coverage

Reviewed sources do not include results for this exact version. Provider specifications and API capabilities remain listed separately.

Model specifications

Target tiers

1080p (1920x1080) or 4K (3840x2160); shape and frame rate are kept

Documented capability

Upscaling factor

1 only

Documented capability

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Video

Output

Restored, upscaled video
Exact model ID
starlight-fast-2
Model type
Video
Target tiers
1080p (1920x1080) or 4K (3840x2160); shape and frame rate are kept
Upscaling factor
1 only
Containers
MP4, MOV, MKV, WebM, AVI and 16 more
Job length
Can take hours; jobs keep running after you close the page

Exact token limits are not published in the reviewed sources, so no estimated limits are shown.

Standard and Fast versions

One enabled version is currently listed for this model.

Starlight Fast 2Selected$0.084 per Topaz unit

Pricing and controls

Topaz Labs logoMade by Topaz Labs

Topaz unit$0.12 per unitTokenRex price $0.084
1080p tier1 unit per 52.0833 frames
4K tier1 unit per 23.8357 frames

frames = end_index − start_index + 1; units = ceil(frames ÷ frames per unit); cost = units × $0.12 (300 frames: $0.72 at 1080p, $1.56 at 4K). Units reported by the provider take precedence.

Market list prices in USD before the TokenRex discount; your wallet is charged in its own currency using TokenRex's standard conversion. A hold is placed before the job starts, settled once when it finishes, and released if it fails. No cache discounts apply.

Controls TokenRex accepts

  • All fields are required and must describe the real file: video_uri (public HTTPS), source_container, source_width, source_height, frame_count, frame_rate.
  • start_index and end_index — zero-based, inclusive, end ≥ start. Source up to 600 seconds.
  • target_resolution — 1920x1080 or 3840x2160 tier; shape and frame rate are kept (768×512 at 8 fps → 1920×1280 or 3240×2160). upscaling_factor — 1 only.
  • Restoration only: no prompt, sound, new scenes or frame interpolation.

Send controls inside input (preferred) or flat beside model — never both. Unknown fields are refused.

Restore a video with Starlight Fast 2

curl https://tokenrex.ai/api/public/v1/videos \
  -H "Authorization: Bearer $TOKENREX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "starlight-fast-2",
  "input": {
    "video_uri": "https://YOUR_PUBLIC_MEDIA_HOST/source.mp4",
    "source_container": "mp4",
    "source_width": 768,
    "source_height": 512,
    "frame_count": 16,
    "frame_rate": 8,
    "start_index": 0,
    "end_index": 15,
    "target_resolution": "1920x1080",
    "upscaling_factor": 1
  },
  "stream": false
}'

Check and download the job

# 1. Check the job (free — polling never charges)
curl https://tokenrex.ai/api/public/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer $TOKENREX_API_KEY"
# → {"id":"video_…","status":"queued|in_progress|completed|failed","progress":40,"created_at":…,"expires_at":…}

# 2. When status is "completed", download the MP4
curl -L -o result.mp4 https://tokenrex.ai/api/public/v1/videos/VIDEO_ID/content \
  -H "Authorization: Bearer $TOKENREX_API_KEY"
  • Save the returned id as soon as POST /v1/videos answers; the job keeps running if your app or browser closes.
  • Poll GET /v1/videos/{id} every 5–30 seconds with the same API key. Seedance usually needs minutes; Starlight restoration can take hours.
  • Polling and downloads never charge again — the job is settled once, when it first reports completed or failed.
  • Do not resend a create request after a timeout: a second request is a second paid job.

Errors

400 invalid_request_errorA control is missing, out of range or not supported (unknown fields are refused, never ignored). Nothing is charged.
402 insufficient_balanceYour wallet cannot cover the hold. Nothing is sent to the model.
status "failed" (for example moderation_blocked)The model refused or could not finish. The hold is released and nothing is charged.
409 job_failed on /contentThe job failed, so there is no file to download.
410 expiredThe result passed its expires_at time and can no longer be downloaded. Save files before then.
502 outcome_unknownThe connection broke while creating the job, so TokenRex cannot tell whether it started. It is never retried automatically; check your wallet history before sending again.

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

A public HTTPS source video with its exact size, frame count, frame rate and frame range on POST /v1/videos.

Output through TokenRex

Available

A job id; the restored MP4 downloads from /v1/videos/{id}/content. Functional test: 30 frames restored to 1920×1080.

Prompt, sound or new scenes

Not exposed

Restoration only — it does not take a prompt, add sound, create scenes or add frames.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (3)
  • Functional test through TokenRex (2026-11-11): frames 0–29 of a 640×360, 30 fps MP4 restored to a 1920×1080, 30 fps MP4 with 30 frames in about 75 seconds. This is a working check, not a quality benchmark.
  • Restoration only: it does not create new scenes, sound or extra frames, and it takes no prompt.
  • Source size, frame count and frame rate must be the real values from the file; TokenRex never estimates them.