Grok Imagine Video 1.5: Runway's listing vs Sume's catalog row
Sume's grok-imagine-video-1.5 row is image-to-video only, 480p or 720p, 4 to 15 s, no audio flag. Runway's changelog lists text-to-video and audio.

On Sume, grok-imagine-video-1.5 is an image-to-video row only: it needs image_url or first_frame_url, takes 480p or 720p, runs 4 to 15 seconds, and has no audio, end-frame or reference support in the catalog. Do not assume another vendor's listing carries over. Runway's changelog entry of Aug 13, 2026 says Grok Imagine 1.5 is available in Runway MCP with text-to-video and image-to-video, native audio, 1 to 15 second clips and up to 1080p; that is Runway's surface, not Sume's row.
Side by side
The Sume side is read from the Video Router docs; the Runway side is only what the vendor's changelog page states (the entry names Runway MCP, not a Runway API endpoint), so verify there before building.
| Capability | Sume row `grok-imagine-video-1.5` |
|---|---|
| Text to video | no |
| Image to video | yes, image_url or first_frame_url required |
| End frame | no |
| Reference images, videos, audios | no |
| Video to video | no |
| Audio flag | no |
| Resolutions | 480p, 720p |
| Duration | 4 to 15 seconds |
What this means for a plan
If your Grok workflow starts from a prompt alone, the Sume row will reject it: add a first frame, which you can make with an image model on Sume. If you need an end frame, use a row that lists end_frame, such as wan-3.0 or minimax-h3. If you need synchronized audio, pick a row with the audio capability and check the flag in the catalog first.
- Prompt only: use a text-to-video row, not this one.
- Photo to motion: this row fits.
- Two keyframes: use another row.
- Pricing: every Video Router row bills at provider list times 1.25.
Read the row yourself
The catalog is the source of truth and updates without a blog post. Fetch the row and look at capabilities and constraints before sending money-bearing requests.
curl -s https://api.sume.com/v1/video-router/models/grok-imagine-video-1.5 \
-H "Authorization: Bearer $SUME_API_KEY"Sources
The Sume behavior is documented on the Video Router page and the Video generation page; failed requests release their reserve per generation admission. For the vendor side, read the Runway changelog directly at the source link below.
Sources
Related posts
More in Comparisons
- Grok STT smart_turn end-of-turn vs Sume STT sentence segmentation
smart_turn predicts when a speaker is done in live streams. Sume STT is batch and cuts sentences from word timings. Which one do you need?
- Grok STT vad_threshold for quiet audio vs Sume STT, which has no gate
xAI added a vad_threshold knob to speech-to-text for quiet or noisy audio. Sume STT exposes no such gate; here is what you can tune instead.
- HeyGen translates 10 languages at once: what Sume does
HeyGen translate handles up to 10 target languages per job. Sume captions burn authored text per language, one $0.20 job per clip up to 60 seconds.
- HeyGen speaker rules as a checklist for a Sume face swap clip
HeyGen asks for a face within 45 degrees, one speaker at a time and under 10 feet. Use that as a pre-check, then Sume's own 4 to 15 second rules.
Written by Sume