Runway's API lists 19 video ids: which ones have a Sume id?
Of 19 video ids on Runway's pricing page, 9 map to a Sume id by name, 2 are unconfirmed, and 8 have no Sume equivalent. Full mapping table with the Sume ids.

Nine of the 19 video ids on Runway's API pricing page map cleanly to a Sume id, eight have no Sume equivalent, and two (h3_max, hailuo3) I cannot confirm from Runway's page alone. If you are porting a Runway script, this table tells you which model strings you can swap and which you must replace.
Runway's list is read from its pricing page on 2026-10-10. Sume's ids come from the API registry and the Video Generation docs.
The mapping
Runway lists these ids: wan3, wan3_prime, seedance2_5, grok_imagine_1_5, grok_imagine_1_5_lite, seedance2, seedance2_fast, seedance2_mini, h3_max, hailuo3, aleph2, gen4.5, gen4_turbo, act_two, veo3.1, veo3.1_fast, happyhorse_1_0, gemini_omni_flash and gemini_omni_flash_1.1 (read 2026-10-10).
Sume's registry carries the Seedance family, Wan 3.0, the 1.5 Grok row, Gemini Omni Flash 1.1, Kling 3, MiniMax H3 and H3 Max, and, where switched on, the Veo 3.1 rows.
| Runway id | Sume id | Status |
|---|---|---|
| wan3 | wan-3.0 | Match |
| seedance2_5 | seedance-2.5 | Match |
| seedance2 | seedance-2 | Match |
| seedance2_fast | seedance-2-fast | Match |
| seedance2_mini | seedance-2-mini | Match |
| grok_imagine_1_5 | grok-imagine-video-1.5 | Match, image slot only |
| gemini_omni_flash_1.1 | gemini-omni-flash-1.1 | Match |
| veo3.1 and veo3.1_fast | veo-3.1, veo-3.1-fast | Match if listed in catalog |
| h3_max, hailuo3 | minimax-h3-max, minimax-h3 | Unconfirmed, names only |
| wan3_prime, grok_imagine_1_5_lite, gemini_omni_flash | None | Not on Sume |
| aleph2, gen4.5, gen4_turbo, act_two, happyhorse_1_0 | None | Not on Sume |
What changes when you swap an id
Matching ids do not mean matching requests. Sume's POST /v1/videos takes model, prompt, duration, resolution and aspect_ratio, plus frame_images and input_references. Per the Video Generation docs, size, seed and non-empty provider.options return a 400 unsupported_parameter, so strip them from a ported script.
The Grok row needs an image: the schema requires one of image_url, first_frame_url or one reference image, and rejects aspect_ratio, end frames and reference video or audio. Runway's page also lists a 1-credit start-image surcharge on its Lite row, so confirm which inputs your script sends before you compare totals.
Billing differs by design
Runway bills in credits at $0.01 each. Sume bills the workspace USD balance, reserving provider list price times 1.25 at submit, and usage.cost reports the billable amount. A matching id therefore does not mean a matching bill.
For example, Runway's Seedance 2.5 line is 20, 30 and 68 credits per output second at 480p, 720p and 1080p, which is $0.20, $0.30 and $0.68 per second, plus input seconds. Running the estimator in Sume's pricing package for a 16:9, 5-second request at 720p gives a billed $2.889, or about $0.58 per second, because Seedance is priced per video token. Compare your real clip, not the label.
| Source | Basis | 5-second clip |
|---|---|---|
| Runway (read 2026-10-10) | 30 credits per output second | $1.50, plus input seconds if any |
| Sume billed | Provider list x 1.25 | $2.889 |
A porting checklist
Work through a ported script in this order. First, replace the model string with the Sume id from the table, and call GET /v1/videos/models to confirm it is returned for your workspace. Second, delete size, seed and provider.options. Third, check the duration against the row's supported_durations: Omni takes 3 to 10 seconds, Seedance 2.5 and Wan 3.0 take up to 30. Fourth, add an Idempotency-Key header to every submit, because a replay returns the original job instead of billing twice.
Finally, read usage.cost on the completed job and compare it with your Runway credit spend for a few real clips. Do this before you move volume, since the rate cards are built differently.
Ids Sume does not have
For Aleph, Gen-4.5 and Act Two there is no Sume id, so no model string replaces them. For video editing on Sume, the docs list Gemini Omni Flash 1.1 (through video_url) and H3 Max Recast. Look at the linked posts for HappyHorse and Veo, which Sume handles differently.
Sources
Related posts
More in Comparisons
- Runway Gen-4.5 at $0.12 a second: nearest Sume rows by capability
Runway's API lists Gen-4.5 at $0.12 per second; Sume has no Gen-4.5 row. These Sume rows take text and image input, with 8-second prices to compare.
- Runway model routers vs sume/auto: what you can steer
Runway's routers pick a model by cost, latency or quality. Sume's sume/auto takes no preference, limits clips to 3-10 s and never names the family.
- Seedance 2.5 on Runway and on Sume: same 30 s, different pricing unit
Runway lists Seedance 2.5 up to 30 seconds from $0.20 per second. Sume bills tokens: about $2.69, $5.78 or $14.22 for 10 s at 480p, 720p, 1080p.
- Seedream 4 vs 4.5 vs 5 Lite on Sume: price, ratios, auto
Seedream 4, 4.5 and 5 Lite are all in the Sume image catalog. Compare price, reference limit, aspect ratios and which one lists auto, with 12-image cost.
Written by Sume