Skip to content
ScaleMax

Images & Video API

OpenAI-compatible image generation and Grok Imagine video routes, model ids, and published flat prices.

Authenticate with Authorization: Bearer $SCALEMAX_API_KEY. Match the billing surface: credit keys use https://api.scalemax.pro/v1; token keys use https://api.scalemax.pro/token/v1. Image models appear in GET /v1/models with family: "image". Video models use family: "video" when listed.

Image model ids and prices

Flat per-image pricing by quality tier (same rates as ScaleMax Image 2). Token keys debit the derived token units at the published $2.50 = 1M rate.

Model idLowMediumHigh
grok-imagine-image$0.006$0.053$0.211
grok-imagine-image-quality$0.006$0.053$0.211
Also published: qwen-image-*, wan2.7-image*, flux-2-*, gpt-image-* — see the live catalog or GET /v1/models.

POST /v1/images/generations

OpenAI-compatible image generation. Returns a synchronous JSON body with image URLs or base64 data.

FieldTypeRequiredNotes
modelstringyesOne of the published image model ids.
promptstringyesText prompt.
nintegernoBatch size up to the model limit (Grok Imagine: 4).
sizestringnoPixel size or aspect ratio (Grok Imagine accepts 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, auto).
qualitystringnolow | medium | high (selects the flat tier).
image-generate.sh
curl -X POST "https://api.scalemax.pro/v1/images/generations" \
  -H "Authorization: Bearer $SCALEMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-imagine-image","prompt":"A red circle on white","size":"1:1","quality":"medium","n":1}'

POST /v1/images/edits

Edit an existing image. Grok Imagine models accept a reference image URL or upload (model-dependent).

Video model ids and prices

Flat per-job charge at the published $2.50 = 1M token rate. Duration 1–15 seconds; resolutions 480p, 720p, 1080p.

Model idCredit priceToken unitsNotes
grok-imagine-video$0.25100,000Text-to-video and image-to-video.
grok-imagine-video-1.5$0.375150,000Image-to-video only — an input image is required.

Video routes

Native video generation is async: create returns 202 with a task id, poll until status is terminal, then download from the ScaleMax url field (never a third-party host). Completed jobs include usage with total_tokens and frontend_cost_microusd.

POST /v1/videos/generations

Start text-to-video or image-to-video generation.

FieldTypeRequiredNotes
modelstringyesgrok-imagine-video or grok-imagine-video-1.5.
promptstringyesScene description.
imagestring | objectconditionalRequired for grok-imagine-video-1.5 (I2V only). URL or uploaded reference.
aspect_ratiostringno1:1, 16:9, 9:16, 4:3, or 3:4.
resolutionstringno480p, 720p, or 1080p.
durationintegerno1–15; default 6. duration_seconds is accepted as an alias.

POST /v1/videos/edits

Edit an existing video clip with a new prompt.

POST /v1/videos/extensions

Extend a completed clip.

GET /v1/videos/:id

Poll task status and progress. Optional ?wait=0..20 long-poll seconds.

GET /v1/videos/:id/content

Stream the finished mp4. Supports Range after the task completes.

video-generate.sh
curl -X POST "https://api.scalemax.pro/v1/videos/generations" \
  -H "Authorization: Bearer $SCALEMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-imagine-video","prompt":"Ocean waves at sunset","aspect_ratio":"16:9","duration":6}'

Key scope

  • Credit keys: any general-purpose scope may call image and video models.
  • Token keys: Claude, OpenAI, combined, Gemini, GLM, Local, and Qwen packs may call the general image catalogue and all published video models.
  • Grok token packs may call grok-imagine-image* and grok-imagine-video* only — not Azure or Qwen image models.