Tokenify

Coming from the OpenAI Videos API

Their Videos API was shut down on 24 September 2026 and they publish no one-to-one replacement. This endpoint takes the same requests on the same paths, so the base URL and the model id are the change.

Their Videos API was shut down on 24 September 2026 and their own guide says “No one-to-one replacement API is available”. The dates live on this page rather than in our error messages, because a date compiled into a refusal becomes a false statement the day after it passes.
Only the model id does not carry over, and that is deliberate. Calling this endpoint with sora-2 is refused rather than quietly served by a different model. Echoing a model name we did not run into your logs and onto your invoice would put a false record in the two places you would check it. The refusal names where to find the ids that work here.

The change

Point the SDK at this gateway and name a model it serves. Everything else — the create call, the polling, the download — is the shape your code already builds.

from openai import OpenAI

client = OpenAI(
base_url="https://api.tokenify.dev/v1",
api_key="YOUR_TOKENIFY_KEY",
)

video = client.videos.create(
model="bytedance/seedance-2.0-mini", # not "sora-2"
prompt="a paper boat on still water",
size="1280x720",
seconds="8", # theirs took 4, 8 or 12
)

while video.status in ("queued", "in_progress"):
video = client.videos.retrieve(video.id)

content = client.videos.download_content(video.id, variant="video")
content.write_to_file("out.mp4")

The models page lists what each one generates, or call GET /v1/models and read kind: "video".

What maps, and what does not

The models are not theirs, so some parameters have different ranges. Nothing is silently adjusted: a value this endpoint cannot honour is refused by name, with the acceptable ones in the message. A request answered as though your value had been used, when it was not, is the one failure worth more than a refusal.

FieldTheirsHere
modelsora-2, sora-2-proA model this gateway serves. Their ids are refused with model_not_available
promptRequiredRequired, unchanged
size1280x720, 720x1280, 1024x1792, 1792x1024A pixel size that matches one of the model’s bands exactly. 1280×720 and 720×1280 are both 720p — the price follows the pixel count, not the orientation, and the orientation is carried through separately. Anything else is refused, including their 1024×1792: it is neither 720p nor 1080p, and substituting the nearer band would charge you for a frame size you did not choose
seconds4, 8 or 12, defaulting to 4A whole number inside the model’s own range, which is in GET /v1/models. Omit it for the model’s minimum
input_referenceAn image used as the first frameNot supported here yet, and refused rather than ignored: a disregarded first frame would produce a video of the prompt alone, charged in full, looking like the model had seen your image and dismissed it. Send a first frame through the model maker’s own dialect
charactersCharacter idsNot supported; refused by name
statusqueued, in_progress, completed, failedThe same four. A job cancelled here reports failed with a code, because their vocabulary has no cancelled and reporting completed would send you to download nothing
progressAn integer0 while waiting, 100 when finished. The suppliers report nothing in between, so there is nothing honest to put there
variantvideo, thumbnail, spritesheetOnly video. The other two are derived assets this gateway does not generate, and asking for one is refused rather than answered with the video

What it costs

Per output token, not per second of compute, and the count scales with the pixels, the frame rate and the length. There is no prompt charge. The rate depends on the resolution band, so the size you send decides the price — which is why an unrecognised one is refused rather than mapped to the nearest band.

The reply to a create carries estimated_output_tokens, which their API has no field for: a job that bills on settlement and quotes nothing at submit leaves you no way to know what you have committed to until it is spent. Their SDKs ignore the extra field.

The rates are per model and per band.

Errors

In their envelope — {"error": {"message", "type", "code", "param"}} — so a client that already handles errors from their chat or images APIs handles these without a branch. The error table lists every code this gateway sends and whether retrying helps.

A supplier’s own error text is never forwarded. It names them, and on these models it has been observed saying things that are not true of this gateway.