[Inference Providers] deepinfra: add text-to-video support - #2398
Draft
ovuruska wants to merge 1 commit into
Draft
[Inference Providers] deepinfra: add text-to-video support#2398ovuruska wants to merge 1 commit into
ovuruska wants to merge 1 commit into
Conversation
Add DeepInfraTextToVideoTask for DeepInfra's asynchronous video generation:
POST v1/openai/videos submits the job, then getResponse polls
v1/openai/videos/{id} until the job succeeds or fails and returns the resulting
video as a Blob. Mirrors the novita text-to-video poll pattern (base URL derived
from the request URL, router-aware). prompt/model applied after caller params.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds
DeepInfraTextToVideoTaskso thedeepinfraprovider supportstext-to-video.DeepInfra's video generation is asynchronous (submit → poll → fetch), so this follows the
novitatext-to-video pattern rather than a thin forwarder:makeRoute:v1/openai/videos(POST submits the job).preparePayload: forwardsprompt; appliesprompt/modelafter caller parameters.getResponse: reads the jobid, pollsv1/openai/videos/{id}(router-aware base URL) untilstatusissucceeded/failed, then fetchesdata[0].urland returns aBlob. Throws typed errors on failure/malformed output.Wired in
getProviderHelper.tsunderdeepinfra. Existing tasks untouched.Test
Added a
textToVideointegration case to the DeepInfra suite (same skip-gated pattern as the other deepinfra tasks).🤖 Generated with Claude Code