feat(deapi): add audio, video and image-editing models#2690
Open
adampachowicz wants to merge 6 commits into
Open
feat(deapi): add audio, video and image-editing models#2690adampachowicz wants to merge 6 commits into
adampachowicz wants to merge 6 commits into
Conversation
…ield, underscored numbers
- Rename all model files to match exact deAPI native slugs so consumers (OpenCode, Vercel AI SDK) send the correct model identifier to https://oai.deapi.ai/v1 (model id is auto-derived from filename): bge-m3-fp16 -> Bge_M3_FP16 flux1schnell -> Flux1schnell flux2klein4b -> Flux_2_Klein_4B_BF16 z-image-turbo -> ZImageTurbo_INT8 z-anime -> ZAnimeDistill_8Step_INT8 - Add "z-image" to packages/core/src/family.ts enum so Z-Image models can be properly classified. - Correct Z-Image release dates: ZImageTurbo_INT8: 2025-03-15 -> 2025-11-26 (Tongyi Lab) ZAnimeDistill_8Step_INT8: 2025-03-15 -> 2025-12-28
Reviewer correctly flagged that the previous logo.svg was not the deAPI brand mark. The chip glyph below is taken from the deAPI brand system (pixel-art frame with center slash, amber #FFBA00 in product contexts; here exported as a flat icon-only path with currentColor so models.dev can theme it light/dark). - Path data sourced from the official deAPI marketing site (resources/v2/assets/logo.svg, chip-glyph subpath). - Centered inside viewBox="0 0 40 40" via translate(5.4525, 4) so the 29.095x32 chip art is padded evenly (~5.45px / 4px). - Single currentColor fill, no embedded color tokens, no defs. Apologies to the maintainer — that was a sourcing mistake on our end, not a misrepresentation of the provider.
- add packages/core/script/generate-deapi.ts (deapi:generate) that reconciles local model TOMLs against the live deAPI /v1/models catalog; scaffolds stubs for new models and warns on files the API no longer serves - deAPI's OpenAI-compatible endpoint exposes only model IDs (no pricing, context or modalities), so per-model metadata stays hand-curated - remove ZAnimeDistill_8Step_INT8: not present in the live deAPI catalog Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the remaining deAPI gateway catalog (verified live against oai.deapi.ai/v1/models), beyond the embeddings/image set in the provider PR: - TTS (text->audio): Kokoro, Chatterbox, Qwen3-TTS Custom Voice - transcription (audio->text): Whisper Large v3 - video (text->video): LTX-Video 13B, LTX-2 19B, LTX-2 22B - image editing (text+image->image): Qwen-Image-Edit Plus Cost is omitted (the OpenAI-compatible endpoint exposes only model IDs), matching the existing image-model entries and the groq/whisper precedent. Co-Authored-By: Claude Opus 4.8 (1M context) <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.
Adds the remaining deAPI model catalog (audio, video and image-editing models) on top of the initial provider registration in #2604.
Stacked on #2604 — this branch is based on
add-deapi-provider-refresh, so the diff currently includes that PR'sprovider.toml/logo as well. Once #2604 merges, this diff reduces to just the 8 new model files below.New models (8)
All entries are open-weight models served on the deAPI worker network. Metadata follows the precedents already in the catalog for non-text modalities (e.g.
groq/whisper-large-v3,google/gemini-2.5-flash-preview-tts,digitalocean/wan2-2-t2v-a14b).Validation
bun run validate→ passes (all 12 deAPI models valid)bun run deapi:generate --dry-run→ exact parity with the liveoai.deapi.ai/v1/modelsgateway (12 found, 12 existing files, 0 to create, 0 orphaned)Operator: CoinAxe Ltd (Malta).