Models

The page contains a single, canonical reference for what models are available right now, how to choose the right one, and how to address models in API calls.

deAPI gives you a unified API across multiple open-source models running on a decentralized GPU cloud. Models evolve frequently; always rely on the live list (endpoint at the bottom) for the current availability and IDs.

---

How model selection works

• Every task requires a model parameter. Example: model: "Flux1schnell" for Text-to-Image or model: "WhisperLargeV3" for speech/video transcription.

• Display names vs. API IDs. In tables and UI we show human-friendly names (e.g., “FLUX.1-schnell”). The API accepts stable IDs (lowercase, hyphen/period separated). Use the Models endpoint to fetch the exact id strings.

• Quality ↔ Speed trade-off. Larger models often yield higher quality but cost more and take longer. Use our Price Calculator on the homepage to estimate cost before running large jobs.

• Versioning & lifecycle. Models may be updated, superseded, or deprecated. Your application should resolve the model ID at runtime (from the live list) or pin to a specific version string if reproducibility is critical.

• Safety & acceptable use. Follow the Terms of Service. Some content types may be blocked or filtered. See the Safety section in each task’s docs.

---

Supported tasks & models (curated)

The table below lists the core, production-ready models available today. For the authoritative list (including experimental or newly added ones), use the Models endpoint.

Service (Task)	Short Summary	What it’s for	Display Name	API Model Slug	Task key(s)
Text-to-Image	Generate images from text	Concept art, prototyping, creative exploration	FLUX.1-schnell Z-Image-Turbo INT8	Flux1schnell ZImageTurbo_INT8	txt2img
Text-to-Speech	Turn text into natural voice	Narration, accessibility, product voices in multiple languages and tones	Kokoro-82M	Kokoro	txt2audio
Video-to-Text	Transcribe video into text	Subtitles, captions, indexing, SEO, datasets (with optional timestamps)	Whisper large-v3	WhisperLargeV3	video2txt
Image/Text-to-Video	Generate lishort AI videos	Cinematic motion, transitions, stylization	LTX-Video-0.9.8 13B	Ltxv_13B_0_9_8_Distilled_FP8	img2video txt2video
Image-to-Text	Extract meaning from images	Descriptions, OCR, accessibility, moderation	Nanonets_Ocr_S_F16	Nanonets-Ocr-S-F16	img2txt
Audio-to-Text	Convert audio into text	Subtitles, notes, search, accessibility (multi-language)	Whisper large-v3	WhisperLargeV3	video2txt
Text-to-Embedding	Create vector embeddings	Search, RAG, semantic similarity, clustering	BGE M3	Bge_M3_FP16	txt2embedding
Image-to-Image	Transform existing images	Style transfer, edits, in/outpainting	QwenImageEdit-Plus (NF4)	QwenImageEdit_Plus_NF4	img2img

Note: Display names and example IDs above are provided for clarity; always fetch the live model list for the exact id strings currently enabled on the network.

---

Picking the right model

• Image Generation (Text-to-Image): Start with Flux1schnell or ZImageTurbo_INT8 for fast iteration. Increase steps/resolution for quality; control style via prompt and (optionally) LoRAs.

• Speech Generation (TTS): Kokoro offers natural prosody across multiple languages/voices. Choose voices/language in the payload; test speed vs. quality for your use case.

• Text Transcription (Video/Audio-to-Text): WhisperLargeV3 is a strong general-purpose baseline with robust multilingual support. For long videos, enable timestamps and chunking.

• Text Recognition (Image-to-Text): Nanonets-Ocr-S-F16 targets clear captions and text extraction. For complex layouts, consider multiple passes or post-processing.

• Video Generation (Image-to-Video / Text-to-Video): Ltxv_13B_0_9_8_Distilled_FP8 is suited for short clips and stylized motion. Start with low duration/frames to validate aesthetics, then scale up.

• Embedding (Text-to-Embedding): Bge_M3_FP16 provides dense vector embeddings for semantic search, clustering, and retrieval-augmented generation (RAG). Use for similarity queries or knowledge base indexing.

• Image Transformation (Image-to-Image):

  For edits and style transfer, start with QwenImageEdit_Plus_NF4. Use fewer steps for quick drafts and increase steps for higher fidelity; combine with masks or control prompts for targeted changes.

For a deeper discussion of strengths/limits and typical parameter sets per task, see Model Selection.

---

API usage examples

1) List models (fetch IDs at runtime)

curl -X GET "https://api.deapi.ai/api/v1/client/models" \
  -H "Authorization: Bearer $DEAPI_API_KEY"

2) Use a model in Text-to-Image

curl -X POST "https://api.deapi.ai/api/v1/client/txt2img" \
  -H "Authorization: Bearer $DEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "isometric cozy cabin at dusk, soft rim light, artstation trending",
    "model": "Flux1schnell",
    "width": 768,
    "height": 768,
    "steps": 25,
    "guidance": 3.5,
    "seed": 12345
  }'

3) Use a model in Video-to-Text (YouTube)

curl -X POST "https://api.deapi.ai/api/v1/client/vid2txt" \
  -H "Authorization: Bearer $DEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "youtube_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
    "include_ts": true,
    "model": "WhisperLargeV3"
  }'

Jobs return a request_id. Poll results with GET /api/v1/client/request-status/{request_id}.

---

Best practices

• Resolve the model list dynamically. Don’t hardcode IDs—fetch once at startup or periodically.

• Pin versions for reproducibility. If you need bit-for-bit repeats (e.g., in T2I), pin model version + set seed.

• Budget before scaling. Larger models and higher resolution/steps cost more—use the calculator on the homepage.

• Handle deprecation. Implement a fallback path if a model becomes unavailable (e.g., switch to a recommended successor).

---

Related docs

• Model Selection: how to choose the best model per task and budget.

• Endpoints: Text-to-Image, Text-to-Speech, Image-to-Text (OCR), Image-to-Image, Video-to-Text, Image-to-Video, Text-to-Embedding, Get Results, Check Balance, Model Selection.

---

Live models (API)

Use the endpoint below to retrieve the current, authoritative list of models (with id strings to use in requests):

GET https://api.deapi.ai/api/v1/client/models

(The response includes stable id values to pass as the model parameter in any task endpoint.)