WaveSpeed
3 model routes · 3 endpoint families
Endpoints
/api/v1/images/tools/face-swap/api/v1/videos/tools/bg-remover/api/v1/videos/tools/upscaleExplore 28 live image, video, audio, LLM, and AI tool APIs from one developer marketplace. Compare endpoints, model costs, task behavior, and integration paths before you ship.
curl --request POST \
--url https://apiin.one/api/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gemini",
"messages": [
{
"role": "user",
"content": "Compare Kling 3.0 and Wan 2.6 for product video generation."
}
]
}'Route supported providers without exposing provider credentials in your application.
Use a catalog of routed model APIs with consistent request and task semantics.
Model cards expose approximate per-call credit cost and generation behavior for live routes.
OpenAI-compatible chat examples and documented category endpoints make integrations faster.
Model marketplace
Search by model, provider, endpoint, use case, or tag. Each route links to a dedicated detail page with parameters, examples, and cost notes.
Google - Image API
Google's Imagen 4 — photorealistic image generation with exceptional detail and prompt adherence.
/api/v1/images/generationsWebhook
Kuaishou - Video API
State-of-the-art AI video generation with 4K quality support. Text-to-video and image-to-video capabilities.
/api/v1/videos/generationsWebhookOpenAI - Image API
OpenAI's GPT Image 1.5 — multimodal image generation and editing with text rendering capabilities.
/api/v1/images/generationsWebhook
xAI - Image API
xAI's Grok Imagine — powerful AI image generation and upscaling from the creators of Grok. Fast, high-quality, and unrestricted.
/api/v1/images/generationsWebhookByteDance / KIE - Image API
Seedream 4.5 — ByteDance's cutting-edge image generation model. Supports text-to-image and image editing with basic/high quality modes.
/api/v1/images/generationsWebhookBlack Forest Labs - Image API
High-quality AI image generation with excellent prompt following and photorealistic output.
/api/v1/images/generationsWebhookSuno AI - Music API
Full-featured AI music generation platform. Supports text-to-music, extend tracks, upload audio covers, generate cover images, and timestamped lyrics. 8 API endpoints.
/api/v1/audio/musicWebhookGoogle - LLM API
Google's most capable AI model for text generation, reasoning, and conversation.
/api/v1/chat/completionsPollingMiniMax - Video API
High-quality AI video generation by MiniMax. Supports image-to-video with standard and pro quality modes, cinematic motion quality.
/api/v1/videos/generationsWebhookCompare real callable models for the current filter by endpoint, I/O, task mode, backend node, and cost.
| Model | Provider | Endpoint | Input / Output | Mode | Node | Cost | Docs |
|---|---|---|---|---|---|---|---|
| imagen-4 Image API | POST /api/v1/images/generations | text -> image | Webhook | node47 | $0.08 | Open | |
| kling-3 Video API | Kuaishou | POST /api/v1/videos/generations | text + image -> video | Webhook | node75 | $3.00 | Open |
| gpt-image-1.5-official Image API | OpenAI | POST /api/v1/images/generations | text + image -> image | Webhook | node42 | $0.10 | Open |
| grok-imagine Image API | xAI | POST /api/v1/images/generations | text -> image | Webhook | node31 | $0.05 | Open |
| seedream-4-5 Image API | ByteDance / KIE | POST /api/v1/images/generations | text + image -> image | Webhook | node30 | $0.12 | Open |
| flux-2 Image API | Black Forest Labs | POST /api/v1/images/generations | text + image -> image | Webhook | node41 | $0.05 | Open |
| suno Music API | Suno AI | POST /api/v1/audio/music | text -> audio | Webhook | node7 | $0.10 | Open |
| gemini LLM API | POST /api/v1/chat/completions | text -> text | Polling | node62 | $0.05 | Open | |
| hailuo-2-3 Video API | MiniMax | POST /api/v1/videos/generations | image -> video | Webhook | node51 | $0.30 | Open |
| wan-2-6 Video API | Alibaba | POST /api/v1/videos/generations | text + image + video -> video | Webhook | node35 | $0.80 | Open |
| vidu-q3 Video API | Shengshu Technology | POST /api/v1/videos/generations | text + image -> video | Polling | node66 | $3.00 | Open |
| pixverse-5-6 Video API | PixVerse | POST /api/v1/videos/generations | text + image -> video | Polling | node65 | $0.90 | Open |
| elevenlabs-v3 Speech API | ElevenLabs | POST /api/v1/audio/speech | text -> audio | Webhook | node58 | $0.01 | Open |
| bg-remover Tool API | API in One | POST /api/v1/images/tools/remove-bg | image -> image | Polling | node19 | $0.01 | Open |
| image-upscale Tool API | KIE | POST /api/v1/images/tools/upscale | image -> image | Webhook | node32 | $0.01 | Open |
| face-swap Tool API | WaveSpeed | POST /api/v1/images/tools/face-swap | image -> image | Polling | node33 | $0.04 | Open |
| cogview-4 Image API | Zhipu AI / WaveSpeed | POST /api/v1/images/generations | text -> image | Polling | node48 | $0.04 | Open |
| kling-image-o1 Image API | Kuaishou / WaveSpeed | POST /api/v1/images/generations | text + image -> image | Polling | node49 | $0.06 | Open |
| ideogram-v3 Image API | Ideogram | POST /api/v1/images/generations | text + image -> image | Polling | node63 | $0.08 | Open |
| recraft-v4 Image API | Recraft | POST /api/v1/images/generations | text -> image | Polling | node78 | $0.10 | Open |
| video-bg-remover Tool API | WaveSpeed | POST /api/v1/videos/tools/bg-remover | video -> video | Polling | node53 | $0.10 | Open |
| ideogram-v4 Image API | Ideogram | POST /api/v1/images/generations | text -> image | Polling | node63 | $0.12 | Open |
| grok-video Video API | xAI | POST /api/v1/videos/generations | text + image -> video | Webhook | node31 | $0.24 | Open |
| ltx-2 Video API | LightTricks / WaveSpeed | POST /api/v1/videos/generations | text + image + video + audio -> video | Polling | node50 | $0.24 | Open |
Provider coverage
Each provider card is generated from the live catalog and shows routed models, endpoint families, and approximate usage cost.
3 model routes · 3 endpoint families
Endpoints
/api/v1/images/tools/face-swap/api/v1/videos/tools/bg-remover/api/v1/videos/tools/upscale2 model routes · 2 endpoint families
Endpoints
/api/v1/images/generations/api/v1/chat/completions2 model routes · 2 endpoint families
Endpoints
/api/v1/videos/generations/api/v1/audio/music2 model routes · 2 endpoint families
Endpoints
/api/v1/images/generations/api/v1/videos/generations2 model routes · 1 endpoint families
Endpoints
/api/v1/images/generations1 model routes · 8 endpoint families
Endpoints
/api/v1/audio/music/api/v1/audio/music/extend/api/v1/audio/music/feed/api/v1/audio/music/cover/generate1 model routes · 1 endpoint families
Endpoints
/api/v1/videos/generations1 model routes · 1 endpoint families
Endpoints
/api/v1/images/tools/remove-bg1 model routes · 1 endpoint families
Endpoints
/api/v1/images/generationsAPI Surface
Map each real server route to its model family, routed model count, sync/async behavior, and docs entry.
/api/v1/images/generationsCreate image generation and edit tasks through the live image model route.
Create image generation and edit tasks through the live image model route.
/api/v1/videos/generationsCreate async text-to-video, image-to-video, and model-specific video tasks.
Create async text-to-video, image-to-video, and model-specific video tasks.
/api/v1/chat/completionsCall the OpenAI-compatible chat completion route with API in One model slugs.
Call the OpenAI-compatible chat completion route with API in One model slugs.
/api/v1/audio/musicGenerate original music tracks with Suno-compatible request parameters.
Generate original music tracks with Suno-compatible request parameters.
/api/v1/audio/music/extendExtend a completed music task with new lyrics, style, or continuation settings.
Extend a completed music task with new lyrics, style, or continuation settings.
/api/v1/audio/music/feedPoll a Suno music task and retrieve generated track results.
Poll a Suno music task and retrieve generated track results.
/api/v1/audio/music/cover/generateCreate cover artwork for generated or uploaded music workflows.
Create cover artwork for generated or uploaded music workflows.
/api/v1/audio/music/cover/statusCheck the status of a music cover artwork generation task.
Check the status of a music cover artwork generation task.
/api/v1/audio/music/upload-cover/generateUpload an audio source and create an AI cover generation task.
Upload an audio source and create an AI cover generation task.
/api/v1/audio/music/upload-cover/statusCheck uploaded audio cover generation status and outputs.
Check uploaded audio cover generation status and outputs.
/api/v1/audio/music/timestamped-lyricsGenerate or retrieve word-level timestamped lyrics for player UIs.
Generate or retrieve word-level timestamped lyrics for player UIs.
/api/v1/audio/speechCreate text-to-speech and multi-speaker audio outputs.
Create text-to-speech and multi-speaker audio outputs.
/api/v1/tasks/{task_id}Check async generation status and retrieve completed media or tool results.
Check async generation status and retrieve completed media or tool results.
/api/v1/images/tools/remove-bgRemove the background from an input image through the image tool route.
Remove the background from an input image through the image tool route.
/api/v1/images/tools/face-swapSwap a source face into a target image using the live face-swap route.
Swap a source face into a target image using the live face-swap route.
/api/v1/images/tools/upscaleUpscale an input image through the implemented image upscale route.
Upscale an input image through the implemented image upscale route.
/api/v1/videos/tools/bg-removerRemove or replace video backgrounds with the implemented video tool route.
Remove or replace video backgrounds with the implemented video tool route.
/api/v1/videos/tools/upscaleUpscale video resolution through the implemented video upscale route.
Upscale video resolution through the implemented video upscale route.
Endpoint families
Create image generation and edit tasks through the live image model route.
/api/v1/images/generationsCreate async text-to-video, image-to-video, and model-specific video tasks.
/api/v1/videos/generationsCall the OpenAI-compatible chat completion route with API in One model slugs.
/api/v1/chat/completionsGenerate original music tracks with Suno-compatible request parameters.
/api/v1/audio/musicExtend a completed music task with new lyrics, style, or continuation settings.
/api/v1/audio/music/extendPoll a Suno music task and retrieve generated track results.
/api/v1/audio/music/feedCreate cover artwork for generated or uploaded music workflows.
/api/v1/audio/music/cover/generateCheck the status of a music cover artwork generation task.
/api/v1/audio/music/cover/statusUpload an audio source and create an AI cover generation task.
/api/v1/audio/music/upload-cover/generateCheck uploaded audio cover generation status and outputs.
/api/v1/audio/music/upload-cover/statusGenerate or retrieve word-level timestamped lyrics for player UIs.
/api/v1/audio/music/timestamped-lyricsCreate text-to-speech and multi-speaker audio outputs.
/api/v1/audio/speechCheck async generation status and retrieve completed media or tool results.
/api/v1/tasks/{task_id}Remove the background from an input image through the image tool route.
/api/v1/images/tools/remove-bgSwap a source face into a target image using the live face-swap route.
/api/v1/images/tools/face-swapUpscale an input image through the implemented image upscale route.
/api/v1/images/tools/upscaleRemove or replace video backgrounds with the implemented video tool route.
/api/v1/videos/tools/bg-removerUpscale video resolution through the implemented video upscale route.
/api/v1/videos/tools/upscaleProduction workflow
The hub is built around stable developer primitives: API keys, model slugs, category endpoints, task IDs, status polling, and transparent credit usage.
Use the hub to pick a category endpoint and model slug. Switch providers by changing the model value.
Async jobs return a task ID. Poll status or configure a webhook when the selected model supports it.
Agent-ready docs
Paste this prompt into Codex, Cursor, Claude, or another coding agent so it can read the API in One docs index and answer route-specific integration questions.
Read this API in One documentation index and answer my question based on it:
https://apiin.one/docs/llms.txt
About API in One:
Unified AI API gateway with OpenAI-compatible chat completions and REST async routes for image, video, music, speech, and AI tools. It uses one API key, one balance, transparent model costs, task polling, webhook-aware routes, and model detail pages with request examples.
My question:
Which API route and model slug should I use for my product workflow?The API Hub is a browsable marketplace for API in One model routes. It groups image, video, audio, LLM, speech, and tool APIs into one integration surface.
No. API in One centralizes authentication and billing so your application can call supported model routes with one API key.
Chat completions are OpenAI-compatible. Async media, speech, music, and tool routes use documented REST payloads with task IDs and status polling.
Model cards show approximate per-call costs. The model cost reference page provides a broader table for image and video routes.
Many async routes support webhooks. Model detail pages and docs show whether the selected route supports webhook callbacks or polling only.