# VidLab API docs

> One API key for the top image, video and audio models. Each call goes to the best available route at the lowest price, billed from a prepaid balance, and you pay only for generations that succeed.

Base URL: https://vidlab.ai/v1. Every model runs on POST /v1/generations with an API key (Authorization: Bearer). Every page here is Markdown: add .md to its address.

## Quickstart

- [Overview](https://docs.vidlab.ai/quickstart.md): One key, one request shape, every model: the base URL, auth and every endpoint on one page.
- [Authentication](https://docs.vidlab.ai/authentication.md): API keys, how to send them and where to keep them.
- [Submit a generation](https://docs.vidlab.ai/submit-a-generation.md): POST /v1/generations with max_cost_usd and an Idempotency-Key: submit, poll and download in cURL, Python and JavaScript.
- [Price it first](https://docs.vidlab.ai/price-it-first.md): POST /v1/generations/quote prices the exact request for free, nothing held.
- [Get the result](https://docs.vidlab.ai/get-the-result.md): Poll a generation, download the file with your key, and list your generations.

## Reference

- [Input fields](https://docs.vidlab.ai/input-fields.md): Every input field, limits, bad-input answers, length from a file and an example for each kind of model.
- [Generation object](https://docs.vidlab.ai/generation-object.md): Every field of a generation.
- [Statuses](https://docs.vidlab.ai/statuses.md): queued, running, succeeded and failed, and what each means for your money.
- [Billing](https://docs.vidlab.ai/billing.md): Prepaid credit, the reservation, pay only for success, reference-video billing, top-ups, auto-reload and refunds.
- [Balance](https://docs.vidlab.ai/balance.md): GET /v1/balance: what your balance can spend now.
- [Uploads](https://docs.vidlab.ai/uploads.md): POST /v1/uploads: send a file from your machine, accepted types and sizes, and the other ways to send a file.
- [Why a generation failed](https://docs.vidlab.ai/why-a-generation-failed.md): The error object of a failed generation and every failure code. A failed generation is never charged.
- [Errors](https://docs.vidlab.ai/errors.md): The error envelope, every request error code and how to fix each.
- [Model list](https://docs.vidlab.ai/model-list.md): GET /v1/models: every model, its options, units, priced variants and status.

## Guides

- [Rate limits](https://docs.vidlab.ai/rate-limits.md): Request limits, what does not count, Retry-After and safe retries with Idempotency-Key.
- [Formats](https://docs.vidlab.ai/formats.md): Run our ad formats end to end: GET /v1/formats, start a run, answer its questions, poll for the finished video.
- [Viral videos](https://docs.vidlab.ai/viral-videos.md): Search the viral video library over MCP or REST: the trending feed, filtered searches, one video in full, products and creators.

## For agents

- [MCP](https://docs.vidlab.ai/mcp.md): Connect VidLab to Claude Code, Cursor, Codex, ChatGPT and Claude desktop.
- [Agent skill](https://docs.vidlab.ai/agent-skill.md): A SKILL.md that teaches your agent to call the VidLab API.
- [llms.txt](https://docs.vidlab.ai/llms-txt.md): Machine-readable docs for coding agents.

## Video models

- [Seedance 2.5](https://docs.vidlab.ai/models/seedance-2.5.md): `seedance-2.5` by ByteDance. Text to video, Image to video, Reference to video, Edit video. from $0.06 / second.
- [Kling 4.0](https://docs.vidlab.ai/models/kling-4.0.md): `kling-4.0` by Kuaishou. Text to video, Image to video, Reference to video, Edit video. from $0.11 / second.
- [MiniMax H3 UGC](https://docs.vidlab.ai/models/minimax-h3-ugc.md): `minimax-h3-ugc` by MiniMax. Text to video, Image to video, Reference to video. from $0.04 / second.
- [Flux 3 Upscale](https://docs.vidlab.ai/models/flux-3-upscale.md): `flux-3-upscale` by Black Forest Labs. Upscale. from $0.11 / second.
- [Wan 3.0](https://docs.vidlab.ai/models/wan-3.0.md): `wan-3.0` by Alibaba. Text to video, Image to video, Reference to video. from $0.04 / second.
- [Wan 3.0 Prime](https://docs.vidlab.ai/models/wan-3.0-prime.md): `wan-3.0-prime` by Alibaba. Text to video, Image to video, Reference to video. from $0.07 / second.
- [Veo 3.1 Fast](https://docs.vidlab.ai/models/veo-3.1-fast.md): `veo-3.1-fast` by Google. Text to video, Image to video. from $0.08 / second.
- [Veo 3.1](https://docs.vidlab.ai/models/veo-3.1.md): `veo-3.1` by Google. Text to video, Image to video. from $0.20 / second.
- [Kling 3.0](https://docs.vidlab.ai/models/kling-3.0.md): `kling-3.0` by Kuaishou. Text to video, Image to video. from $0.09 / second.
- [Kling 2.6 Pro](https://docs.vidlab.ai/models/kling-2.6-pro.md): `kling-2.6-pro` by Kuaishou. Text to video, Image to video. from $0.07 / second.
- [Seedance 2.0](https://docs.vidlab.ai/models/seedance-2.0.md): `seedance-2.0` by ByteDance. Text to video, Image to video, Reference to video. from $0.08 / second.
- [Wan 2.6](https://docs.vidlab.ai/models/wan-2.6.md): `wan-2.6` by Alibaba. Text to video, Image to video. from $0.07 / second.
- [Hailuo 2.3](https://docs.vidlab.ai/models/hailuo-2.3.md): `hailuo-2.3` by MiniMax. Text to video, Image to video. from $0.06 / second.
- [HappyHorse 1.0](https://docs.vidlab.ai/models/happyhorse-1.0.md): `happyhorse-1.0` by Alibaba. Text to video, Image to video, Reference to video, Edit video. from $0.17 / second.
- [HappyHorse 1.1](https://docs.vidlab.ai/models/happyhorse-1.1.md): `happyhorse-1.1` by Alibaba. Text to video, Image to video, Reference to video. from $0.15 / second.
- [Wan 2.2 Animate](https://docs.vidlab.ai/models/wan-2.2-animate.md): `wan-2.2-animate` by Alibaba. Animate. $0.08 / second.
- [Wan 2.2 Speech To Video](https://docs.vidlab.ai/models/wan-2.2-speech-to-video.md): `wan-2.2-speech-to-video` by Alibaba. Lip sync. from $0.08 / second.
- [Wan 2.2 Turbo](https://docs.vidlab.ai/models/wan-2.2-turbo.md): `wan-2.2-turbo` by Alibaba. Text to video, Image to video. from $0.05 / second.
- [Wan 2.5](https://docs.vidlab.ai/models/wan-2.5.md): `wan-2.5` by Alibaba. Text to video, Image to video. from $0.05 / second.
- [Wan 2.6 Flash](https://docs.vidlab.ai/models/wan-2.6-flash.md): `wan-2.6-flash` by Alibaba. Image to video, Reference to video, Edit video. from $0.03 / second.
- [Wan 2.6 I2V](https://docs.vidlab.ai/models/wan-2.6-i2v.md): `wan-2.6-i2v` by Alibaba. Text to video, Image to video. from $0.09 / second.
- [Wan 2.6 I2V Flash](https://docs.vidlab.ai/models/wan-2.6-i2v-flash.md): `wan-2.6-i2v-flash` by Alibaba. Image to video. from $0.03 / second.
- [Wan 2.7](https://docs.vidlab.ai/models/wan-2.7.md): `wan-2.7` by Alibaba. Text to video, Image to video, Reference to video, Edit video. from $0.09 / second.
- [Wan 2.7 R2V](https://docs.vidlab.ai/models/wan-2.7-r2v.md): `wan-2.7-r2v` by Alibaba. Image to video, Reference to video. from $0.09 / second.
- [Wan 2.7 Video Edit](https://docs.vidlab.ai/models/wan-2.7-videoedit.md): `wan-2.7-videoedit` by Alibaba. Edit video. from $0.09 / second.
- [Flux 3 Video](https://docs.vidlab.ai/models/flux-3-video.md): `flux-3-video` by Black Forest Labs. Text to video, Image to video, Reference to video, Edit video. from $0.06 / second.
- [ByteDance Lip Sync](https://docs.vidlab.ai/models/bytedance-lipsync.md): `bytedance-lipsync` by ByteDance. Lip sync. $0.05 / second.
- [OmniHuman 1.5](https://docs.vidlab.ai/models/omnihuman-1.5.md): `omnihuman-1.5` by ByteDance. Lip sync. $0.17 / second.
- [Seedance 2.0 Face](https://docs.vidlab.ai/models/seedance-2.0-face.md): `seedance-2.0-face` by ByteDance. Text to video, Image to video, Reference to video. from $0.13 / second.
- [Seedance 2.0 Fast](https://docs.vidlab.ai/models/seedance-2.0-fast.md): `seedance-2.0-fast` by ByteDance. Text to video, Image to video, Reference to video. from $0.05 / second.
- [Seedance 2.0 Fast Face](https://docs.vidlab.ai/models/seedance-2.0-fast-face.md): `seedance-2.0-fast-face` by ByteDance. Text to video, Image to video, Reference to video. from $0.10 / second.
- [Seedance 2.0 Mini](https://docs.vidlab.ai/models/seedance-2.0-mini.md): `seedance-2.0-mini` by ByteDance. Text to video, Image to video, Reference to video. from $0.03 / second.
- [Gemini Omni](https://docs.vidlab.ai/models/gemini-omni.md): `gemini-omni` by Google. Text to video, Image to video. from $0.10 / second.
- [Gemini Omni Flash Preview](https://docs.vidlab.ai/models/gemini-omni-flash-preview.md): `gemini-omni-flash-preview` by Google. Text to video, Image to video, Reference to video. $0.11 / second.
- [Veo 3.1 Lite](https://docs.vidlab.ai/models/veo-3.1-lite.md): `veo-3.1-lite` by Google. Text to video, Image to video, Reference to video. from $0.05 / second.
- [Kling 2.1 Master](https://docs.vidlab.ai/models/kling-2.1-master.md): `kling-2.1-master` by Kuaishou. Text to video, Image to video. $0.20 / second.
- [Kling 2.1 Pro](https://docs.vidlab.ai/models/kling-2.1-pro.md): `kling-2.1-pro` by Kuaishou. Image to video. $0.07 / second.
- [Kling 2.1 Standard](https://docs.vidlab.ai/models/kling-2.1-std.md): `kling-2.1-std` by Kuaishou. Image to video. $0.04 / second.
- [Kling 2.5 Turbo Pro](https://docs.vidlab.ai/models/kling-2.5-turbo-pro.md): `kling-2.5-turbo-pro` by Kuaishou. Text to video, Image to video. $0.06 / second.
- [Kling 2.6 Motion Control](https://docs.vidlab.ai/models/kling-2.6-motion-control.md): `kling-2.6-motion-control` by Kuaishou. Motion control. from $0.07 / second.
- [Kling 2.6 Standard](https://docs.vidlab.ai/models/kling-2.6-std.md): `kling-2.6-std` by Kuaishou. Text to video, Image to video. $0.05 / second.
- [Kling 3.0 Motion Control](https://docs.vidlab.ai/models/kling-3.0-motion-control.md): `kling-3.0-motion-control` by Kuaishou. Motion control. from $0.13 / second.
- [Kling 3.0 Omni](https://docs.vidlab.ai/models/kling-3.0-omni.md): `kling-3.0-omni` by Kuaishou. Text to video, Image to video, Reference to video, Edit video. from $0.09 / second.
- [Kling 3.0 Turbo](https://docs.vidlab.ai/models/kling-3.0-turbo.md): `kling-3.0-turbo` by Kuaishou. Text to video, Image to video. from $0.12 / second.
- [Kling Avatar Pro](https://docs.vidlab.ai/models/kling-avatar-pro.md): `kling-avatar-pro` by Kuaishou. Lip sync. $0.10 / second.
- [Kling Avatar Standard](https://docs.vidlab.ai/models/kling-avatar-std.md): `kling-avatar-std` by Kuaishou. Lip sync. $0.05 / second.
- [Kling O1](https://docs.vidlab.ai/models/kling-o1.md): `kling-o1` by Kuaishou. Text to video, Image to video, Reference to video. from $0.09 / second.
- [InfiniteTalk](https://docs.vidlab.ai/models/infinitalk.md): `infinitalk` by MeiGen. Lip sync. from $0.02 / second.
- [Hailuo 02](https://docs.vidlab.ai/models/hailuo-02.md): `hailuo-02` by MiniMax. Text to video, Image to video. from $0.02 / second.
- [Hailuo 02 Pro](https://docs.vidlab.ai/models/hailuo-02-pro.md): `hailuo-02-pro` by MiniMax. Text to video, Image to video. $0.06 / second.
- [Hailuo 02 Standard](https://docs.vidlab.ai/models/hailuo-02-std.md): `hailuo-02-std` by MiniMax. Text to video, Image to video. from $0.02 / second.
- [Hailuo 2.3 Fast](https://docs.vidlab.ai/models/hailuo-2.3-fast.md): `hailuo-2.3-fast` by MiniMax. Image to video. from $0.04 / second.
- [Hailuo 2.3 Standard](https://docs.vidlab.ai/models/hailuo-2.3-std.md): `hailuo-2.3-std` by MiniMax. Image to video. from $0.04 / second.
- [MiniMax H3](https://docs.vidlab.ai/models/minimax-h3.md): `minimax-h3` by MiniMax. Text to video, Image to video, Reference to video, Edit video. from $0.05 / second.
- [MiniMax H3 Max](https://docs.vidlab.ai/models/minimax-h3-max.md): `minimax-h3-max` by MiniMax. Text to video, Image to video, Reference to video. from $0.05 / second.
- [PixVerse V6](https://docs.vidlab.ai/models/pixverse-v6.md): `pixverse-v6` by PixVerse. Text to video, Image to video. from $0.02 / second.
- [PixVerse V6 Max](https://docs.vidlab.ai/models/pixverse-v6-max.md): `pixverse-v6-max` by PixVerse. Text to video, Image to video. from $0.03 / second.
- [Vidu Q3](https://docs.vidlab.ai/models/vidu-q3.md): `vidu-q3` by Shengshu. Image to video, Reference to video. from $0.05 / second.
- [Vidu Q3 Mix](https://docs.vidlab.ai/models/vidu-q3-mix.md): `vidu-q3-mix` by Shengshu. Image to video, Reference to video. from $0.13 / second.
- [Vidu Q3 Pro](https://docs.vidlab.ai/models/vidu-q3-pro.md): `vidu-q3-pro` by Shengshu. Text to video, Image to video. from $0.07 / second.
- [Vidu Q3 Turbo](https://docs.vidlab.ai/models/vidu-q3-turbo.md): `vidu-q3-turbo` by Shengshu. Text to video, Image to video. from $0.04 / second.
- [Vidu Q4](https://docs.vidlab.ai/models/vidu-q4.md): `vidu-q4` by Shengshu. Image to video, Reference to video. from $0.05 / second.
- [Vidu Q4 Preview](https://docs.vidlab.ai/models/vidu-q4-preview.md): `vidu-q4-preview` by Shengshu. Text to video, Image to video, Reference to video. from $0.06 / second.
- [SkyReels V4 Fast](https://docs.vidlab.ai/models/skyreels-v4-fast.md): `skyreels-v4-fast` by Skywork. Text to video, Image to video. from $0.08 / second.
- [SkyReels V4 Standard](https://docs.vidlab.ai/models/skyreels-v4-std.md): `skyreels-v4-std` by Skywork. Text to video, Image to video. from $0.11 / second.
- [Grok Imagine Video](https://docs.vidlab.ai/models/grok-imagine-video.md): `grok-imagine-video` by xAI. Text to video, Image to video. from $0.02 / second.
- [Grok Imagine Video 1.5](https://docs.vidlab.ai/models/grok-imagine-video-1.5.md): `grok-imagine-video-1.5` by xAI. Text to video, Image to video, Reference to video. from $0.04 / second.
- [Grok Imagine Video 1.5 Preview](https://docs.vidlab.ai/models/grok-imagine-video-1.5-preview.md): `grok-imagine-video-1.5-preview` by xAI. Image to video. from $0.02 / second.
- [OmniHuman 2.0](https://docs.vidlab.ai/models/omnihuman-2.0.md): `omnihuman-2.0` by ByteDance. Lip sync. $0.10 / second.
- [Kling O3 Omni](https://docs.vidlab.ai/models/kling-o3.md): `kling-o3` by Kuaishou. Text to video, Image to video, Reference to video, Edit video. from $0.09 / second.
- [Topaz Video Upscale 4K](https://docs.vidlab.ai/models/topaz-video-upscale.md): `topaz-video-upscale` by Topaz Labs. Upscale. from $0.05 / second.
- [Seedance 1.5 Pro](https://docs.vidlab.ai/models/seedance-1.5-pro.md): `seedance-1.5-pro` by ByteDance. Text to video, Image to video. from $0.03 / second.
- [Seedance 1.0 Pro Fast](https://docs.vidlab.ai/models/seedance-1.0-pro-fast.md): `seedance-1.0-pro-fast` by ByteDance. Text to video, Image to video. from $0.015 / second.
- [Wan 2.6 R2V Flash](https://docs.vidlab.ai/models/wan-2.6-r2v-flash.md): `wan-2.6-r2v-flash` by Alibaba. Image to video, Reference to video. $0.07 / second.
- [HappyHorse 1.0 Video Edit](https://docs.vidlab.ai/models/happyhorse-1.0-edit.md): `happyhorse-1.0-edit` by Alibaba. Edit video. $0.16 / second.
- [HappyHorse 1.1 R2V](https://docs.vidlab.ai/models/happyhorse-1.1-r2v.md): `happyhorse-1.1-r2v` by Alibaba. Image to video, Reference to video. $0.16 / second.

## Image models

- [UGC Real 1](https://docs.vidlab.ai/models/ugc-real-1.md): `ugc-real-1` by VidLab. Text to image. $0.03 / image.
- [Nano Banana Pro](https://docs.vidlab.ai/models/nano-banana-pro.md): `nano-banana-pro` by Google. Text to image, Image to image. from $0.04 / image.
- [Nano Banana 2](https://docs.vidlab.ai/models/nano-banana-2.md): `nano-banana-2` by Google. Text to image, Image to image. from $0.03 / image.
- [GPT Image 2](https://docs.vidlab.ai/models/gpt-image-2.md): `gpt-image-2` by OpenAI. Text to image, Image to image. $0.03 / image.
- [Nano Banana](https://docs.vidlab.ai/models/nano-banana.md): `nano-banana` by Google. Text to image, Image to image. $0.03 / image.
- [GPT Image 1.5](https://docs.vidlab.ai/models/gpt-image-1.5.md): `gpt-image-1.5` by OpenAI. Text to image, Image to image. from $0.02 / image.
- [Seedream 4.5](https://docs.vidlab.ai/models/seedream-4.5.md): `seedream-4.5` by ByteDance. Text to image, Image to image. $0.04 / image.
- [Seedream 5.0 Pro](https://docs.vidlab.ai/models/seedream-5.0-pro.md): `seedream-5.0-pro` by ByteDance. Text to image, Image to image. $0.04 / image.
- [Flux 2 Pro](https://docs.vidlab.ai/models/flux-2-pro.md): `flux-2-pro` by Black Forest Labs. Text to image, Image to image. from $0.03 / image.
- [Midjourney V7](https://docs.vidlab.ai/models/midjourney-v7.md): `midjourney-v7` by Midjourney. Text to image, Image to image. from $0.06 / image.
- [Ideogram V3](https://docs.vidlab.ai/models/ideogram-v3.md): `ideogram-v3` by Ideogram. Text to image, Image to image. from $0.03 / image.
- [Qwen Image](https://docs.vidlab.ai/models/qwen-image.md): `qwen-image` by Alibaba. Text to image, Image to image. $0.03 / image.
- [Qwen Image 2.0](https://docs.vidlab.ai/models/qwen-image-2.0.md): `qwen-image-2.0` by Alibaba. Text to image, Image to image. $0.03 / image.
- [Qwen Image 2.0 Pro](https://docs.vidlab.ai/models/qwen-image-2.0-pro.md): `qwen-image-2.0-pro` by Alibaba. Text to image, Image to image. $0.07 / image.
- [Qwen Image 2.1](https://docs.vidlab.ai/models/qwen-image-2.1.md): `qwen-image-2.1` by Alibaba. Text to image, Image to image. from $0.03 / image.
- [Qwen Image 3.0](https://docs.vidlab.ai/models/qwen-image-3.0.md): `qwen-image-3.0` by Alibaba. Text to image, Image to image. $0.03 / image.
- [Qwen Image 3.0 Pro](https://docs.vidlab.ai/models/qwen-image-3.0-pro.md): `qwen-image-3.0-pro` by Alibaba. Text to image, Image to image. from $0.04 / image.
- [Qwen Image Edit](https://docs.vidlab.ai/models/qwen-image-edit.md): `qwen-image-edit` by Alibaba. Edit image. $0.04 / image.
- [Wan 2.7 Image](https://docs.vidlab.ai/models/wan-2.7-image.md): `wan-2.7-image` by Alibaba. Text to image, Image to image. $0.03 / image.
- [Wan 2.7 Image Pro](https://docs.vidlab.ai/models/wan-2.7-image-pro.md): `wan-2.7-image-pro` by Alibaba. Text to image, Image to image. $0.07 / image.
- [Z Image](https://docs.vidlab.ai/models/z-image.md): `z-image` by Alibaba. Text to image. $0.01 / image.
- [Z Image Turbo](https://docs.vidlab.ai/models/z-image-turbo.md): `z-image-turbo` by Alibaba. Text to image. $0.02 / image.
- [Flux 2 Flex](https://docs.vidlab.ai/models/flux-2-flex.md): `flux-2-flex` by Black Forest Labs. Text to image, Image to image. from $0.05 / image.
- [Flux 2 Max](https://docs.vidlab.ai/models/flux-2-max.md): `flux-2-max` by Black Forest Labs. Text to image, Image to image. from $0.07 / image.
- [Flux 3](https://docs.vidlab.ai/models/flux-3.md): `flux-3` by Black Forest Labs. Text to image, Image to image. from $0.05 / image.
- [Flux 3 Klein](https://docs.vidlab.ai/models/flux-3-klein.md): `flux-3-klein` by Black Forest Labs. Text to image, Image to image. from $0.01 / image.
- [Flux Kontext Max](https://docs.vidlab.ai/models/flux-kontext-max.md): `flux-kontext-max` by Black Forest Labs. Text to image, Image to image. $0.07 / image.
- [Flux Kontext Pro](https://docs.vidlab.ai/models/flux-kontext-pro.md): `flux-kontext-pro` by Black Forest Labs. Text to image, Image to image. $0.04 / image.
- [Seedream 3.0](https://docs.vidlab.ai/models/seedream-3.0.md): `seedream-3.0` by ByteDance. Text to image. $0.03 / image.
- [Seedream 4.0](https://docs.vidlab.ai/models/seedream-4.0.md): `seedream-4.0` by ByteDance. Text to image, Image to image. $0.03 / image.
- [Seedream 5.0 Flash](https://docs.vidlab.ai/models/seedream-5.0-flash.md): `seedream-5.0-flash` by ByteDance. Text to image, Image to image. $0.02 / image.
- [Seedream 5.0 Lite](https://docs.vidlab.ai/models/seedream-5.0-lite.md): `seedream-5.0-lite` by ByteDance. Text to image, Image to image. from $0.03 / image.
- [Imagen 4](https://docs.vidlab.ai/models/imagen-4.md): `imagen-4` by Google. Text to image. $0.05 / image.
- [Imagen 4 Fast](https://docs.vidlab.ai/models/imagen-4-fast.md): `imagen-4-fast` by Google. Text to image. $0.03 / image.
- [Imagen 4 Ultra](https://docs.vidlab.ai/models/imagen-4-ultra.md): `imagen-4-ultra` by Google. Text to image. $0.08 / image.
- [Nano Banana 2 Lite](https://docs.vidlab.ai/models/nano-banana-2-lite.md): `nano-banana-2-lite` by Google. Text to image, Image to image. $0.02 / image.
- [Nano Banana 2.1](https://docs.vidlab.ai/models/nano-banana-2.1.md): `nano-banana-2.1` by Google. Text to image, Image to image. from $0.03 / image.
- [Ideogram Character](https://docs.vidlab.ai/models/ideogram-character.md): `ideogram-character` by Ideogram. Image to image. from $0.08 / image.
- [MAI Image 2.6](https://docs.vidlab.ai/models/mai-image-2.6.md): `mai-image-2.6` by Microsoft. Text to image, Image to image. from $0.04 / image.
- [MAI Image 2.6 Flash](https://docs.vidlab.ai/models/mai-image-2.6-flash.md): `mai-image-2.6-flash` by Microsoft. Text to image, Image to image. from $0.02 / image.
- [DALL·E 3](https://docs.vidlab.ai/models/dall-e-3.md): `dall-e-3` by OpenAI. Text to image. $0.04 / image.
- [GPT 4o Image](https://docs.vidlab.ai/models/gpt-4o-image.md): `gpt-4o-image` by OpenAI. Text to image, Image to image. $0.04 / image.
- [GPT Image 1](https://docs.vidlab.ai/models/gpt-image-1.md): `gpt-image-1` by OpenAI. Text to image, Image to image. from $0.02 / image.
- [GPT Image 2.5 Flare](https://docs.vidlab.ai/models/gpt-image-2.5-flare.md): `gpt-image-2.5-flare` by OpenAI. Text to image, Image to image. from $0.02 / image.
- [GPT Image 2.5 Sunburst](https://docs.vidlab.ai/models/gpt-image-2.5-sunburst.md): `gpt-image-2.5-sunburst` by OpenAI. Text to image, Image to image. from $0.02 / image.
- [Recraft Crisp Upscale](https://docs.vidlab.ai/models/recraft-crisp-upscale.md): `recraft-crisp-upscale` by Recraft. Upscale. $0.01 / image.
- [Hunyuan Image 3.5 Preview](https://docs.vidlab.ai/models/hunyuan-image-3.5-preview.md): `hunyuan-image-3.5-preview` by Tencent. Text to image, Image to image. from $0.03 / image.
- [Grok Imagine Image](https://docs.vidlab.ai/models/grok-imagine-image.md): `grok-imagine-image` by xAI. Text to image, Image to image. $0.02 / image.
- [Grok Imagine Image 2.0](https://docs.vidlab.ai/models/grok-imagine-image-2.0.md): `grok-imagine-image-2.0` by xAI. Text to image, Image to image. $0.02 / image.
- [Grok Imagine Image 2.0 Quality](https://docs.vidlab.ai/models/grok-imagine-image-2.0-quality.md): `grok-imagine-image-2.0-quality` by xAI. Text to image, Image to image. from $0.05 / image.
- [Topaz Image Upscale 4K](https://docs.vidlab.ai/models/topaz-image-upscale.md): `topaz-image-upscale` by Topaz Labs. Upscale. $0.06 / image.
- [Recraft Crisp Remove BG](https://docs.vidlab.ai/models/recraft-remove-bg.md): `recraft-remove-bg` by Recraft. Remove background. $0.01 / image.
- [Grok Imagine 1.5 Edit](https://docs.vidlab.ai/models/grok-imagine-1.5-edit.md): `grok-imagine-1.5-edit` by xAI. Edit image. $0.02 / image.
- [Flux 2 Klein 4B](https://docs.vidlab.ai/models/flux-2-klein-4b.md): `flux-2-klein-4b` by Black Forest Labs. Text to image, Image to image. $0.015 / image.
- [Flux 2 Klein 9B](https://docs.vidlab.ai/models/flux-2-klein-9b.md): `flux-2-klein-9b` by Black Forest Labs. Text to image, Image to image. $0.015 / image.

## Audio models

- [Suno V6](https://docs.vidlab.ai/models/suno-v6.md): `suno-v6` by Suno. Music. $0.08 / run.
- [ElevenLabs Dialogue v3](https://docs.vidlab.ai/models/elevenlabs-dialogue-v3.md): `elevenlabs-dialogue-v3` by ElevenLabs. Text to speech. $0.09 / 1,000 characters.
- [ElevenLabs Turbo v2.5 TTS](https://docs.vidlab.ai/models/elevenlabs-tts.md): `elevenlabs-tts` by ElevenLabs. Text to speech. from $0.04 / 1,000 characters.
- [Gemini 3.8 Flash Native Speech](https://docs.vidlab.ai/models/gemini-3.8-flash-tts.md): `gemini-3.8-flash-tts` by Google. Text to speech. $0.03 / minute.
- [GPT-4o Mini Steerable TTS](https://docs.vidlab.ai/models/gpt-4o-mini-tts.md): `gpt-4o-mini-tts` by OpenAI. Text to speech. $0.02 / 1,000 characters.
- [FlowMusic Commercial BGM](https://docs.vidlab.ai/models/flowmusic.md): `flowmusic` by FlowMusic. Music. $0.08 / run.

## Machine-readable

- [OpenAPI 3.1](https://docs.vidlab.ai/openapi.json): the /v1 API as JSON.
- [llms-full.txt](https://docs.vidlab.ai/llms-full.txt): every guide and every model as one Markdown file.