# HotAPI

HotAPI is a unified gateway for uncensored AI models — image, video, voice, and chat generation behind one API key, with pay-as-you-go credits and public docs.

This file is the AI-oriented index for integrating the HotAPI developer API.

Canonical URL: https://hotapi.ai

## Documentation

- [Get started with HotAPI](https://hotapi.ai/docs/getting-started): Use a coding agent or make the first API request yourself. Both paths end with a complete, production-safe integration.
- [Run and track generation tasks](https://hotapi.ai/docs/guides/async-tasks): Submit, poll, cancel, and recover results from asynchronous image and video tasks.
- [Keep your API key server-side](https://hotapi.ai/docs/guides/authentication): How to send, manage, and rotate HotAPI API keys.
- [Credits and billing](https://hotapi.ai/docs/guides/billing): How the credit balance works — pricing, charges, refunds, top-ups, and tracking usage.
- [Chat completions with an OpenAI-compatible API](https://hotapi.ai/docs/guides/chat-completions): HotAPI is an OpenAI-compatible API. Point the OpenAI SDK or any OpenAI-style client at POST /v1/chat/completions for synchronous and streaming chat, per-token billing, and tool calling.
- [Use the HotAPI CLI](https://hotapi.ai/docs/guides/cli): Install the hotapi command, generate from a terminal or agent, and use its JSON and exit-code contract for reliable automation.
- [Handle API errors](https://hotapi.ai/docs/guides/errors): The error envelope, the error categories, and how to handle each one.
- [Retry safely under rate limits](https://hotapi.ai/docs/guides/rate-limits): The per-organization and per-key request limits, the headers that report them, and how to stay within them.
- [Use local images](https://hotapi.ai/docs/guides/uploads): Pass images to edit, face-swap, and video models — as a public URL, or by uploading a local file.
- [Receive completed tasks](https://hotapi.ai/docs/guides/webhooks): Receive terminal task results without polling — delivery, signing, retries.
- [AI video generation API](https://hotapi.ai/docs/video-generation-api): Generate video with HotAPI's AI video generation API — typed text-to-video, image-to-video, and reference-to-video endpoints on one async task API with polling or webhooks.

## Models

- [Berry 1.0 Pro Spicy / Image to Video](https://hotapi.ai/models/berry-1.0-pro-spicy/image-to-video): Unrestricted high-resolution image-to-video at 1080p, 2K, or 4K, with optional last-frame control.
- [Berry 1.0 Pro Spicy / Reference to Video](https://hotapi.ai/models/berry-1.0-pro-spicy/reference-to-video): Unrestricted high-resolution reference-to-video from up to 10 images, 5 audio, and 5 video URLs, at 1080p–4K.
- [Berry 1.0 Pro Spicy / Text to Video](https://hotapi.ai/models/berry-1.0-pro-spicy/text-to-video): Unrestricted high-resolution text-to-video at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Berry 1.0 Pro Turbo Spicy / Image to Video](https://hotapi.ai/models/berry-1.0-pro-turbo-spicy/image-to-video): Faster unrestricted high-resolution image-to-video at 1080p, 2K, or 4K, with optional end-frame control.
- [Berry 1.0 Pro Turbo Spicy / Reference to Video](https://hotapi.ai/models/berry-1.0-pro-turbo-spicy/reference-to-video): Faster unrestricted reference-to-video from up to 10 images, 5 audio, and 5 video URLs, with 1080p, 2K, or 4K output.
- [Berry 1.0 Pro Turbo Spicy / Text to Video](https://hotapi.ai/models/berry-1.0-pro-turbo-spicy/text-to-video): Speed-oriented unrestricted high-resolution text-to-video at 1080p, 2K, or 4K for 2–30 seconds.
- [Berry 1.0 Spicy / Image to Video](https://hotapi.ai/models/berry-1.0-spicy/image-to-video): Unrestricted image-to-video in 480p–1080p with optional last-frame control, audio, and prompt extension.
- [Berry 1.0 Spicy / Reference to Video](https://hotapi.ai/models/berry-1.0-spicy/reference-to-video): Unrestricted reference-to-video from up to 10 images, 5 audio, and 5 video URLs, in 480p–1080p for 2–30 seconds.
- [Berry 1.0 Spicy / Text to Video](https://hotapi.ai/models/berry-1.0-spicy/text-to-video): Unrestricted text-to-video in 480p–1080p, 2–30 seconds, with generated audio and prompt extension.
- [Berry 1.0 Turbo Spicy / Image to Video](https://hotapi.ai/models/berry-1.0-turbo-spicy/image-to-video): Faster unrestricted image animation in 480p–1080p, with optional last-frame and generated-audio controls.
- [Berry 1.0 Turbo Spicy / Reference to Video](https://hotapi.ai/models/berry-1.0-turbo-spicy/reference-to-video): Faster unrestricted reference-to-video from up to 10 images, 5 audio, and 5 video URLs, in 480p–1080p.
- [Berry 1.0 Turbo Spicy / Text to Video](https://hotapi.ai/models/berry-1.0-turbo-spicy/text-to-video): Speed-oriented unrestricted text-to-video in 480p–1080p, with 2–30 second duration control and generated audio.
- [Face Swap Spicy / Face Swap](https://hotapi.ai/models/face-swap-spicy/face-swap): Uncensored face swapping between a source and target image via a single API call.
- [Head Swap / Head Replacement](https://hotapi.ai/models/head-swap-spicy/head-swap): Replace a whole head from a reference image while retaining the target composition. Flat $0.02 per image.
- [Lime 1.0 / Image to Video](https://hotapi.ai/models/lime-1.0-spicy/image-to-video): Animate one image with included native audio. Choose 5 or 10 seconds at 480p or super-resolved 720p.
- [MiniMax H3 Spicy / Generate Video](https://hotapi.ai/models/minimax-h3-spicy/generate-video): Uncensored video from text, frames, or references, 480p–4k with generated audio, 5–15 seconds.
- [Qwen Image 2.1 Spicy / Text to Image](https://hotapi.ai/models/qwen-image-2.1-spicy/text-to-image): Uncensored text-to-image with optional reference guidance (up to 8 images), built for keeping the same synthetic character consistent across a scene or a series.
- [Qwen Image Edit Spicy / Image Edit](https://hotapi.ai/models/qwen-image-edit-spicy/image-edit): Uncensored image editing with a source image and up to two additional reference images.
- [Qwen 3.8 27B Spicy / Chat Completions](https://hotapi.ai/models/qwen3.8-27b-spicy/chat): Uncensored OpenAI-compatible chat completions — Qwen 3.8 27B, 256K context, sync and SSE streaming.
- [Seedance 2.0 Fast Spicy / Image to Video](https://hotapi.ai/models/seedance-2.0-fast-spicy/image-to-video): The faster, lower-cost uncensored image-to-video tier — animate a first frame (and optional last frame) at 480p/720p with synced audio, no content filter.
- [Seedance 2.0 Fast Spicy / Reference to Video](https://hotapi.ai/models/seedance-2.0-fast-spicy/reference-to-video): The faster, lower-cost uncensored reference-to-video tier — subject/style consistency from 1–9 reference images at 480p/720p with synced audio, no content filter.
- [Seedance 2.0 Fast Spicy / Text to Video](https://hotapi.ai/models/seedance-2.0-fast-spicy/text-to-video): The faster, lower-cost uncensored text-to-video tier at 480p/720p with synced audio and no content filter.
- [Seedance 2.0 Mini Spicy / Image to Video](https://hotapi.ai/models/seedance-2.0-mini-spicy/image-to-video): The lowest-cost uncensored image-to-video tier — animate a first frame (and optional last frame) at 480p/720p with synced audio, no content filter.
- [Seedance 2.0 Mini Spicy / Reference to Video](https://hotapi.ai/models/seedance-2.0-mini-spicy/reference-to-video): The lowest-cost uncensored reference-to-video tier — subject/style consistency from 1–9 reference images at 480p/720p with synced audio, no content filter.
- [Seedance 2.0 Mini Spicy / Text to Video](https://hotapi.ai/models/seedance-2.0-mini-spicy/text-to-video): The lowest-cost uncensored text-to-video tier — 480p at $0.03/sec, 720p at $0.06, synchronized audio, no content filter.
- [Seedance 2.0 Spicy / Image to Video](https://hotapi.ai/models/seedance-2.0-spicy/image-to-video): Uncensored image-to-video generation up to 1080p — animate a first frame (and optional last frame) with synced audio, no content filter.
- [Seedance 2.0 Spicy / Reference to Video](https://hotapi.ai/models/seedance-2.0-spicy/reference-to-video): Uncensored reference-to-video — drive subject, motion, and style from 1–9 reference images plus 1–3 reference videos or audio clips, no content filter.
- [Seedance 2.0 Spicy / Text to Video](https://hotapi.ai/models/seedance-2.0-spicy/text-to-video): Uncensored text-to-video generation up to 1080p with synchronized audio and no content filter.
- [Seedance 2.5 Spicy / Draft to Video](https://hotapi.ai/models/seedance-2.5-spicy/draft-to-video): Finalize a Seedance 2.5 draft preview into the 1080p final video, reusing the draft's composition.
- [Seedance 2.5 Spicy / Image to Video](https://hotapi.ai/models/seedance-2.5-spicy/image-to-video): Animate a first frame, with an optional last frame, into a 4–30 second 480p, 720p, or 1080p video, with an optional 480p draft preview.
- [Seedance 2.5 Spicy / Reference to Video](https://hotapi.ai/models/seedance-2.5-spicy/reference-to-video): Generate video from up to 30 reference images, 10 reference audio URLs, or 10 reference video URLs at 480p, 720p, or 1080p, with MP4 or MOV output and an optional 480p draft.
- [Seedance 2.5 Spicy / Text to Video](https://hotapi.ai/models/seedance-2.5-spicy/text-to-video): Text-to-video generation at 480p, 720p, or 1080p for 4–30 seconds, with selectable aspect ratio, audio, and an optional 480p draft preview.
- [Seedance 2.5 Spicy / Video to Video](https://hotapi.ai/models/seedance-2.5-spicy/video-to-video): Edit one 4–30 second source video with optional image or audio references, MP4 or MOV output, and 480p draft previews.
- [Seedream 5.0 Lite Spicy / Image Edit](https://hotapi.ai/models/seedream-5.0-lite-spicy/image-edit): Uncensored high-resolution image editing and multi-image blending — 1–14 reference images plus a prompt, no content filter, through one API.
- [Seedream 5.0 Lite Spicy / Text to Image](https://hotapi.ai/models/seedream-5.0-lite-spicy/text-to-image): Uncensored text-to-image generation with crisp 2K–4K output and no content filter, through one API.
- [Seedream 5.0 Pro Spicy / Image Edit](https://hotapi.ai/models/seedream-5.0-pro-spicy/image-edit): Uncensored Pro-tier high-resolution image editing and multi-image blending — 1–10 reference images plus a prompt, no content filter, through one API.
- [Seedream 5.0 Pro Spicy / Text to Image](https://hotapi.ai/models/seedream-5.0-pro-spicy/text-to-image): Uncensored Pro-tier text-to-image generation with crisp 2K–4K output and no content filter, through one API.
- [Silly 1.0 Lite / Chat Completions](https://hotapi.ai/models/silly-1.0-lite/chat): Budget character chat and image understanding with OpenAI-compatible JSON and SSE responses. Independent from Silly 1.0.
- [Silly 2.0 / Chat Completions](https://hotapi.ai/models/silly-2.0/chat): Premium companion roleplay chat on a GLM-5.3 base — uncensored, stronger character lock, OpenAI-compatible, sync and SSE streaming.
- [Siren 1.0 Spicy / Generate Speech](https://hotapi.ai/models/siren-1.0-spicy/generate-speech): Expressive text-to-speech that carries breath, pauses and tone shifts, for narration and character voice work behind the same credit balance as the rest of the gateway.
- [Wan 3.0 Prime Pro Spicy / Image to Video](https://hotapi.ai/models/w3.0-prime-pro-spicy/image-to-video): Unrestricted Wan 3.0 image-to-video with first and optional last frame at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Prime Pro Spicy / Reference to Video](https://hotapi.ai/models/w3.0-prime-pro-spicy/reference-to-video): Unrestricted Wan 3.0 reference-to-video with images, videos, audio, a document, or a web page at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Prime Pro Spicy / Text to Video](https://hotapi.ai/models/w3.0-prime-pro-spicy/text-to-video): Unrestricted Wan 3.0 text-to-video at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Prime Spicy / Image to Video](https://hotapi.ai/models/w3.0-prime-spicy/image-to-video): Unrestricted Wan 3.0 image-to-video with first and optional last frame at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 3.0 Prime Spicy / Reference to Video](https://hotapi.ai/models/w3.0-prime-spicy/reference-to-video): Unrestricted Wan 3.0 reference-to-video with images, videos, audio, a document, or a web page at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 3.0 Prime Spicy / Text to Video](https://hotapi.ai/models/w3.0-prime-spicy/text-to-video): Unrestricted Wan 3.0 text-to-video at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 3.0 Pro Spicy / Image to Video](https://hotapi.ai/models/w3.0-pro-spicy/image-to-video): Unrestricted Wan 3.0 image-to-video with first and optional last frame at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Pro Spicy / Reference to Video](https://hotapi.ai/models/w3.0-pro-spicy/reference-to-video): Unrestricted Wan 3.0 reference-to-video with images, videos, audio, a document, or a web page at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Pro Spicy / Text to Video](https://hotapi.ai/models/w3.0-pro-spicy/text-to-video): Unrestricted Wan 3.0 text-to-video at 1080p, 2K, or 4K for 2–30 seconds, with generated audio.
- [Wan 3.0 Spicy / Image to Video](https://hotapi.ai/models/w3.0-spicy/image-to-video): Unrestricted Wan 3.0 image-to-video with first and optional last frame at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 3.0 Spicy / Reference to Video](https://hotapi.ai/models/w3.0-spicy/reference-to-video): Unrestricted Wan 3.0 reference-to-video with images, videos, audio, a document, or a web page at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 3.0 Spicy / Text to Video](https://hotapi.ai/models/w3.0-spicy/text-to-video): Unrestricted Wan 3.0 text-to-video at 480p / 720p / 1080p for 2–30 seconds, with generated audio.
- [Wan 2.2 Spicy / Image to Video](https://hotapi.ai/models/wan-2.2-spicy/image-to-video): Uncensored image-to-video generation — the faster, lighter Wan generation for high-volume jobs.
- [Wan 2.7 Spicy / Image to Video](https://hotapi.ai/models/wan-2.7-spicy/image-to-video): Uncensored image-to-video generation up to 1080p with optional audio, latest Wan generation.
- [Wan Animate / Animate Video](https://hotapi.ai/models/wan-animate-spicy/animate-video): Transfer reference-video motion to an image character or replace a character in a video. Charges use server-measured reference duration.
- [Z-Image Spicy Pro / Text to Image](https://hotapi.ai/models/z-image-spicy-pro/text-to-image): Uncensored Pro-tier text-to-image generation with a 256–2560px canvas and no content filter.
- [Z-Image Spicy / Text to Image](https://hotapi.ai/models/z-image-spicy/text-to-image): Uncensored text-to-image generation with fast, high-fidelity output and no content filter.

## Machine-readable reference

- [OpenAPI 3.1 contract](https://api.hotapi.ai/docs/json): Authoritative endpoint, authentication, request, and response schemas.
- [API Reference](https://hotapi.ai/docs/api): Rendered endpoint reference with copyable request examples.
- [Docs MCP server](https://hotapi.ai/mcp): Read-only Streamable HTTP MCP server for documentation search and exact operation lookup.

## Legal

- [Terms of Service](https://hotapi.ai/legal/terms.md): Terms of Service — eligibility, credits, liability, termination.
- [Privacy Policy](https://hotapi.ai/legal/privacy.md): Privacy Policy — data collected, processors, retention.
- [Acceptable Use Policy](https://hotapi.ai/legal/acceptable-use.md): Acceptable Use Policy — prohibited uses and how they are enforced.
- [Refund Policy](https://hotapi.ai/legal/refund-policy.md): Refund Policy — refunds, credit reversals, disputes.

See [llms-full.txt](https://hotapi.ai/llms-full.txt) for an aggregated Markdown export of the site's public content.