# PoYo.ai

> PoYo.ai is a unified model API for developers: image, video, music, 3D, chat, and tools behind one API key. Image, video, music, 3D, and tools use one async submit/status workflow. Chat uses OpenAI-compatible, Claude Messages, or Gemini native endpoints.

Every listed model has a live schema file. To go from "which model" to a working call: pick a model ID below, then fetch `https://poyo.ai/models/<model-id>/llms.txt`. That file returns the current input fields, defaults, constraints, pricing, and cURL/Python/JavaScript snippets generated from the same documentation OpenAPI the playground uses. If you fetch only one more thing, make it that file.

Media models: create an API key at [poyo.ai/dashboard/api-key](https://poyo.ai/dashboard/api-key) and set `POYO_API_KEY`. POST JSON to `https://api.poyo.ai/api/generate/submit` with `Authorization: Bearer $POYO_API_KEY`. Poll `https://api.poyo.ai/api/generate/status/{task_id}` or set `callback_url`. Failed tasks are not charged.

Chat models: POST to `https://api.poyo.ai/v1/chat/completions`, `https://api.poyo.ai/v1/messages`, or `https://api.poyo.ai/v1beta/models/{model}:generateContent` as documented in that model's `llms.txt`.

Billing is per successful output, priced per model, drawn from credits. Current prices live in each model's `llms.txt` and on the model page — do not infer them from training data.

This index lists 136 image, video, music, 3D, and chat models.

A worked example: [Flux Dev](https://poyo.ai/models/flux-dev/llms.txt).

## Documentation

- [Quickstart](https://docs.poyo.ai/index.md): First API call and request lifecycle
- [API overview](https://docs.poyo.ai/api-manual/overview.md): Architecture and unified generate API
- [Authentication](https://docs.poyo.ai/api-manual/overview.md): Bearer API keys
- [Query task status](https://docs.poyo.ai/api-manual/task-management/query-task-status.md): Poll long-running jobs
- [Webhooks](https://docs.poyo.ai/api-manual/task-management/webhooks.md): Receive results without polling
- [Error codes](https://docs.poyo.ai/api-manual/error-codes.md): Error shapes and retries
- [MCP](https://poyo.ai/mcp): Connect coding agents to PoYo

## Agent-readable surfaces

- [Per-model schema, worked example](https://poyo.ai/models/flux-dev/llms.txt): Live input and output schema, pricing, and snippets for `flux-dev`. Substitute any model page ID to get the same for that model
- [Documentation index](https://docs.poyo.ai/llms.txt): Every documentation page as a Markdown link
- [Full documentation text](https://docs.poyo.ai/llms-full.txt): The entire documentation in one file. Prefer the index or a specific page
- [MCP](https://poyo.ai/mcp): Model Context Protocol endpoint for agents

## Image generation

- [GPT Image 2](https://poyo.ai/models/gpt-image-2/llms.txt): `gpt-image-2`, `gpt-image-2-edit`. OpenAI's premium image generation family for text-to-image creation and single-image editing with simple prompt-driven controls.
- [Qwen Image 3.0](https://poyo.ai/models/qwen-image-3/llms.txt): `qwen-image-3`, `qwen-image-3-pro`. Alibaba's third-generation image model for long prompts, information-dense layouts, fine text rendering, multilingual visuals, and knowledge-rich image generation.
- [Flux Dev](https://poyo.ai/models/flux-dev/llms.txt): `flux-dev`. Black Forest Labs image model for text-to-image generation and single-image editing with output-size based pricing.
- [Flux Kontext](https://poyo.ai/models/flux-kontext/llms.txt): `flux-kontext-pro`, `flux-kontext-pro-edit`, `flux-kontext-max`, `flux-kontext-max-edit`. Black Forest Labs' in-context image generation and editing family for scene-preserving edits, text replacement, and prompt-driven visual changes.
- [Flux Schnell](https://poyo.ai/models/flux-schnell/llms.txt): `flux-schnell`. Black Forest Labs fast text-to-image model for low-cost prompt-based image generation with output-size based pricing.
- [FLUX.2](https://poyo.ai/models/flux-2/llms.txt): `flux-2-pro`, `flux-2-pro-edit`, `flux-2-flex`, `flux-2-flex-edit`. Black Forest Labs' production-grade model combining 4MP image generation and editing with multi-reference support, precise typography, and hex color control.
- [GPT Image 1.5](https://poyo.ai/models/gpt-image-1-5-api/llms.txt): `gpt-image-1.5`, `gpt-image-1.5-edit`. OpenAI's latest image model with 4x speed, precision editing, and superior text rendering.
- [GPT Image 2.5](https://poyo.ai/models/gpt-image-2-5/llms.txt): `gpt-image-2.5-flare`, `gpt-image-2.5-sunburst`. OpenAI image generation and editing with high-fidelity reference images, precise inpainting, multi-turn consistency, and transparent backgrounds. Explore Flare and Sunburst and compare GPT Image 2.5 with GPT Image 2 on PoYo.
- [GPT-4o Image](https://poyo.ai/models/gpt-4o-image-api/llms.txt): `gpt-4o-image`, `gpt-4o-image-edit`. OpenAI's native multimodal image generator with exceptional text rendering, precise prompt following, and conversational editing capabilities.
- [Grok Imagine Image 2.0](https://poyo.ai/models/grok-imagine-image-2/llms.txt): `grok-imagine-image-2.0`. xAI image generation and editing with up to three input images, five supported aspect ratios, 1K or 2K resolution, selectable quality, and up to four outputs.
- [Grok Imagine Image Quality](https://poyo.ai/models/grok-imagine-image-quality/llms.txt): `grok-imagine-image-quality`. xAI's higher-fidelity Grok Imagine image model for polished text-to-image generation and reference-based image editing.
- [Ideogram 4.5](https://poyo.ai/models/ideogram-4-5/llms.txt): `ideogram-v4.5`, `ideogram-v4.5-edit`. Generate images, posters and typography with Ideogram 4.5, or precisely edit a source image with masks and reference images. Compare quality-based pricing for generation and editing on PoYo.
- [Nano Banana Pro](https://poyo.ai/models/nano-banana-2-api/llms.txt): `nano-banana-pro`, `nano-banana-pro-edit`, `nano-banana-2`, `nano-banana-2-edit`. Google's advanced Gemini 3 Pro image model featuring 4K resolution, enhanced reasoning, real-time data integration, and multi-image composition capabilities.
- [Kling O1 Image](https://poyo.ai/models/kling-o1-image/llms.txt): `kling-o1-image-edit`. Kling O1 Image Edit focuses on reference-based image transformation with optional elements guidance, flexible aspect ratios, and 1K or 2K output tiers.
- [Kling O3 Image](https://poyo.ai/models/kling-o3-image/llms.txt): `kling-o3-image`, `kling-o3-image-edit`. Kling's O3 image family supports prompt-only generation, multi-reference editing, single outputs, and connected series generation with 1K to 4K resolution tiers.
- [Nano Banana](https://poyo.ai/models/nano-banana-api/llms.txt): `nano-banana`, `nano-banana-edit`. Google's leaderboard-topping image model (Gemini 2.5 Flash) excelling in natural language editing, character consistency, and multi-image blending.
- [Nano Banana 2](https://poyo.ai/models/nano-banana-2/llms.txt): `nano-banana-2-new`, `nano-banana-2-new-edit`, `nano-banana-2-official`, `nano-banana-2-official-edit`. Google's next-gen image model powered by Gemini 3.1 Flash with native 2K/4K resolution, chain-of-thought reasoning, precise multi-language text rendering, and up to 14 reference images.
- [Nano Banana 2 Lite](https://poyo.ai/models/nano-banana-2-lite/llms.txt): `nano-banana-2-lite`, `nano-banana-2-lite-edit`. Google's fastest and most cost-efficient Gemini Image model, built for rapid ideation, high-throughput image generation, low-latency creative workflows, and scaled production pipelines.
- [Nano Banana 2.1](https://poyo.ai/models/nano-banana-2-1/llms.txt): `nano-banana-2.1`. Generate and edit 1K, 2K and 4K images with Google's Nano Banana 2.1. Combine up to 10 reference images for product visuals, posters and consistent creative assets. From 4 credits ($0.02) per image.
- [Qwen Image 2.1](https://poyo.ai/models/qwen-image-2-1/llms.txt): `qwen-image-2.1`. Alibaba's 7B open-weight unified text-to-image and editing model with native RGBA transparency, up to 10 reference images, and 2K resolution.
- [Seedream 4](https://poyo.ai/models/seedream-4/llms.txt): `seedream-4`, `seedream-4-edit`. ByteDance's multimodal image model for native 1K to 4K generation, reference-guided editing, and batch outputs up to 15 images.
- [Seedream 4.5](https://poyo.ai/models/seedream-4-5-api/llms.txt): `seedream-4.5`, `seedream-4.5-edit`. ByteDance's unified 4K image generation and editing model with professional-grade text rendering and commercial photography quality.
- [Seedream 5.0 Flash](https://poyo.ai/models/seedream-5-0-flash/llms.txt): `seedream-5.0-flash`, `seedream-5.0-flash-edit`. ByteDance's fast, cost-efficient image model for 1K/1.5K/2K generation, multi-reference editing, and multilingual visual content. 4 credits per image.
- [Seedream 5.0 Lite](https://poyo.ai/models/seedream-5-0-lite-api/llms.txt): `seedream-5.0-lite`, `seedream-5.0-lite-edit`. ByteDance's efficient multimodal image model with native 2K/3K resolution, deep thinking, bilingual text rendering, and smart editing.
- [Seedream 5.0 Pro](https://poyo.ai/models/seedream-5-0-pro/llms.txt): `seedream-5.0-pro`, `seedream-5.0-pro-edit`. ByteDance's flagship image model for precise prompt following, dense layouts, multilingual text rendering, and region-precise editing.
- [Wan 2.7 Image](https://poyo.ai/models/wan-2-7-image/llms.txt): `wan-2.7-image`, `wan-2.7-image-pro`. Alibaba's unified Wan 2.7 image family for text-to-image generation and reference-based image editing with standard and pro quality tiers.
- [Z-Image](https://poyo.ai/models/z-image/llms.txt): `z-image`. Alibaba's efficient 6B-parameter image model with sub-second generation and exceptional Chinese-English bilingual text rendering capabilities.

## Video generation

- [FLUX 3](https://poyo.ai/models/flux-3/llms.txt): `flux-3/text-to-video`, `flux-3/image-to-video`, `flux-3/first-last-frame-to-video`, `flux-3/extend-video`, `flux-3/keyframes-to-video`. Black Forest Labs' FLUX 3 video family for text, images, first and last frames, source-video extension, positioned keyframes, and native audio generation.
- [Gemini Omni 1.1 Flash](https://poyo.ai/models/gemini-omni-1-1-flash/llms.txt): `gemini-omni-1.1-flash`. Gemini Omni 1.1 Flash API for text-to-video, first and last frame interpolation, reference image generation, and reference-video workflows.
- [Kling 3.0](https://poyo.ai/models/kling-3-api/llms.txt): `kling-3.0/standard`, `kling-3.0/pro`, `kling-3.0/4K`. Kuaishou's advanced Kling 3.0 video model family with Standard, Pro, and native 4K generation, multi-shot storyboarding, synchronized audio, and element-based consistency.
- [Kling 3.0 Motion Control](https://poyo.ai/models/kling-3-0-motion-control/llms.txt): `kling-3.0-motion-control`. Kling 3.0 Motion Control is a reference-driven motion transfer model that combines one character image and one source video with transparent per-second pricing.
- [Kling O3](https://poyo.ai/models/kling-o3-api/llms.txt): `kling-o3/standard`, `kling-o3/pro`, `kling-o3/4K`. Kling O3 video generation on PoYo with Standard, Pro, and 4K variants for text-to-video, image-to-video, and reference-to-video workflows.
- [MiniMax H3 / Hailuo 03](https://poyo.ai/models/minimax-h3/llms.txt): `hailuo-03`. MiniMax H3 (Hailuo 03) generates native 2K video from text, first/last frames, or image, video, and audio references.
- [Seedance 2.0 Mini](https://poyo.ai/models/seedance-2-mini/llms.txt): `seedance-2-mini`. ByteDance Seedance 2.0 Mini video generation for lower-cost text-to-video, image-to-video, and multimodal reference workflows with 480p and 720p output.
- [Seedance 2.5](https://poyo.ai/models/seedance-2-5/llms.txt): `seedance-2.5`. ByteDance Seedance 2.5 video generation with 4-30 second output, first and last frame control, up to 50 image, video, and audio references, optional synchronized audio, and 480p, 720p, or 1080p delivery.
- [Grok Imagine Video 1.5](https://poyo.ai/models/grok-imagine-video-1-5/llms.txt): `grok-imagine-video-1.5`. Grok Imagine Video 1.5 API for text-to-video, single-frame image-to-video, and 1–7 image reference-to-video generation with up to 1080p output.
- [Kling 3.0 Turbo](https://poyo.ai/models/kling-3-0-turbo/llms.txt): `kling-3.0-turbo/standard`, `kling-3.0-turbo/pro`. Kling 3.0 Turbo is the speed-optimized Kling 3.0 variant for high-volume text-to-video and image-to-video generation with multi-shot storyboarding. Standard (720p) and Pro (1080p) models available.
- [Happy Horse 1.1](https://poyo.ai/models/happy-horse-1-1/llms.txt): `happy-horse-1.1`. Alibaba Happy Horse 1.1 video generation with text-to-video, image-to-video, and reference-to-video workflows.
- [Seedance 2](https://poyo.ai/models/seedance-2/llms.txt): `seedance-2`, `seedance-2-fast`. ByteDance Seedance 2 video generation with text-to-video, image-to-video, multimodal reference-to-video, video-to-video, and audio-to-video workflows using image, video, and audio references with optional native audio.
- [Sora 2 Official](https://poyo.ai/models/sora-2-official/llms.txt): `sora-2-official`, `sora-2-pro-official`, `sora-2-beta`. OpenAI Sora 2 on PoYo with synced audio, improved physics, optional reference image input, and fixed 4-second, 8-second, 12-second, 16-second, and 20-second tiers.
- [Wan 2.7 Video](https://poyo.ai/models/wan-2-7-video/llms.txt): `wan2.7-text-to-video`, `wan2.7-image-to-video`, `wan2.7-reference-to-video`, `wan2.7-edit-video`. Wan 2.7 Video models on PoYo for text-to-video, image-to-video, reference-to-video, and edit-video workflows.
- [Grok Imagine](https://poyo.ai/models/grok-imagine/llms.txt): `grok-imagine-image`, `grok-imagine`. xAI's Aurora-powered visual AI for image generation and video creation with Fun, Normal, and Spicy creative modes.
- [Hailuo 02](https://poyo.ai/models/hailuo-02/llms.txt): `hailuo-02`, `hailuo-02-pro`. MiniMax's #2 globally-ranked video model with NCR architecture, ultra-realistic physics, and 1080p cinematic output.
- [Hailuo 2.3](https://poyo.ai/models/hailuo-2-3/llms.txt): `hailuo-2.3`. MiniMax's Hailuo 2.3 video model for realistic human motion, expressive characters, and text-to-video or first-frame guided generation at 768p and 1080p.
- [Happy Horse](https://poyo.ai/models/happy-horse/llms.txt): `happy-horse`. Alibaba Happy Horse 1.0 video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit workflows.
- [Kling 1.6](https://poyo.ai/models/kling-1-6/llms.txt): `kling-1.6/standard`, `kling-1.6/pro`. Kling 1.6 Standard and Pro video generation on PoYo with text, first/last frame, and multi-image element reference workflows.
- [Kling 2.1](https://poyo.ai/models/kling-2-1/llms.txt): `kling-2.1/standard`, `kling-2.1/pro`. Kling 2.1 on PoYo provides Standard and Pro image-to-video modes with 5-second and 10-second clips, start-frame control, and optional end-frame control in Pro.
- [Kling 2.5 Turbo Pro](https://poyo.ai/models/kling-2-5-turbo-pro/llms.txt): `kling-2.5-turbo-pro`. Kling 2.5 Turbo Pro is a flexible short-form video model with text-to-video, optional frame guidance, smooth motion, cinematic depth, and fixed 5-second and 10-second tiers.
- [Kling 2.6](https://poyo.ai/models/kling-2-6/llms.txt): `kling-2.6`. Kuaishou's revolutionary video model that simultaneously generates visuals with synchronized dialogue, sound effects, and ambient audio in one pass.
- [Kling 2.6 Motion Control](https://poyo.ai/models/kling-2-6-motion-control/llms.txt): `kling-2.6-motion-control`. Kuaishou's motion control model that transfers motion from reference videos to character images while maintaining identity and adapting environments.
- [Kling Avatar 2.0](https://poyo.ai/models/kling-avatar-2-0/llms.txt): `kling-avatar-2.0/standard`, `kling-avatar-2.0/pro`. Kling Avatar 2.0 creates audio-driven talking avatar videos from one reference image and one driving audio file, with Standard and Pro quality modes.
- [MiniMax H3 Max](https://poyo.ai/models/minimax-h3-max/llms.txt): `h3-max`. MiniMax H3 Max generates 5–15 second videos from text, first/last frames, or image, video and audio references at 480p, 768p and 1080p.
- [MiniMax H3 Max Turbo](https://poyo.ai/models/minimax-h3-max-turbo/llms.txt): `h3-max-turbo`. MiniMax H3 Max Turbo generates 5–15 second videos from text or first/last frames at 480p, 768p and 1080p.
- [Omni Flash](https://poyo.ai/models/omni-flash/llms.txt): `omni-flash`. Omni Flash API access for text-to-video, image-to-video, three-image reference fusion, and video-input generation workflows.
- [Runway Gen-4.5](https://poyo.ai/models/runway-gen-4-5/llms.txt): `runway-gen-4.5`. Runway Gen-4.5 is a high-fidelity video model focused on prompt adherence, cinematic motion, visual fidelity, and optional reference image guidance.
- [Seedance 1.0 Pro](https://poyo.ai/models/seedance-1-pro/llms.txt): `seedance-1.0-pro`. ByteDance's #1 ranked video model with multi-shot storytelling, cinema-grade motion, and bilingual text-to-video generation.
- [Seedance 1.5 Pro](https://poyo.ai/models/seedance-1-5-pro/llms.txt): `seedance-1.5-pro`. ByteDance's latest video model with synchronized audio generation, flexible aspect ratios, and enhanced motion control.
- [Veo 3.1](https://poyo.ai/models/veo-3-1/llms.txt): `veo3.1-lite`, `veo3.1-fast`, `veo3.1-quality`. Google DeepMind's VEO 3.1 video family with text-to-video, image-to-video, 720p, 1080p, and 4K output options.
- [Veo 3.1 Official](https://poyo.ai/models/veo-3-1-official/llms.txt): `veo3.1-fast-official`, `veo3.1-lite-official`, `veo3.1-quality-official`. Official VEO 3.1 video generation with text, image, first/last-frame and reference workflows across fast, lite and quality tiers.
- [Wan 2.2 Fast](https://poyo.ai/models/wan-2-2-fast/llms.txt): `wan2.2-image-to-video-fast`, `wan2.2-text-to-video-fast`. Wan 2.2 Fast provides fast text-to-video and image-to-video generation with low-cost 480p and 720p tiers for quick iteration.
- [Wan 2.5](https://poyo.ai/models/wan-2-5/llms.txt): `wan2.5-image-to-video`, `wan2.5-text-to-video`. Wan 2.5 combines text-to-video and image-to-video generation with 5-second and 10-second output, synchronized audio support, and multiple size and resolution tiers.
- [Wan 2.6](https://poyo.ai/models/wan-2-6/llms.txt): `wan2.6-text-to-video`, `wan2.6-image-to-video`, `wan2.6-video-to-video`. Alibaba's Wan 2.6 video generation family for text-to-video, image-to-video, and video-to-video with multi-shot 1080p output.
- [Wan 3.0](https://poyo.ai/models/wan-3-0/llms.txt): `wan3.0-text-to-video`, `wan3.0-image-to-video`, `wan3.0-reference-to-video`. Generate videos up to 30 seconds with Wan 3.0 using text, first and last frames, or multimodal references including images, video, audio, documents, and links.
- [Wan 3.0 Video Prime](https://poyo.ai/models/wan-3-0-video-prime/llms.txt): `wan3.0-prime-text-to-video`, `wan3.0-prime-image-to-video`, `wan3.0-prime-reference-to-video`. Wan 3.0 Video Prime is Alibaba's Wan 3.0 tier optimized for faster turnaround, with multimodal image, video, audio, document, and public webpage references, videos up to 30 seconds, and optional generated audio.
- [Wan Animate](https://poyo.ai/models/wan-animate/llms.txt): `wan-animate-move`, `wan-animate-replace`. Alibaba's 14B-parameter character animation model that transfers motion from reference videos to static characters with exceptional identity preservation.

## Music and audio

- [Add Instrumental](https://poyo.ai/models/add-instrumental/llms.txt): `add-instrumental`. Generate musical accompaniment for uploaded audio files containing vocals or melodies. AI creates matching instrumental backing tracks with customizable style tags, genre preferences, and quality controls. Perfect for adding professional-quality backing to vocal recordings.
- [Add Vocals](https://poyo.ai/models/add-vocals/llms.txt): `add-vocals`. Layer AI-generated vocals onto existing instrumental tracks. Provide lyrics or descriptions and the API generates matching vocal performances with customizable gender, style, and expression. Transform instrumental music into complete songs with professional AI singing.
- [AI Music Video](https://poyo.ai/models/create-music-video/llms.txt): `create-music-video`. Generate visualized music videos from audio tracks. Create engaging visual content automatically synchronized to your music with optional author attribution and brand watermarks. Perfect for social media content, promotional materials, and music distribution.
- [Boost Music Style](https://poyo.ai/models/boost-music-style/llms.txt): `boost-music-style`. AI-enhanced music style description generator. Transform simple style inputs like 'pop, mysterious' into detailed, comprehensive musical descriptions. Optimize your prompts for better music generation results with enriched genre, mood, and instrumentation details.
- [Check Suno Voice](https://poyo.ai/models/suno-voice-check/llms.txt): `suno-voice-check`. Check whether the Suno Voice produced by a completed Generate Voice task is currently available.
- [Convert to WAV](https://poyo.ai/models/convert-to-wav/llms.txt): `convert-to-wav`. Obtain high-quality WAV format files from your generated music. Convert any PoYo-generated audio to lossless WAV format for professional use, further editing, or high-fidelity playback. Essential for production workflows requiring uncompressed audio.
- [Eleven v4](https://poyo.ai/models/eleven-v4/llms.txt): `elevenlabs-v4-tts`. Generate expressive text-to-speech with Eleven v4. Direct delivery with audio tags and create multilingual voiceovers with voice controls, 19 audio formats and optional timestamps.
- [Eleven v4 Turbo](https://poyo.ai/models/eleven-v4-turbo/llms.txt): `elevenlabs-v4-turbo-tts`. Generate natural, expressive speech with Eleven v4 Turbo. Supports 90+ languages, inline audio tags, stability and similarity controls, 19 output formats, and optional timing files through an asynchronous API.
- [ElevenLabs Music](https://poyo.ai/models/elevenlabs-music/llms.txt): `elevenlabs-music`. Generate studio-grade AI music with prompt-based songs, instrumental mode, structured composition plans, section timing, multilingual vocals, and flexible audio output formats.
- [ElevenLabs TTS Turbo v2.5](https://poyo.ai/models/elevenlabs-tts-turbo-2-5/llms.txt): `elevenlabs-tts-turbo-2-5`. Generate low-latency multilingual speech with ElevenLabs TTS Turbo v2.5. Supports voice selection, stability, similarity boost, style, speed, timestamps, language code, context text, and text normalization.
- [ElevenLabs V3 TTS](https://poyo.ai/models/elevenlabs-v3-tts/llms.txt): `elevenlabs-v3-tts`. Generate expressive text-to-speech audio with ElevenLabs V3 TTS. Supports audio tags, voice selection, stability, language code, text normalization, and optional timestamps for production speech workflows.
- [Extend Music](https://poyo.ai/models/extend-music/llms.txt): `extend-music`. Extend or modify existing music tracks by creating sequels based on source audio. Supports custom mode with full parameter control or simple mode inheriting original parameters. Specify continuation points and maintain style consistency across extensions up to 8 minutes.
- [Gemini 3.1 Flash TTS](https://poyo.ai/models/gemini-3-1-flash-tts/llms.txt): `gemini-3-1-flash-tts`. Generate expressive multilingual speech with Gemini 3.1 Flash TTS. Supports granular audio tags, natural-language style instructions, Gemini voice presets, two-speaker dialogue, and MP3, WAV, or OGG Opus output.
- [Gemini 3.8 Flash Lite TTS](https://poyo.ai/models/gemini-3-8-flash-lite-tts/llms.txt): `gemini-3.8-flash-lite-tts`. Generate natural multilingual speech with Gemini 3.8 Flash Lite TTS. Choose from 30 preset voices, direct delivery with style instructions and create structured two-speaker dialogue.
- [Gemini 3.8 Flash TTS](https://poyo.ai/models/gemini-3-8-flash-tts/llms.txt): `gemini-3.8-flash-tts`. Generate expressive multilingual speech with Gemini 3.8 Flash TTS. Direct emotion and pacing with separate style instructions, choose from 30 preset voices, and create structured two-speaker dialogue.
- [Generate Lyrics](https://poyo.ai/models/generate-lyrics/llms.txt): `generate-lyrics`. AI-powered lyrics generation based on themes, moods, and descriptions. Create original song lyrics from simple prompts up to 200 characters. Generate creative, coherent lyrics for any genre or emotional tone with professional songwriting quality.
- [Generate Mashup](https://poyo.ai/models/generate-mashup/llms.txt): `generate-mashup`. Blend exactly two uploaded audio tracks with Suno using simple or custom controls for style, vocals, model version, and duration.
- [Generate MIDI](https://poyo.ai/models/generate-midi/llms.txt): `generate-midi`. Convert a completed Suno vocal-separation task into a downloadable MIDI file.
- [Generate Music Cover](https://poyo.ai/models/generate-music-cover/llms.txt): `generate-music-cover`. Generate alternative cover versions of existing music tracks. Create variations with automatic style changes while maintaining the essence of the original composition. Perfect for producing multiple versions or exploring different interpretations of your generated music.
- [Generate Persona](https://poyo.ai/models/generate-persona/llms.txt): `generate-persona`. Create reusable music personas from existing audio tracks. Save distinctive vocal characteristics, musical styles, and personality traits for consistent use across multiple generations. Build your own AI artist profiles for brand consistency and style continuity.
- [Generate Sounds](https://poyo.ai/models/generate-sounds/llms.txt): `generate-sounds`. Generate sound effects and ambience with optional loop, tempo, musical key, and lyric controls.
- [Generate Suno Voice](https://poyo.ai/models/suno-voice-generate/llms.txt): `suno-voice-generate`. Create a reusable Suno Voice ID from a validated task and a recording of its verification phrase.
- [Get Timestamped Lyrics](https://poyo.ai/models/get-timestamped-lyrics/llms.txt): `get-timestamped-lyrics`. Retrieve lyrics synchronized with precise timestamps from generated music. Returns word-by-word timing data, waveform visualization, and alignment accuracy scores. Essential for karaoke applications, lyric videos, and music synchronization projects.
- [MiniMax Music 2.6](https://poyo.ai/models/minimax-music-2-6/llms.txt): `minimax-music-2.6`. Generate complete songs from style prompts and lyrics with MiniMax Music 2.6. Supports vocal tracks, instrumental generation, prompt-driven lyrics optimization, and configurable audio output settings.
- [Regenerate Suno Voice Phrase](https://poyo.ai/models/suno-voice-regenerate/llms.txt): `suno-voice-regenerate`. Request a new verification phrase for an existing Suno Voice validation task.
- [Replace Section](https://poyo.ai/models/replace-section/llms.txt): `replace-section`. Replace specific sections of generated music tracks with precision timing control. Modify choruses, verses, or any segment by specifying start and end times. Maintains overall coherence while allowing targeted changes to lyrics, style, or musical elements.
- [Suno Music](https://poyo.ai/models/generate-music/llms.txt): `generate-music`. AI music generator with customizable styles, vocals, and full creative control over musical characteristics and quality.
- [Upload and Cover Audio](https://poyo.ai/models/upload-and-cover-audio/llms.txt): `upload-and-cover-audio`. Transform audio tracks into new styles while preserving original melodies. Upload your audio files (up to 2 minutes) and convert them with AI-powered style transfer. Supports custom and simplified modes with vocal/instrumental options and audio weight controls.
- [Upload and Extend Audio](https://poyo.ai/models/upload-and-extend-audio/llms.txt): `upload-and-extend-audio`. Upload audio files and extend them while maintaining the original style and characteristics. AI generates seamless continuations from specified time points. Supports multiple model versions with style weight and creative controls for natural extensions.
- [Validate Suno Voice](https://poyo.ai/models/suno-voice-validate/llms.txt): `suno-voice-validate`. Validate a clean vocal sample and receive the verification phrase required to create a reusable Suno Voice.
- [Vocal Remover](https://poyo.ai/models/vocal-remover-api/llms.txt): `separate-vocals`, `stem-split`, `upload-and-separate-vocals`. Separate vocals from instrumentals or split audio into multiple stem tracks. Two modes available: vocal separation for isolating vocals and backing tracks, or stem splitting for extracting drums, bass, vocals, and other instruments individually. Professional-grade audio source separation.
- [xAI TTS 1](https://poyo.ai/models/xai-tts-1/llms.txt): `xai-tts-1`. Generate low-latency expressive multilingual speech with xAI TTS 1. Supports speech tags, five voice presets, automatic language detection, and flexible MP3, WAV, PCM, mu-law, or A-law output.

## 3D

- [Hunyuan 3D v3.1](https://poyo.ai/models/hunyuan-3d-3-1/llms.txt): `hunyuan-3d/v3.1/pro/text-to-3d`, `hunyuan-3d/v3.1/pro/image-to-3d`, `hunyuan-3d/v3.1/rapid/text-to-3d`, `hunyuan-3d/v3.1/rapid/image-to-3d`. Hunyuan 3D v3.1 generation with Pro and Rapid text-to-3D and image-to-3D models.
- [Meshy 6 3D](https://poyo.ai/models/meshy-6-3d/llms.txt): `meshy-6-text-to-3d`, `meshy-6-image-to-3d`, `meshy-6-multi-image-to-3d`. Meshy 6 3D generation with text-to-3D, image-to-3D, and multi-image-to-3D workflows.
- [Meshy 7.1](https://poyo.ai/models/meshy-7-1/llms.txt): `meshy-7.1-image-to-3d`, `meshy-7.1-text-to-3d`, `meshy-7.1-multi-image-to-3d`. Detailed 3D assets from text, a single image, or up to four views, with geometry controls and optional textures, rigging and animation.
- [Tripo3D H3.1](https://poyo.ai/models/tripo-h31-3d/llms.txt): `tripo3d-h3.1-text-to-3d`, `tripo3d-h3.1-image-to-3d`, `tripo3d-h3.1-multiview-to-3d`. High-detail Tripo3D H3.1 generation with text-to-3D, image-to-3D, and multiview-to-3D workflows.
- [Tripo3D P1](https://poyo.ai/models/tripo-p1-3d/llms.txt): `tripo3d-p1-text-to-3d`, `tripo3d-p1-image-to-3d`. Clean low-poly Tripo3D P1 generation with text-to-3D and image-to-3D workflows.

## Chat

- [Claude Sonnet 5](https://poyo.ai/models/claude-sonnet-5/llms.txt): `claude-sonnet-5`. Claude Sonnet 5 API access for agentic coding, long-running agents, browser and computer use, professional workflows, 1M context, and up to 128K output.
- [DeepSeek V4 Flash](https://poyo.ai/models/deepseek-v4-flash/llms.txt): `deepseek-v4-flash`. DeepSeek V4 Flash is a fast, economical DeepSeek V4 API model with 1M-context chat, 284B total parameters, and 13B active parameters.
- [Kimi K3](https://poyo.ai/models/kimi-k3/llms.txt): `kimi-k3`. Moonshot AI's 2.8T-parameter flagship multimodal model with a 1M-token context window, built for long-horizon coding, deep reasoning, knowledge work, and tool-using agents.
- [Claude 4.5 Series](https://poyo.ai/models/claude-4-5-api/llms.txt): `claude-opus-4-5-20251101`, `claude-sonnet-4-5-20250929`, `claude-haiku-4-5-20251001`. Anthropic's Claude 4.5 series model — Opus, Sonnet & Haiku
- [Claude 4.6 API](https://poyo.ai/models/claude-4-6-api/llms.txt): `claude-sonnet-4-6`, `claude-opus-4-6`. Claude Sonnet 4.6 and Claude Opus 4.6 API access for coding, agents, computer use, and long-context reasoning.
- [Claude Fable 5.1](https://poyo.ai/models/claude-fable-5-1/llms.txt): `claude-fable-5-1`. Anthropic's most capable generally available model for long-horizon coding, knowledge work, research, vision, 1M context, and up to 128K output.
- [Claude Haiku 5.5](https://poyo.ai/models/claude-haiku-5-5/llms.txt): `claude-haiku-5-5`. Anthropic’s compact model for fast classification, extraction, summaries, and subagent workflows with adaptive reasoning and a 1M-token context.
- [Claude Opus 4.8](https://poyo.ai/models/claude-opus-4-8/llms.txt): `claude-opus-4-8`. Claude Opus 4.8 supports long-context chat, agentic coding, professional reasoning, high-output workflows, 1M context, and up to 128K output.
- [Claude Opus 5](https://poyo.ai/models/claude-opus-5/llms.txt): `claude-opus-5`. Anthropic's flagship agentic model for advanced coding, long-horizon execution, computer use, deep research, and professional knowledge work.
- [Claude Opus 5.5](https://poyo.ai/models/claude-opus-5-5/llms.txt): `claude-opus-5-5`. Claude Opus 5.5 API on PoYo. Use Chat Completions or Claude Messages at $3.2 input and $16 output per million tokens, 20% below official standard rates.
- [Claude Sonnet 5.5](https://poyo.ai/models/claude-sonnet-5-5/llms.txt): `claude-sonnet-5-5`. Claude Sonnet 5.5 API on PoYo. Use Chat Completions or Claude Messages at $1.6 input and $8 output per million tokens, 20% below official standard rates.
- [DeepSeek V4.1 Flash](https://poyo.ai/models/deepseek-v4-1-flash/llms.txt): `deepseek-flash`. DeepSeek V4.1 Flash is a 552B MoE chat model with native vision, 1M context, 384K max output, and 8B/16B active parameters for cheaper agent workloads.
- [Gemini 3.5 Flash](https://poyo.ai/models/gemini-3-5-flash/llms.txt): `gemini-3.5-flash`. Gemini 3.5 Flash API access for chat, coding, reasoning, and production agent workflows.
- [DeepSeek V4 Pro](https://poyo.ai/models/deepseek-v4-pro/llms.txt): `deepseek-v4-pro`. DeepSeek V4 Pro is a stronger reasoning, coding, and agent workflow model with 1M-context chat, 1.6T total parameters, and 49B active parameters.
- [Claude Opus 4.7](https://poyo.ai/models/claude-opus-4-7/llms.txt): `claude-opus-4-7`. Anthropic's most capable generally available model for frontier coding, deep reasoning, and high-resolution vision.
- [Gemini 3 Series](https://poyo.ai/models/gemini-3-api/llms.txt): `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-pro-preview`. Google's Gemini 3 series model — Flash Preview & Pro Preview
- [Gemini 3.7 Flash](https://poyo.ai/models/gemini-3-7-flash/llms.txt): `gemini-3.7-flash`. Google's GA Flash model for agentic coding, multimodal reasoning, web development, long-context knowledge work, and tool-using applications.
- [Gemini 3.8 Flash](https://poyo.ai/models/gemini-3-8-flash/llms.txt): `gemini-3.8-flash`. Google's best reasoning and coding Flash model for long-horizon software engineering, autonomous agents, and enterprise workflows.
- [Gemini 4 Argon](https://poyo.ai/models/gemini-4-argon/llms.txt): `gemini-4-argon`. Gemini 4 Argon API on PoYo. Google DeepMind's frontier reasoning model with 1M unified context & output for long-horizon coding, knowledge work, and cybersecurity at $1.60 input and $8.00 output per 1M tokens (20% off official).
- [GPT-5.2](https://poyo.ai/models/gpt-5-2/llms.txt): `gpt-5.2`. GPT-5.2 API access for chat, coding, reasoning, and production agent workflows.
- [GPT-5.4](https://poyo.ai/models/gpt-5-4/llms.txt): `gpt-5.4`. GPT-5.4 API access for chat, coding, reasoning, and production agent workflows.
- [GPT-5.5](https://poyo.ai/models/gpt-5-5/llms.txt): `gpt-5.5`. GPT-5.5 API access for chat, coding, reasoning, and production agent workflows.
- [GPT-5.6](https://poyo.ai/models/gpt-5-6/llms.txt): `gpt-5-6-luna`, `gpt-5-6-terra`, `gpt-5-6-sol`. GPT-5.6 API access for Sol, Terra, and Luna through the Responses API, from high-throughput automation to frontier coding and agent workflows.
- [GPT-6 Astra](https://poyo.ai/models/gpt-6-astra/llms.txt): `gpt-6-astra`. GPT-6 Astra API for advanced reasoning, coding, and agent workflows. Use Chat Completions or Responses with pay-as-you-go pricing on PoYo.
- [GPT-6 Luna](https://poyo.ai/models/gpt-6-luna/llms.txt): `gpt-6-luna`. GPT-6 Luna API on PoYo. Use Chat Completions or Responses at $0.08 input and $0.4 output per million tokens, 20% below official standard rates.
- [GPT-6 Sol](https://poyo.ai/models/gpt-6-sol/llms.txt): `gpt-6-sol`. GPT-6 Sol API on PoYo. Use Chat Completions or Responses at $1.6 input and $8 output per million tokens, 20% below official standard rates.
- [GPT-6.1 Sol](https://poyo.ai/models/gpt-6-1-sol/llms.txt): `gpt-6.1-sol`. GPT-6.1 Sol API on PoYo. Use Chat Completions or Responses at $1.6 input and $8 output per million tokens, 20% below official standard rates.
- [Grok 4.6](https://poyo.ai/models/grok-4-6/llms.txt): `grok-4.6`. xAI's frontier model for long-running agents, coding, engineering, knowledge work, and ambitious interactive or visual projects.
- [Grok 4.7](https://poyo.ai/models/grok-4-7/llms.txt): `grok-4.7`. Grok 4.7 API on PoYo. Use Chat Completions at $1.6 input and $4.8 output per million tokens, 20% below official standard rates.

## Tools

- [AI Video Background Removal](https://poyo.ai/models/video-background-removal/llms.txt): `poyo-ai/video-background-removal`. AI video background removal API for isolating subjects from existing videos with optional output format, audio, and background color controls.
- [AI Video Upscaler](https://poyo.ai/models/video-upscaler/llms.txt): `poyo-ai/video-upscaler`. AI video upscaler API for increasing the resolution of existing videos with a public video URL and scale factor.
- [Image Translator](https://poyo.ai/models/image-translator/llms.txt): `poyo-ai/image-translator`. Basic AI image translation on PoYo with image_urls, source_language, and target_language controls.
- [Omni Moderation](https://poyo.ai/models/omni-moderation-latest/llms.txt): `omni-moderation-latest`. Omni Moderation is OpenAI’s multimodal model for reviewing multilingual text and images. PoYo provides free API access to this model, with category flags and confidence scores for content review workflows.
- [Video Translator](https://poyo.ai/models/video-translator/llms.txt): `poyo-ai/video-translator`. Basic AI video translation on PoYo with video_urls, source_language, and target_language controls.

## Optional

- [Model gallery](https://poyo.ai/models): Browse the full catalog
- [Dashboard](https://poyo.ai/dashboard): API keys, usage, and billing
- [Docs](https://docs.poyo.ai): Human-readable documentation