A curated index of open-source examples for the PoYo AI API: one repository per model with cURL, Node.js, and often Python examples, plus prompt libraries, developer tools, and starter apps. One API key covers video, image, chat, music, speech, and 3D models.
Each entry lists the cheapest headline price from PoYo's live model catalog. Prices are in USD (1 credit = $0.005) and can change, so confirm on the model page before a production rollout.
Last generated from PoYo's model catalog on 2026-11-18.
- Video
- Image
- Chat and LLM
- Music and speech
- 3D
- Prompt libraries
- Tools
- Starter apps
- More models on PoYo
- Quickstart
- Contributing
| Model | Repository | What it does | Price from | Links |
|---|---|---|---|---|
| Seedance 2.5 Flash | Seedance-2.5-Flash-API | ByteDance Seedance 2.5 Flash, the faster, lower-cost tier of Seedance 2.5: up to 30-second 480p or 720p videos with synchronized audio from text, first and last frames, or image... | $0.0925 per second | Model page · Docs |
| Seedance 2.5 | Seedance-2.5-API | 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... | $0.14 per second | Model page · Docs |
| Kling 4.0 New | Kling-4.0-API | Generate 3–30 second videos from text, first and last frames, or image/video references and subjects. | $0.1425 per second | Model page · Docs |
| Seedance 2.0 | Seedance-2.0-API | 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... | $0.07 per second | Model page · Docs |
| Sora 2 | Sora-2-API | 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. | $0.20 per video | Model page · Docs |
| Veo 3.1 | Veo-3.1-API | Official VEO 3.1 video generation with text, image, first/last-frame and reference workflows across fast, lite and quality tiers. | $0.018 per second | Model page · Docs |
| Kling 3.0 | Kling-3.0-API | 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. | $0.135 per second | Model page · Docs |
| MiniMax H3 (Hailuo 03) | MiniMax-H3-API | MiniMax H3 (Hailuo 03) generates native 2K video from text, first/last frames, or image, video, and audio references. | $0.105 per second | Model page · Docs |
| HeyGen Avatar 6 New | HeyGen-Avatar-6-API | HeyGen Avatar 6 and Avatar 6 Turbo lip-synced talking videos at 1080p or 2K from a photo, an animated character video, or one of 1,248 HeyGen public avatars, driven by audio or text. | $0.04 per second | Model page · Docs |
| FLUX 3 Video | FLUX-3-Video-API | Black Forest Labs' FLUX 3 video family for text, images, first and last frames, source-video extension, positioned keyframes, and native audio generation. | $0.17 per second | Model page · Docs |
| Grok Imagine Video 1.5 | Grok-Imagine-Video-1.5-API | 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. | $0.0725 per second | Model page · Docs |
| Hailuo 2.3 | Hailuo-2.3-API | 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. | $0.175 per video | Model page · Docs |
| Happy Horse | Happy-Horse-API | Alibaba Happy Horse 1.0 video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit workflows. | $0.08 per second | Model page · Docs |
| Kling 3.0 Turbo | Kling-3.0-Turbo-API | 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. | $0.085 per second | Model page · Docs |
| Kling Avatar 2.0 | Kling-Avatar-2.0-API | 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. | $0.035 per second | Model page · Docs |
| Kling O3 | Kling-O3-API | Kling O3 video generation on PoYo with Standard, Pro, and 4K variants for text-to-video, image-to-video, and reference-to-video workflows. | $0.05 per second | Model page · Docs |
| Omni Flash | Omni-Flash-API | Omni Flash API access for text-to-video, image-to-video, three-image reference fusion, and video-input generation workflows. | $0.60 per generation | Model page · Docs |
| Runway Gen-4.5 | Runway-Gen-4.5-API | Runway Gen-4.5 is a high-fidelity video model focused on prompt adherence, cinematic motion, visual fidelity, and optional reference image guidance. | $0.375 per video | Model page · Docs |
| Seedance 2.0 Mini | Seedance-2.0-Mini-API | 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. | $0.05 per second | Model page · Docs |
| Wan 2.2 Fast | Wan-2.2-Fast-API | Wan 2.2 Fast provides fast text-to-video and image-to-video generation with low-cost 480p and 720p tiers for quick iteration. | $0.03 per generation | Model page · Docs |
| Wan 2.7 Video | Wan-2.7-Video-API | Wan 2.7 Video models on PoYo for text-to-video, image-to-video, reference-to-video, and edit-video workflows. | $0.06 per second | Model page · Docs |
| Model | Repository | What it does | Price from | Links |
|---|---|---|---|---|
| GPT Image 2.6 New | GPT-Image-2.6-API | Affordable GPT Image 2.6 API for text-to-image and reference image editing with OpenAI's Flare and Sunburst. | $0.0085 per image | Model page · Docs |
| GPT Image 2 | GPT-Image-2-API | OpenAI's premium image generation family for text-to-image creation and single-image editing with simple prompt-driven controls. | $0.01 per generation | Model page · Docs |
| Nano Banana Pro | Nano-Banana-Pro-API | Google's advanced Gemini 3 Pro image model featuring 4K resolution, enhanced reasoning, real-time data integration, and multi-image composition capabilities. | $0.09 per generation | Model page · Docs |
| Nano Banana 2 (legacy ids) | Nano-Banana-2-API | Legacy nano-banana-2 / nano-banana-2-edit model IDs plus Nano Banana 2 Lite for low-cost drafts. | $0.025 per generation | Model page · Docs |
| Seedream 5.5 New | Seedream-5.5-API | ByteDance Seed's image model for text-to-image, multi-reference editing with up to 10 images, native transparent PNGs, and layer decomposition into a base image plus up to 99... | $0.02 per image | Model page · Docs |
| MiniMax H3 Image New | MiniMax-H3-Image-API | MiniMax's open-weight image model for text-to-image and editing with up to 16 reference images, 1K, 2K or 4K output, custom sizes up to 20 megapixels, and sharp in-image text. | $0.016 per image | Model page · Docs |
| Kling Image 4.0 New | Kling-Image-4.0-API | Kling AI's image model for native 8K text-to-image, editing with up to 10 references and multi-angle elements, image sets of up to 10, and long webpage or ecommerce page designs. | $0.05 per image | Model page · Docs |
| MAI Image 2.7 New | MAI-Image-2.7-API | Microsoft's MAI Image 2.7 and MAI Image 2.7 Flash for text-to-image and editing with up to 5 reference images, transparent backgrounds, and custom sizes up to 4,194,304 pixels. | $1.40 per 1M input tokens | Model page · Docs |
| Flux Kontext | Flux-Kontext-API | Black Forest Labs' in-context image generation and editing family for scene-preserving edits, text replacement, and prompt-driven visual changes. | $0.04 per generation | Model page · Docs |
| FLUX.2 | FLUX.2-API | Black Forest Labs' production-grade model combining 4MP image generation and editing with multi-reference support, precise typography, and hex color control. | $0.03 per generation | Model page · Docs |
| Grok Imagine Image | Grok-Imagine-Image-API | xAI's Aurora-powered Grok Imagine image generation with Fun, Normal, and Spicy creative modes. | $0.03 per image | Model page · Docs |
| Grok Imagine Image Quality | Grok-Imagine-Image-Quality-API | xAI's higher-fidelity Grok Imagine image model for polished text-to-image generation and reference-based image editing. | $0.04 per image | Model page · Docs |
| Nano Banana 2 Lite | Nano-Banana-2-Lite-API | 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... | $0.025 per generation | Model page · Docs |
| Qwen Image 3.0 | Qwen-Image-3-API | Alibaba's third-generation image model for long prompts, information-dense layouts, fine text rendering, multilingual visuals, and knowledge-rich image generation. | $0.024 per image | Model page · Docs |
| Seedream 4.5 | Seedream-4.5-API | ByteDance's unified 4K image generation and editing model with professional-grade text rendering and commercial photography quality. | $0.025 per generation | Model page · Docs |
| Seedream 5.0 Lite | Seedream-5.0-Lite-API | ByteDance's efficient multimodal image model with native 2K/3K resolution, deep thinking, bilingual text rendering, and smart editing. | $0.025 per generation | Model page · Docs |
| Seedream 5.0 Pro | Seedream-5.0-Pro-API | ByteDance's flagship image model for precise prompt following, dense layouts, multilingual text rendering, and region-precise editing. | $0.075 per image | Model page · Docs |
| Model | Repository | What it does | Price from | Links |
|---|---|---|---|---|
| Gemini 4 Carbon New | Gemini-4-Carbon-API | Google's strongest Gemini 4 reasoning model for long-horizon agentic coding, knowledge work, science, and cyber defense with 1M context and 64K output at $1.60 input and $8.00... | $1.60 per 1M input tokens | Model page · Docs |
| GPT-6.2 Astra / Sol New | GPT-6.2-API | OpenAI's GPT-6.2 Astra (frontier) and GPT-6.2 Sol (efficient) through Chat Completions and Responses, with streaming, reasoning effort, and OpenAI SDK examples. | $1.60 per 1M input tokens | Model page · Docs |
| Claude 4.5 | Claude-4.5-API | Anthropic's Claude 4.5 series model — Opus, Sonnet & Haiku | $0.80 per 1M input tokens | Model page · Docs |
| Claude Opus 4.8 | Claude-Opus-4.8-API | Claude Opus 4.8 supports long-context chat, agentic coding, professional reasoning, high-output workflows, 1M context, and up to 128K output. | $4.00 per 1M input tokens | Model page · Docs |
| Claude Opus 5 | Claude-Opus-5-API | Anthropic's flagship agentic model for advanced coding, long-horizon execution, computer use, deep research, and professional knowledge work. | $2.00 per 1M input tokens | Model page · Docs |
| Claude Sonnet 5 | Claude-Sonnet-5-API | Claude Sonnet 5 API access for agentic coding, long-running agents, browser and computer use, professional workflows, 1M context, and up to 128K output. | $0.85 per 1M input tokens | Model page · Docs |
| DeepSeek V4 | DeepSeek-V4-API | DeepSeek V4 Flash is a fast, economical DeepSeek V4 API model with 1M-context chat, 284B total parameters, and 13B active parameters. | $0.112 per 1M input tokens | Model page · Docs |
| Gemini 3 | Gemini-3-API | Google's Gemini 3 series model — Flash Preview & Pro Preview | $0.40 per 1M input tokens | Model page · Docs |
| Gemini 3.5 Flash | Gemini-3.5-Flash-API | Gemini 3.5 Flash API access for chat, coding, reasoning, and production agent workflows. | $0.90 per 1M input tokens | Model page · Docs |
| GPT-5.5 | GPT-5.5-API | GPT-5.5 API access for chat, coding, reasoning, and production agent workflows. | $3.00 per 1M input tokens | Model page · Docs |
| GPT-5.6 | GPT-5.6-API | GPT-5.6 API access for Sol, Terra, and Luna through the Responses API, from high-throughput automation to frontier coding and agent workflows. | $0.056 per 1M input tokens | Model page · Docs |
| Kimi K3 | Kimi-K3-API | 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. | $2.28 per 1M input tokens | Model page · Docs |
| Model | Repository | What it does | Price from | Links |
|---|---|---|---|---|
| ElevenLabs Music | ElevenLabs-Music-API | Generate studio-grade AI music with prompt-based songs, instrumental mode, structured composition plans, section timing, multilingual vocals, and flexible audio output formats. | $0.64 per started minute | Model page · Docs |
| ElevenLabs V3 TTS | ElevenLabs-V3-TTS-API | Generate expressive text-to-speech audio with ElevenLabs V3 TTS. | $0.08 per 1000 characters | Model page · Docs |
| Gemini 3.1 Flash TTS | Gemini-3.1-Flash-TTS-API | Generate expressive multilingual speech with Gemini 3.1 Flash TTS. | $0.12 per 1000 characters | Model page · Docs |
| MiniMax Music 2.6 | MiniMax-Music-2.6-API | Generate complete songs from style prompts and lyrics with MiniMax Music 2.6. | $0.10 per generation | Model page · Docs |
| Model | Repository | What it does | Price from | Links |
|---|---|---|---|---|
| Hunyuan 3D v3.1 | Hunyuan-3D-3.1-API | Hunyuan 3D v3.1 generation with Pro and Rapid text-to-3D and image-to-3D models. | $0.18 per generation | Model page · Docs |
| Meshy 6 | Meshy-6-API | Meshy 6 3D generation with text-to-3D, image-to-3D, and multi-image-to-3D workflows. | $0.30 per generation | Model page · Docs |
| Tripo3D H3.1 | Tripo3D-H3.1-API | High-detail Tripo3D H3.1 generation with text-to-3D, image-to-3D, and multiview-to-3D workflows. | $0.075 per generation | Model page · Docs |
| Library | What it contains | Links |
|---|---|---|
| awesome-seedance-2.5-flash-api-prompts | 30 curated Seedance 2.5 Flash API prompts with exact request JSON, duration, resolution, and cost: product ads, cinematic shots, references, first-last frame, camera moves, UGC. | Model page · Docs |
| Tool | What it does |
|---|---|
| poyo-devtools | Official PoYo CLI (poyo), stdio MCP bridge to the hosted PoYo MCP server, and Agent Skill, with model schemas and pricing from the PoYo Capability Catalog. npm: @poyoapi/cli, @poyoapi/mcp, @poyoapi/core. |
| poyo-n8n | Official PoYo community node for n8n multimodal workflows. |
| poyo-comfyui | Official PoYo custom nodes for ComfyUI multimodal workflows. |
| poyo-examples | Cross-model examples for building with PoYo AI APIs. |
| App | What it is |
|---|---|
| open-generative-studio | Open-source generative media studio built on the PoYo API. |
Recent PoYo models that do not have a dedicated example repository yet. They use the same request pattern as the repositories above.
| Model | Category | Price from | Links |
|---|---|---|---|
| FLUX 3 Max | Video | $0.17 per second | Model page · Docs |
| Gemini Omni 1.1 Flash | Video | $0.225 per generation | Model page · Docs |
| Gemini Omni 1.2 Flash | Video | $0.0273 per second | Model page · Docs |
| Kling 4.0 Flash | Video | $0.094 per second | Model page · Docs |
| MiniMax H3 Max | Video | $0.05 per second | Model page · Docs |
| MiniMax H3 Max Turbo | Video | $0.025 per second | Model page · Docs |
| OmniHuman 2.0 | Video | $0.105 per second | Model page · Docs |
| PixVerse V6 Max | Video | $0.024 per second | Model page · Docs |
| Vidu Q4 | Video | $0.045 per second | Model page · Docs |
| Wan 3.0 | Video | $0.05 per billed second | Model page · Docs |
| Wan 3.0 Video Prime | Video | $0.068 per billed second | Model page · Docs |
| FLUX 3 Image Klein | Image | $0.009 per image | Model page · Docs |
| GPT Image 2.5 | Image | $0.0085 per image | Model page · Docs |
| Grok Imagine Image 2.0 | Image | $0.04 per image | Model page · Docs |
| Ideogram 4.5 | Image | $0.008 per image | Model page · Docs |
| Ideogram Vector 1.0 | Image | $0.10 per image | Model page · Docs |
| MAI Image 2.6 | Image | $1.40 per 1M input tokens | Model page · Docs |
| Nano Banana 2.1 | Image | $0.02 per image | Model page · Docs |
| Qwen Image 2.1 | Image | $0.03 per generation | Model page · Docs |
| Seedream 5.0 Flash | Image | $0.02 per image | Model page · Docs |
| Claude Fable 5.1 | Chat and LLM | $8.00 per 1M input tokens | Model page · Docs |
| Claude Fable 5.2 | Chat and LLM | $6.40 per 1M input tokens | Model page · Docs |
| Claude Haiku 5.5 | Chat and LLM | $0.08 per 1M input tokens | Model page · Docs |
| Claude Opus 5.5 | Chat and LLM | $3.20 per 1M input tokens | Model page · Docs |
| Claude Sonnet 5.5 | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| DeepSeek V4.1 Flash | Chat and LLM | $0.30 per 1M input tokens | Model page · Docs |
| GPT-6 Astra | Chat and LLM | $8.00 per 1M input tokens | Model page · Docs |
| GPT-6 Luna | Chat and LLM | $0.08 per 1M input tokens | Model page · Docs |
| GPT-6 Sol | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| GPT-6.1 Sol | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| GPT-6.1 Terra | Chat and LLM | $0.80 per 1M input tokens | Model page · Docs |
| Gemini 3.7 Flash | Chat and LLM | $0.60 per 1M input tokens | Model page · Docs |
| Gemini 3.8 Flash | Chat and LLM | $0.60 per 1M input tokens | Model page · Docs |
| Gemini 4 Argon | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| Grok 4.6 | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| Grok 4.7 | Chat and LLM | $1.60 per 1M input tokens | Model page · Docs |
| Eleven v4 | Music and speech | $0.08 per 1000 characters | Model page · Docs |
| Eleven v4 Turbo | Music and speech | $0.04 per 1000 characters | Model page · Docs |
| Gemini 3.8 Flash Lite TTS | Music and speech | $0.03 per 1000 characters | Model page · Docs |
| Gemini 3.8 Flash TTS | Music and speech | $0.045 per 1000 characters | Model page · Docs |
| Meshy 7.1 | 3D | $0.80 per generation | Model page · Docs |
- Create an API key in the PoYo dashboard.
- Media models are asynchronous:
POST https://api.poyo.ai/api/generate/submitwithmodelandinput, then pollGET https://api.poyo.ai/api/generate/status/{task_id}or pass acallback_url. - Chat models answer directly through
POST /v1/chat/completions,/v1/responses,/v1/messages, or Gemini Native/v1beta/models/{model}:generateContent, depending on the model.
curl -X POST "https://api.poyo.ai/api/generate/submit" \
-H "Authorization: Bearer $POYO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "seedance-2.5-flash", "input": {"prompt": "A paper boat drifts down a rain-filled street gutter at dusk.", "duration": 4, "resolution": "480p"}}'This list is generated by scripts/build_index.py from PoYo's model catalog. Open an issue or pull request to suggest a model repository, a prompt library, or a community project built on PoYo.
MIT