From 0a3acc77b8f1a71fac51f977db84a952b49d2eb7 Mon Sep 17 00:00:00 2001 From: jiehao71727 Date: Sun, 9 Aug 2026 21:55:13 +0800 Subject: [PATCH] Add current model API quickstarts --- CHANGELOG.md | 4 ++++ README.md | 35 ++++++++++++++++++++++++----------- curl/README.md | 12 ++++++------ curl/chat/claude-opus-5.md | 20 ++++++++++++++++++++ curl/chat/gpt-5-6.md | 18 ++++++++++++++++++ curl/chat/kimi-k3.md | 21 +++++++++++++++++++++ curl/image/qwen-image-3.md | 23 +++++++++++++++++++++++ curl/video/flux-3.md | 22 ++++++++++++++++++++++ curl/video/hailuo-03.md | 21 +++++++++++++++++++++ curl/video/seedance-2-5.md | 22 ++++++++++++++++++++++ 10 files changed, 181 insertions(+), 17 deletions(-) create mode 100644 curl/chat/claude-opus-5.md create mode 100644 curl/chat/gpt-5-6.md create mode 100644 curl/chat/kimi-k3.md create mode 100644 curl/image/qwen-image-3.md create mode 100644 curl/video/flux-3.md create mode 100644 curl/video/hailuo-03.md create mode 100644 curl/video/seedance-2-5.md diff --git a/CHANGELOG.md b/CHANGELOG.md index 640534d..28435db 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,8 @@ All notable public example changes are recorded here. ### Added +- Runnable focused repositories and cURL quickstarts for Seedance 2.5, MiniMax H3, FLUX 3 Video, Qwen Image 3, Kimi K3, GPT-5.6, and Claude Opus 5. +- Exact production model IDs, current pricing snapshots, request limits, and GitHub Actions checks for both 2026 model batches. - Focused `seedream-5-0-pro-api` repository for structured image generation, reference-guided editing, polling, and webhook workflows. - Focused model repository links for Claude Sonnet 5, Nano Banana 2 Lite, Grok Imagine Image, Omni Flash, and Kling 3.0 Turbo. - cURL quickstarts for current high-interest models: `claude-sonnet-5`, `nano-banana-2-lite`, and `omni-flash`. @@ -17,6 +19,8 @@ All notable public example changes are recorded here. ### Changed +- Seedance 2.5 is now documented as a live API integration; stale coming-soon and 4K claims were removed. +- README and cURL indexes now prioritize the two latest model batches for Google, AI answer engines, and GitHub discovery. - README and cURL indexes now surface Seedream 5.0 Pro as the current image-model quickstart. - README, cURL index, and GitHub organization profile now surface Claude Sonnet 5, Nano Banana 2 Lite, and Omni Flash entry points. - README and cURL index now surface recent model quickstarts as follow-up links for new model posts. diff --git a/README.md b/README.md index 34a4203..b0a29e9 100644 --- a/README.md +++ b/README.md @@ -53,6 +53,13 @@ These examples match the latest model and repo maintenance work. Use the focused | Model | Best for | Start here | | --- | --- | --- | +| `seedance-2.5` | 4-30 second controllable video with up to 50 multimodal references | [PoyoAPI/seedance-2-5-api](https://github.com/PoyoAPI/seedance-2-5-api) ([model page](https://poyo.ai/models/seedance-2-5)) | +| `hailuo-03` (MiniMax H3) | 2K video, first/last frames, and reference-driven generation | [PoyoAPI/minimax-h3-api](https://github.com/PoyoAPI/minimax-h3-api) ([model page](https://poyo.ai/models/minimax-h3)) | +| `flux-3/text-to-video` | FLUX 3 generation, extension, and keyframe-directed video | [PoyoAPI/flux-3-video-api](https://github.com/PoyoAPI/flux-3-video-api) ([model page](https://poyo.ai/models/flux-3)) | +| `qwen-image-3` | 1K/2K image generation and multi-image editing | [PoyoAPI/qwen-image-3-api](https://github.com/PoyoAPI/qwen-image-3-api) ([model page](https://poyo.ai/models/qwen-image-3)) | +| `kimi-k3` | Long-context chat, coding, and agent planning | [PoyoAPI/kimi-k3-api](https://github.com/PoyoAPI/kimi-k3-api) ([model page](https://poyo.ai/models/kimi-k3)) | +| `gpt-5-6-luna` / `terra` / `sol` | Responses API workloads across three capability and cost tiers | [PoyoAPI/gpt-5-6-api](https://github.com/PoyoAPI/gpt-5-6-api) ([model page](https://poyo.ai/models/gpt-5-6)) | +| `claude-opus-5` | Complex reasoning, research, and architecture review | [PoyoAPI/claude-opus-5-api](https://github.com/PoyoAPI/claude-opus-5-api) ([model page](https://poyo.ai/models/claude-opus-5)) | | `seedream-5.0-pro` | Dense layouts, multilingual text, product visuals, and precise image edits | [PoyoAPI/seedream-5-0-pro-api](https://github.com/PoyoAPI/seedream-5-0-pro-api) ([model page](https://poyo.ai/models/seedream-5-0-pro)) | | `seedance-2-mini` | Lower-cost ByteDance video drafts and fast direction tests | [PoyoAPI/seedance-2-mini-api](https://github.com/PoyoAPI/seedance-2-mini-api) ([model page](https://poyo.ai/models/seedance-2-mini)) | | `wan2.2-text-to-video-fast` | Low-cost Wan text-to-video and guided image-to-video drafts | [PoyoAPI/wan-2-2-fast-api](https://github.com/PoyoAPI/wan-2-2-fast-api) ([model page](https://poyo.ai/models/wan-2-2-fast)) | @@ -83,10 +90,10 @@ PoYo uses credit-based pricing, and failed generation tasks are not charged cred | Goal | Start here | | --- | --- | -| Generate or edit images | [Flux Kontext repo](https://github.com/PoyoAPI/flux-kontext-api), [`curl/image/nano-banana-2-lite.md`](curl/image/nano-banana-2-lite.md), [`curl/image/gpt-image-2.md`](curl/image/gpt-image-2.md), [`curl/image/grok-imagine-image.md`](curl/image/grok-imagine-image.md), [`node/gpt-image-2/`](node/gpt-image-2/), [`python/gpt-image-2/`](python/gpt-image-2/) | -| Generate short videos | [Seedance 2.0 Mini repo](https://github.com/PoyoAPI/seedance-2-mini-api), [Wan 2.2 Fast repo](https://github.com/PoyoAPI/wan-2-2-fast-api), [Hailuo 2.3 repo](https://github.com/PoyoAPI/hailuo-2-3-api), [Kling Avatar 2.0 repo](https://github.com/PoyoAPI/kling-avatar-2-0-api), [Veo 3.1 Official repo](https://github.com/PoyoAPI/veo-3-1-official-api), [Grok Imagine Video 1.5 repo](https://github.com/PoyoAPI/grok-imagine-video-1-5-api), [`curl/video/omni-flash.md`](curl/video/omni-flash.md), [`curl/video/seedance-2-mini.md`](curl/video/seedance-2-mini.md), [`curl/video/kling-3-0-turbo.md`](curl/video/kling-3-0-turbo.md), [`curl/video/seedance-2.md`](curl/video/seedance-2.md), [`node/seedance-2/`](node/seedance-2/), [`python/seedance-2/`](python/seedance-2/) | +| Generate or edit images | [Qwen Image 3 repo](https://github.com/PoyoAPI/qwen-image-3-api), [Flux Kontext repo](https://github.com/PoyoAPI/flux-kontext-api), [`curl/image/qwen-image-3.md`](curl/image/qwen-image-3.md), [`curl/image/gpt-image-2.md`](curl/image/gpt-image-2.md) | +| Generate short videos | [Seedance 2.5 repo](https://github.com/PoyoAPI/seedance-2-5-api), [MiniMax H3 repo](https://github.com/PoyoAPI/minimax-h3-api), [FLUX 3 Video repo](https://github.com/PoyoAPI/flux-3-video-api), [`curl/video/seedance-2-5.md`](curl/video/seedance-2-5.md), [`curl/video/hailuo-03.md`](curl/video/hailuo-03.md), [`curl/video/flux-3.md`](curl/video/flux-3.md) | | Try a high-interest video quickstart | [`curl/video/sora-2.md`](curl/video/sora-2.md) | -| Build chat completions | [Gemini 3 repo](https://github.com/PoyoAPI/gemini-3-api), [DeepSeek V4 repo](https://github.com/PoyoAPI/deepseek-v4-api), [`curl/chat/claude-sonnet-5.md`](curl/chat/claude-sonnet-5.md), [`curl/chat/gpt-5.2.md`](curl/chat/gpt-5.2.md), [`node/gpt-5.2/`](node/gpt-5.2/), [`python/gpt-5.2/`](python/gpt-5.2/) | +| Build chat and agent workflows | [Kimi K3 repo](https://github.com/PoyoAPI/kimi-k3-api), [GPT-5.6 repo](https://github.com/PoyoAPI/gpt-5-6-api), [Claude Opus 5 repo](https://github.com/PoyoAPI/claude-opus-5-api), [`curl/chat/kimi-k3.md`](curl/chat/kimi-k3.md), [`curl/chat/gpt-5-6.md`](curl/chat/gpt-5-6.md), [`curl/chat/claude-opus-5.md`](curl/chat/claude-opus-5.md) | | Generate speech or music | [ElevenLabs v3 TTS repo](https://github.com/PoyoAPI/elevenlabs-v3-tts-api), [MiniMax Music 2.6 repo](https://github.com/PoyoAPI/minimax-music-2-6-api), [`curl/music/generate-music.md`](curl/music/generate-music.md) | | Keep API keys out of browser code | [`nextjs/gpt-image-2-route/`](nextjs/gpt-image-2-route/) | | Receive production callbacks | [`webhooks/`](webhooks/) | @@ -120,6 +127,13 @@ PoYo uses credit-based pricing, and failed generation tasks are not charged cred | Model | Modality | Workflow | cURL | Node.js | Python | Next.js | Webhook | Sample Output | | --- | --- | --- | --- | --- | --- | --- | --- | --- | +| `seedance-2.5` | Video | Async task | [cURL](curl/video/seedance-2-5.md) | [Focused repo](https://github.com/PoyoAPI/seedance-2-5-api) | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/seedance-2-5) | +| `hailuo-03` | Video | Async task | [cURL](curl/video/hailuo-03.md) | [Focused repo](https://github.com/PoyoAPI/minimax-h3-api) | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/minimax-h3) | +| `flux-3/text-to-video` | Video | Async task | [cURL](curl/video/flux-3.md) | [Focused repo](https://github.com/PoyoAPI/flux-3-video-api) | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/flux-3) | +| `qwen-image-3` | Image | Async task | [cURL](curl/image/qwen-image-3.md) | [Focused repo](https://github.com/PoyoAPI/qwen-image-3-api) | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/qwen-image-3) | +| `kimi-k3` | Chat | Sync response | [cURL](curl/chat/kimi-k3.md) | [Focused repo](https://github.com/PoyoAPI/kimi-k3-api) | - | - | - | [PoYo model page](https://poyo.ai/models/kimi-k3) | +| `gpt-5-6-luna` | Chat | Responses API | [cURL](curl/chat/gpt-5-6.md) | [Focused repo](https://github.com/PoyoAPI/gpt-5-6-api) | - | - | - | [PoYo model page](https://poyo.ai/models/gpt-5-6) | +| `claude-opus-5` | Chat | Messages API | [cURL](curl/chat/claude-opus-5.md) | [Focused repo](https://github.com/PoyoAPI/claude-opus-5-api) | - | - | - | [PoYo model page](https://poyo.ai/models/claude-opus-5) | | `claude-sonnet-5` | Chat | Sync response | [cURL](curl/chat/claude-sonnet-5.md) | - | - | - | - | [PoYo model page](https://poyo.ai/models/claude-sonnet-5) | | `nano-banana-2-lite` | Image | Async task | [cURL](curl/image/nano-banana-2-lite.md) | - | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/nano-banana-2-lite) | | `omni-flash` | Video | Async task | [cURL](curl/video/omni-flash.md) | - | - | - | [Receivers](webhooks/) | [PoYo model page](https://poyo.ai/models/omni-flash) | @@ -139,6 +153,9 @@ Use this repo as the main integration hub. If you are searching for a single mod | Category | Model repo | Best for | | --- | --- | --- | +| Chat | [PoyoAPI/kimi-k3-api](https://github.com/PoyoAPI/kimi-k3-api) ([model page](https://poyo.ai/models/kimi-k3)) | Kimi K3 long-context chat, coding, and agent workflows | +| Chat | [PoyoAPI/gpt-5-6-api](https://github.com/PoyoAPI/gpt-5-6-api) ([model page](https://poyo.ai/models/gpt-5-6)) | GPT-5.6 Luna, Terra, and Sol Responses API workflows | +| Chat | [PoyoAPI/claude-opus-5-api](https://github.com/PoyoAPI/claude-opus-5-api) ([model page](https://poyo.ai/models/claude-opus-5)) | Claude Opus 5 reasoning, research, and agent workflows | | Chat | [PoyoAPI/gpt-5-5-api](https://github.com/PoyoAPI/gpt-5-5-api) ([model page](https://poyo.ai/models/gpt-5-5)) | GPT-5.5 chat, coding, and agent workflows | | Chat | [PoyoAPI/claude-opus-4-8-api](https://github.com/PoyoAPI/claude-opus-4-8-api) ([model page](https://poyo.ai/models/claude-opus-4-8)) | Claude Opus 4.8 reasoning, coding, and agent workflows | | Chat | [PoyoAPI/gemini-3-5-flash-api](https://github.com/PoyoAPI/gemini-3-5-flash-api) ([model page](https://poyo.ai/models/gemini-3-5-flash)) | Gemini 3.5 Flash fast assistant and routing workflows | @@ -146,6 +163,7 @@ Use this repo as the main integration hub. If you are searching for a single mod | Chat | [PoyoAPI/gemini-3-api](https://github.com/PoyoAPI/gemini-3-api) | Gemini 3 chat, coding, and agent workflows | | Chat | [PoyoAPI/deepseek-v4-api](https://github.com/PoyoAPI/deepseek-v4-api) | DeepSeek V4 Flash and Pro cost-aware assistant workflows | | Chat | [PoyoAPI/claude-sonnet-5-api](https://github.com/PoyoAPI/claude-sonnet-5-api) | Claude Sonnet 5 chat, coding, and agentic workflows | +| Image | [PoyoAPI/qwen-image-3-api](https://github.com/PoyoAPI/qwen-image-3-api) ([model page](https://poyo.ai/models/qwen-image-3)) | Qwen Image 3 generation and multi-image editing | | Image | [PoyoAPI/grok-imagine-image-quality-api](https://github.com/PoyoAPI/grok-imagine-image-quality-api) ([model page](https://poyo.ai/models/grok-imagine-image-quality)) | Grok Imagine Image Quality photorealistic image drafts | | Image | [PoyoAPI/flux-2-api](https://github.com/PoyoAPI/flux-2-api) ([model page](https://poyo.ai/models/flux-2)) | FLUX.2 pro and flex image generation and editing workflows | | Image | [PoyoAPI/flux-kontext-api](https://github.com/PoyoAPI/flux-kontext-api) ([model page](https://poyo.ai/models/flux-kontext)) | Flux Kontext scene-preserving image generation and editing workflows | @@ -157,6 +175,9 @@ Use this repo as the main integration hub. If you are searching for a single mod | Image | [PoyoAPI/nano-banana-2-lite-api](https://github.com/PoyoAPI/nano-banana-2-lite-api) | Nano Banana 2 Lite lower-cost image drafts | | Image | [PoyoAPI/nano-banana-2-api](https://github.com/PoyoAPI/nano-banana-2-api) | Nano Banana 2 generation and image edits | | Image | [PoyoAPI/nano-banana-pro-api](https://github.com/PoyoAPI/nano-banana-pro-api) | Nano Banana Pro higher-detail image workflows | +| Video | [PoyoAPI/seedance-2-5-api](https://github.com/PoyoAPI/seedance-2-5-api) ([model page](https://poyo.ai/models/seedance-2-5)) | Seedance 2.5 4-30 second multimodal-reference video workflows | +| Video | [PoyoAPI/minimax-h3-api](https://github.com/PoyoAPI/minimax-h3-api) ([model page](https://poyo.ai/models/minimax-h3)) | MiniMax H3 / Hailuo 03 2K video workflows | +| Video | [PoyoAPI/flux-3-video-api](https://github.com/PoyoAPI/flux-3-video-api) ([model page](https://poyo.ai/models/flux-3)) | FLUX 3 generation, extension, and keyframe video workflows | | Video | [PoyoAPI/kling-3-api](https://github.com/PoyoAPI/kling-3-api) ([model page](https://poyo.ai/models/kling-3-api)) | Kling 3.0 standard, pro, and 4K video workflows | | Video | [PoyoAPI/seedance-2-mini-api](https://github.com/PoyoAPI/seedance-2-mini-api) ([model page](https://poyo.ai/models/seedance-2-mini)) | Seedance 2.0 Mini lower-cost video draft workflows | | Video | [PoyoAPI/wan-2-2-fast-api](https://github.com/PoyoAPI/wan-2-2-fast-api) ([model page](https://poyo.ai/models/wan-2-2-fast)) | Wan 2.2 Fast text-to-video and image-to-video draft loops | @@ -180,14 +201,6 @@ Use this repo as the main integration hub. If you are searching for a single mod | 3D | [PoyoAPI/tripo-h31-3d-api](https://github.com/PoyoAPI/tripo-h31-3d-api) ([model page](https://poyo.ai/models/tripo-h31-3d)) | Tripo3D H3.1 high-detail text, image, and multiview 3D asset workflows | | 3D | [PoyoAPI/meshy-6-3d-api](https://github.com/PoyoAPI/meshy-6-3d-api) ([model page](https://poyo.ai/models/meshy-6-3d)) | Meshy 6 text-to-3D, image-to-3D, and multi-image-to-3D workflows | -## Coming Soon / Watchlist - -These repos track high-interest models before runnable API examples are available. They should not be treated as live submit examples. - -| Model | Status | Links | Notes | -| --- | --- | --- | --- | -| Seedance 2.5 | Coming soon | [Model page](https://poyo.ai/models/seedance-2-5), [GitHub repo](https://github.com/PoyoAPI/seedance-2-5-api) | Tracks expected Seedance 2.5 workflows: 30-second single-segment clips, up to 4K-oriented output, up to 50 multimodal references, region-level editing, and longer-scene consistency. | - ## Unified Async Flow Most media and 3D examples use the same backend pattern. diff --git a/curl/README.md b/curl/README.md index 8681257..3b2495b 100644 --- a/curl/README.md +++ b/curl/README.md @@ -4,11 +4,11 @@ Use these examples when you want the smallest possible backend-safe API call. | Category | Example | | --- | --- | -| Image | [`image/nano-banana-2-lite.md`](image/nano-banana-2-lite.md), [`image/gpt-image-2.md`](image/gpt-image-2.md), [`image/grok-imagine-image.md`](image/grok-imagine-image.md) | -| Video | [`video/omni-flash.md`](video/omni-flash.md), [`video/seedance-2-mini.md`](video/seedance-2-mini.md), [`video/kling-3-0-turbo.md`](video/kling-3-0-turbo.md), [`video/seedance-2.md`](video/seedance-2.md), [`video/sora-2.md`](video/sora-2.md) | +| Image | [`image/qwen-image-3.md`](image/qwen-image-3.md), [`image/nano-banana-2-lite.md`](image/nano-banana-2-lite.md), [`image/gpt-image-2.md`](image/gpt-image-2.md), [`image/grok-imagine-image.md`](image/grok-imagine-image.md) | +| Video | [`video/seedance-2-5.md`](video/seedance-2-5.md), [`video/hailuo-03.md`](video/hailuo-03.md), [`video/flux-3.md`](video/flux-3.md), [`video/omni-flash.md`](video/omni-flash.md), [`video/seedance-2-mini.md`](video/seedance-2-mini.md) | | Music | [`music/generate-music.md`](music/generate-music.md) | | 3D | [`3d/meshy-6-text-to-3d.md`](3d/meshy-6-text-to-3d.md) | -| Chat | [`chat/claude-sonnet-5.md`](chat/claude-sonnet-5.md), [`chat/gpt-5.2.md`](chat/gpt-5.2.md) | +| Chat | [`chat/kimi-k3.md`](chat/kimi-k3.md), [`chat/gpt-5-6.md`](chat/gpt-5-6.md), [`chat/claude-opus-5.md`](chat/claude-opus-5.md), [`chat/claude-sonnet-5.md`](chat/claude-sonnet-5.md) | ## Focused Model Repos @@ -16,9 +16,9 @@ Use these standalone repos when you want the smallest project for one current mo | Category | Repository | | --- | --- | -| Chat | [GPT-5.5 API](https://github.com/PoyoAPI/gpt-5-5-api) ([model](https://poyo.ai/models/gpt-5-5)), [Claude Opus 4.8 API](https://github.com/PoyoAPI/claude-opus-4-8-api) ([model](https://poyo.ai/models/claude-opus-4-8)), [Gemini 3.5 Flash API](https://github.com/PoyoAPI/gemini-3-5-flash-api) ([model](https://poyo.ai/models/gemini-3-5-flash)), [Claude 4.5 API](https://github.com/PoyoAPI/claude-4-5-api) ([model](https://poyo.ai/models/claude-4-5-api)), [Gemini 3 API](https://github.com/PoyoAPI/gemini-3-api), [DeepSeek V4 API](https://github.com/PoyoAPI/deepseek-v4-api) | -| Image | [Seedream 5.0 Pro API](https://github.com/PoyoAPI/seedream-5-0-pro-api) ([model](https://poyo.ai/models/seedream-5-0-pro)), [Flux Kontext API](https://github.com/PoyoAPI/flux-kontext-api) ([model](https://poyo.ai/models/flux-kontext)), [Grok Imagine Image Quality API](https://github.com/PoyoAPI/grok-imagine-image-quality-api) ([model](https://poyo.ai/models/grok-imagine-image-quality)), [FLUX.2 API](https://github.com/PoyoAPI/flux-2-api) ([model](https://poyo.ai/models/flux-2)), [Seedream 5.0 Lite API](https://github.com/PoyoAPI/seedream-5-0-lite-api) ([model](https://poyo.ai/models/seedream-5-0-lite-api)), [Seedream 4.5 API](https://github.com/PoyoAPI/seedream-4-5-api) ([model](https://poyo.ai/models/seedream-4-5-api)) | -| Video | [Seedance 2.0 Mini API](https://github.com/PoyoAPI/seedance-2-mini-api) ([model](https://poyo.ai/models/seedance-2-mini)), [Wan 2.2 Fast API](https://github.com/PoyoAPI/wan-2-2-fast-api) ([model](https://poyo.ai/models/wan-2-2-fast)), [Hailuo 2.3 API](https://github.com/PoyoAPI/hailuo-2-3-api) ([model](https://poyo.ai/models/hailuo-2-3)), [Kling Avatar 2.0 API](https://github.com/PoyoAPI/kling-avatar-2-0-api) ([model](https://poyo.ai/models/kling-avatar-2-0)), [Kling 3.0 API](https://github.com/PoyoAPI/kling-3-api) ([model](https://poyo.ai/models/kling-3-api)), [Runway Gen-4.5 API](https://github.com/PoyoAPI/runway-gen-4-5-api) ([model](https://poyo.ai/models/runway-gen-4-5)), [Kling O3 API](https://github.com/PoyoAPI/kling-o3-api) ([model](https://poyo.ai/models/kling-o3-api)), [Wan 2.7 Video API](https://github.com/PoyoAPI/wan-2-7-video-api) ([model](https://poyo.ai/models/wan-2-7-video)), [Veo 3.1 Official API](https://github.com/PoyoAPI/veo-3-1-official-api), [Grok Imagine Video 1.5 API](https://github.com/PoyoAPI/grok-imagine-video-1-5-api) | +| Chat | [Kimi K3 API](https://github.com/PoyoAPI/kimi-k3-api), [GPT-5.6 API](https://github.com/PoyoAPI/gpt-5-6-api), [Claude Opus 5 API](https://github.com/PoyoAPI/claude-opus-5-api), [GPT-5.5 API](https://github.com/PoyoAPI/gpt-5-5-api) | +| Image | [Qwen Image 3 API](https://github.com/PoyoAPI/qwen-image-3-api), [Seedream 5.0 Pro API](https://github.com/PoyoAPI/seedream-5-0-pro-api), [Flux Kontext API](https://github.com/PoyoAPI/flux-kontext-api) | +| Video | [Seedance 2.5 API](https://github.com/PoyoAPI/seedance-2-5-api), [MiniMax H3 API](https://github.com/PoyoAPI/minimax-h3-api), [FLUX 3 Video API](https://github.com/PoyoAPI/flux-3-video-api), [Seedance 2.0 Mini API](https://github.com/PoyoAPI/seedance-2-mini-api), [Wan 2.2 Fast API](https://github.com/PoyoAPI/wan-2-2-fast-api) | | Music | [Gemini 3.1 Flash TTS API](https://github.com/PoyoAPI/gemini-3-1-flash-tts-api) ([model](https://poyo.ai/models/gemini-3-1-flash-tts)), [ElevenLabs Music API](https://github.com/PoyoAPI/elevenlabs-music-api) ([model](https://poyo.ai/models/elevenlabs-music)), [ElevenLabs v3 TTS API](https://github.com/PoyoAPI/elevenlabs-v3-tts-api), [MiniMax Music 2.6 API](https://github.com/PoyoAPI/minimax-music-2-6-api) | | 3D | [Tripo3D H3.1 API](https://github.com/PoyoAPI/tripo-h31-3d-api) ([model](https://poyo.ai/models/tripo-h31-3d)), [Hunyuan 3D 3.1 API](https://github.com/PoyoAPI/hunyuan-3d-3-1-api) ([model](https://poyo.ai/models/hunyuan-3d-3-1)), [Meshy 6 3D API](https://github.com/PoyoAPI/meshy-6-3d-api) ([model](https://poyo.ai/models/meshy-6-3d)) | diff --git a/curl/chat/claude-opus-5.md b/curl/chat/claude-opus-5.md new file mode 100644 index 0000000..63567f6 --- /dev/null +++ b/curl/chat/claude-opus-5.md @@ -0,0 +1,20 @@ +# Claude Opus 5 API cURL quickstart + +Call the Anthropic-compatible Messages endpoint with model `claude-opus-5`. + +```bash +curl -X POST "https://api.poyo.ai/v1/messages" \ + -H "x-api-key: $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "claude-opus-5", + "max_tokens": 900, + "system": "You are a rigorous research and engineering assistant.", + "messages": [ + {"role": "user", "content": "Review this canary rollout strategy and list missing safety checks."} + ] + }' +``` + +See the [Claude Opus 5 focused repository](https://github.com/PoyoAPI/claude-opus-5-api) for Node.js and production guidance. + diff --git a/curl/chat/gpt-5-6.md b/curl/chat/gpt-5-6.md new file mode 100644 index 0000000..05ed6ca --- /dev/null +++ b/curl/chat/gpt-5-6.md @@ -0,0 +1,18 @@ +# GPT-5.6 API cURL quickstart + +GPT-5.6 uses the Responses-compatible endpoint and explicit Luna, Terra, or Sol model IDs. There is no generic `gpt-5-6` alias in this integration. + +```bash +curl -X POST "https://api.poyo.ai/v1/responses" \ + -H "Authorization: Bearer $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "gpt-5-6-luna", + "instructions": "Answer as a concise senior backend engineer.", + "input": "Explain how to make webhook processing idempotent.", + "max_output_tokens": 700 + }' +``` + +See the [GPT-5.6 focused repository](https://github.com/PoyoAPI/gpt-5-6-api) for all three model IDs and their pricing tiers. + diff --git a/curl/chat/kimi-k3.md b/curl/chat/kimi-k3.md new file mode 100644 index 0000000..eb43c70 --- /dev/null +++ b/curl/chat/kimi-k3.md @@ -0,0 +1,21 @@ +# Kimi K3 API cURL quickstart + +Call the OpenAI-compatible chat endpoint with model `kimi-k3`. + +```bash +curl -X POST "https://api.poyo.ai/v1/chat/completions" \ + -H "Authorization: Bearer $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "kimi-k3", + "messages": [ + {"role": "system", "content": "You are a precise software architecture assistant."}, + {"role": "user", "content": "Design a migration checklist for splitting a monolith into three services."} + ], + "temperature": 0.2, + "max_tokens": 900 + }' +``` + +See the [Kimi K3 focused repository](https://github.com/PoyoAPI/kimi-k3-api) for Node.js and production guidance. + diff --git a/curl/image/qwen-image-3.md b/curl/image/qwen-image-3.md new file mode 100644 index 0000000..1279857 --- /dev/null +++ b/curl/image/qwen-image-3.md @@ -0,0 +1,23 @@ +# Qwen Image 3 API cURL quickstart + +Use `qwen-image-3` for standard generation or `qwen-image-3-pro` for the higher-tier model. + +```bash +curl -X POST "https://api.poyo.ai/api/generate/submit" \ + -H "Authorization: Bearer $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "qwen-image-3", + "input": { + "prompt": "Editorial travel poster of Hangzhou at dawn, crisp geometric layout", + "size": "3:2", + "resolution": "2K", + "output_format": "png", + "prompt_extend": true, + "enable_safety_checker": true + } + }' +``` + +Store `data.task_id`, then call `GET /api/generate/status/{task_id}`. See the [Qwen Image 3 focused repository](https://github.com/PoyoAPI/qwen-image-3-api) for editing inputs and pricing. + diff --git a/curl/video/flux-3.md b/curl/video/flux-3.md new file mode 100644 index 0000000..2837cd0 --- /dev/null +++ b/curl/video/flux-3.md @@ -0,0 +1,22 @@ +# FLUX 3 Video API cURL quickstart + +FLUX 3 provides separate model IDs for text, image, first/last-frame, extension, and keyframe workflows. This example starts with text-to-video. + +```bash +curl -X POST "https://api.poyo.ai/api/generate/submit" \ + -H "Authorization: Bearer $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "flux-3/text-to-video", + "input": { + "prompt": "A premium macro product shot with crisp reflections", + "duration": 5, + "resolution": "720p", + "aspect_ratio": "16:9", + "sound": true + } + }' +``` + +Store `data.task_id`, then call `GET /api/generate/status/{task_id}`. See the [FLUX 3 Video focused repository](https://github.com/PoyoAPI/flux-3-video-api) for all five workflow IDs. + diff --git a/curl/video/hailuo-03.md b/curl/video/hailuo-03.md new file mode 100644 index 0000000..4b545b3 --- /dev/null +++ b/curl/video/hailuo-03.md @@ -0,0 +1,21 @@ +# MiniMax H3 API cURL quickstart + +MiniMax H3 uses the production model ID `hailuo-03`. + +```bash +curl -X POST "https://api.poyo.ai/api/generate/submit" \ + -H "Authorization: Bearer $POYO_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "hailuo-03", + "input": { + "prompt": "A paper dragon awakens on an illustrator desk, warm morning light", + "duration": 5, + "resolution": "2K", + "aspect_ratio": "16:9" + } + }' +``` + +Store `data.task_id`, then call `GET /api/generate/status/{task_id}`. See the [MiniMax H3 focused repository](https://github.com/PoyoAPI/minimax-h3-api) for first/last-frame and reference rules. + diff --git a/curl/video/seedance-2-5.md b/curl/video/seedance-2-5.md new file mode 100644 index 0000000..da970e2 --- /dev/null +++ b/curl/video/seedance-2-5.md @@ -0,0 +1,22 @@ +# Seedance 2.5 API cURL quickstart + +Use model `seedance-2.5` for 4-30 second video generation at 480p or 720p. + +```bash +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", + "input": { + "prompt": "A cinematic tracking shot through a neon-lit night market after rain", + "duration": 8, + "resolution": "720p", + "aspect_ratio": "16:9", + "generate_audio": false + } + }' +``` + +Store `data.task_id`, then call `GET /api/generate/status/{task_id}`. See the [focused repository](https://github.com/PoyoAPI/seedance-2-5-api) for reference limits, pricing, Node.js polling, and production notes. +