{ "schemaVersion": 1, "generatedFrom": "src/model-docs/tested-models.ts and structured model MDX pages", "instructions": [ "Use summary, capability, and bestFor to select a model.", "Use availability=online for callable models; do not call coming_soon models.", "Use request for text-model fields; use input and routes for asynchronous media-model field discovery.", "Open docs or docsZh for full descriptions, examples, limits, and pricing links." ], "models": [ { "id": "851-labs/background-remover", "title": "851 Background Remover API", "category": "image", "capability": "image generation", "availability": "online", "summary": "Submit one image to separate the foreground and produce a transparent PNG. No prompt is needed for product cutouts, portraits and compositing assets.", "bestFor": [ "Product assets", "Portraits and pets" ], "docs": "https://www.hiapi.ai/docs/models/image/851-background-remover/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/851-background-remover/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_url", "type": "string", "required": true } ] }, { "id": "Nano-Banana", "title": "Nano Banana API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Nano Banana API is fast and prompt-tolerant, suited to quick creative exploration, social images, and batch ideation with one HiAPI API key.", "bestFor": [ "Fast text-to-image", "Format adaptation", "Output handoff", "Batch ideation" ], "docs": "https://www.hiapi.ai/docs/models/image/nano-banana/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/nano-banana/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "16:9", "9:16", "3:4", "4:3", "3:2", "2:3", "5:4", "4:5", "21:9" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] } ] }, { "id": "Nano-Banana-2", "title": "Nano Banana 2", "category": "image", "capability": "Image generation / editing", "availability": "online", "summary": "Nano Banana 2 is the balanced Nano Banana tier, with optional references, wider ratios, and 1K / 2K / 4K output.", "bestFor": [ "Balanced image generation", "Optional references", "Wide ratio work", "Resolution tiers" ], "docs": "https://www.hiapi.ai/docs/models/image/nano-banana-2/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/nano-banana-2/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_input", "type": "string[]", "required": false, "default": "[]" }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpg" ] } ] }, { "id": "Nano-Banana-2-Lite", "title": "Nano Banana 2 Lite API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Google Nano Banana 2 Lite: the entry tier of the Nano Banana family — low-latency 1K output at an ultra-low price, up to 10 optional reference images, 15 ratios including ultra-wide banners.", "bestFor": [ "High-volume drafts", "Optional reference remixing", "Ultra-wide banners", "Entry tier & playgrounds" ], "docs": "https://www.hiapi.ai/docs/models/image/nano-banana-2-lite/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/nano-banana-2-lite/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": false }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "auto", "enum": [ "auto", "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9", "1:4", "4:1", "1:8", "8:1" ] } ] }, { "id": "Nano-Banana-Pro", "title": "Nano Banana Pro", "category": "image", "capability": "Image generation / editing", "availability": "online", "summary": "Nano Banana Pro targets premium brand visuals, reference-based editing, and higher-resolution delivery.", "bestFor": [ "Premium product visuals", "Reference editing", "Higher-resolution delivery", "Format control" ], "docs": "https://www.hiapi.ai/docs/models/image/nano-banana-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/nano-banana-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_input", "type": "string[]", "required": false }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "16:9", "9:16", "3:4", "4:3", "3:2", "2:3", "5:4", "4:5", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpg" ] } ] }, { "id": "deepseek-v4-flash", "title": "DeepSeek V4 Flash API", "category": "text", "capability": "Text generation · Chat Completions", "availability": "online", "summary": "DeepSeek V4 Flash is the efficiency-focused model in the DeepSeek V4 family. According to DeepSeek, it has 284B total parameters with 13B activated per token, a 1M-token context window, and both thinking and non-thinking modes. HiAPI exposes it through an OpenAI-compatible Chat Completions endpoint.", "bestFor": [ "High-throughput generation", "Reasoning and coding", "Agent workflows", "Structured output" ], "docs": "https://www.hiapi.ai/docs/models/text/deepseek-v4-flash/", "docsZh": "https://www.hiapi.ai/docs/zh/models/text/deepseek-v4-flash/", "protocol": "chat-completions", "endpoint": "https://api.hiapi.ai/v1/chat/completions", "request": [ { "name": "model", "type": "string", "required": true }, { "name": "messages", "type": "array", "required": true, "children": [ { "name": "role", "type": "enum", "required": true, "enum": [ "system", "user", "assistant", "tool" ] }, { "name": "content", "type": "string", "required": true } ] }, { "name": "stream", "type": "boolean", "required": false, "default": false }, { "name": "max_tokens", "type": "integer", "required": false }, { "name": "thinking", "type": "object", "required": false, "children": [ { "name": "type", "type": "enum", "required": true, "default": "enabled", "enum": [ "enabled", "disabled" ] } ] }, { "name": "reasoning_effort", "type": "enum", "required": false, "default": "high", "enum": [ "high", "max" ] }, { "name": "response_format", "type": "object", "required": false }, { "name": "tools", "type": "array", "required": false } ] }, { "id": "deepseek-v4-flash-vision-exp", "title": "DeepSeek V4 Flash Vision Exp API", "category": "text", "capability": "text generation", "availability": "online", "summary": "DeepSeek V4 Flash Vision Exp adds image understanding to the experimental V4 Flash model. Use it for document and chart reading, visual questions, and text-and-image workflows with Responses or Chat Completions.", "bestFor": [ "Visual questions", "Application workflows" ], "docs": "https://www.hiapi.ai/docs/models/text/deepseek-v4-flash-vision-exp/", "docsZh": "https://www.hiapi.ai/docs/zh/models/text/deepseek-v4-flash-vision-exp/", "protocol": "responses", "endpoint": "https://api.hiapi.ai/v1/responses", "request": [ { "name": "model", "type": "string", "required": true, "enum": [ "deepseek-v4-flash-vision-exp" ] }, { "name": "input", "type": "string | array", "required": true }, { "name": "instructions", "type": "string", "required": false }, { "name": "store", "type": "boolean", "required": false, "default": false }, { "name": "stream", "type": "boolean", "required": false, "default": false }, { "name": "max_output_tokens", "type": "integer", "required": false }, { "name": "reasoning", "type": "object", "required": false, "children": [ { "name": "effort", "type": "enum", "required": false, "default": "high", "enum": [ "none", "low", "medium", "high" ] } ] }, { "name": "text.format", "type": "object", "required": false }, { "name": "tools", "type": "array", "required": false }, { "name": "tool_choice", "type": "string | object", "required": false } ], "textContract": { "chatCompletions": true, "nonStreaming": true }, "requestExample": { "model": "deepseek-v4-flash-vision-exp", "input": [ { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "Describe the main subject and two visible details." }, { "type": "input_image", "image_url": "https://static.hiapi.ai/example/subject-1.jpg", "detail": "low" } ] } ], "store": false, "reasoning": { "effort": "high", "VISION_EXP_DEFAULT_OUTPUT_TOKENS": 1024 }, "max_output_tokens": 1024, "stream": false } }, { "id": "deepseek-v4-pro", "title": "DeepSeek V4 Pro API", "category": "text", "capability": "Text generation · Responses + Chat Completions", "availability": "online", "summary": "DeepSeek V4 Pro 0813 is the official production release of DeepSeek’s V4 Pro model. It is designed for demanding reasoning, coding, and Agent workloads, with a 1M-token context window, up to 384K output tokens, thinking and non-thinking modes, and native Responses and Chat Completions support.", "bestFor": [ "Complex reasoning", "Coding Agents", "Long-context work", "Structured output" ], "docs": "https://www.hiapi.ai/docs/models/text/deepseek-v4-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/text/deepseek-v4-pro/", "protocol": "responses", "endpoint": "https://api.hiapi.ai/v1/responses", "request": [ { "name": "model", "type": "string", "required": true }, { "name": "input", "type": "string | array", "required": true }, { "name": "instructions", "type": "string", "required": false }, { "name": "stream", "type": "boolean", "required": false, "default": false }, { "name": "max_output_tokens", "type": "integer", "required": false }, { "name": "reasoning", "type": "object", "required": false, "children": [ { "name": "effort", "type": "enum", "required": false, "default": "high", "enum": [ "none", "low", "high", "max" ] } ] }, { "name": "text", "type": "object", "required": false }, { "name": "tools", "type": "array", "required": false }, { "name": "tool_choice", "type": "string | object", "required": false } ] }, { "id": "deepseek-v4.1-flash", "title": "DeepSeek V4.1 Flash Preview API", "category": "text", "capability": "Text generation · Responses + Chat Completions", "availability": "online", "summary": "DeepSeek V4.1 Flash Preview is available through HiAPI for text generation, reasoning, and streaming. Use Responses for new integrations or retain Chat Completions for existing clients.", "bestFor": [ "Text responses" ], "docs": "https://www.hiapi.ai/docs/models/text/deepseek-v4-1-flash/", "docsZh": "https://www.hiapi.ai/docs/zh/models/text/deepseek-v4-1-flash/", "protocol": "responses", "endpoint": "https://api.hiapi.ai/v1/responses", "request": [ { "name": "model", "type": "string", "required": true }, { "name": "input", "type": "string | array", "required": true }, { "name": "stream", "type": "boolean", "required": false, "default": false }, { "name": "max_output_tokens", "type": "integer", "required": false }, { "name": "reasoning", "type": "object", "required": false, "children": [ { "name": "effort", "type": "enum", "required": false, "enum": [ "none", "high", "max" ] } ] } ] }, { "id": "elevenlabs/text-to-dialogue", "title": "ElevenLabs Text to Dialogue API", "category": "audio", "capability": "Audio generation (text-to-dialogue)", "availability": "online", "summary": "ElevenLabs Eleven v3 multi-speaker text-to-dialogue: turn scripted lines into natural, expressive conversation audio with a distinct voice per line, 70+ languages, billed per character.", "bestFor": [ "Audio dramas & audiobooks", "Podcasts & interview intros", "Game NPCs & interactive stories", "Multilingual voiceover" ], "docs": "https://www.hiapi.ai/docs/models/audio/elevenlabs-text-to-dialogue-v3/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/elevenlabs-text-to-dialogue-v3/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "dialogue", "type": "object[]", "required": true, "children": [ { "name": "text", "type": "string", "required": true }, { "name": "voice", "type": "string", "required": true, "default": "EkK5I93UQWFDigLMpZcX" } ] }, { "name": "language_code", "type": "enum", "required": false, "enum": [ "af", "ar", "hy", "as", "az", "be", "bn", "bs", "bg", "ca", "ceb", "ny", "hr", "cs", "da", "nl", "en", "et", "fil", "fi", "fr", "gl", "ka", "de", "el", "gu", "ha", "he", "hi", "hu", "is", "id", "ga", "it", "ja", "jv", "kn", "kk", "ky", "ko", "lv", "ln", "lt", "lb", "mk", "ms", "ml", "zh", "mr", "ne", "no", "ps", "fa", "pl", "pt", "pa", "ro", "ru", "sr", "sd", "sk", "sl", "so", "es", "sw", "sv", "ta", "te", "th", "tr", "uk", "ur", "vi", "cy" ] }, { "name": "stability", "type": "enum", "required": false, "default": 0.5, "enum": [ 0, 0.5, 1 ] } ] }, { "id": "flux-1.1-pro", "title": "FLUX 1.1 Pro", "category": "image", "capability": "Image generation", "availability": "online", "summary": "FLUX 1.1 Pro is suited to photorealistic images, commercial posters, product shots, and optional reference guidance.", "bestFor": [ "Photorealistic products", "Reference guidance", "Custom dimensions", "Output quality control" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-1-1-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-1-1-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_prompt", "type": "string", "required": false }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "custom", "1:1", "16:9", "3:2", "2:3", "4:5", "5:4", "9:16", "3:4", "4:3" ] }, { "name": "width", "type": "integer", "required": false }, { "name": "height", "type": "integer", "required": false }, { "name": "safety_tolerance", "type": "integer", "required": false, "default": 2 }, { "name": "seed", "type": "integer", "required": false }, { "name": "prompt_upsampling", "type": "boolean", "required": false, "default": false }, { "name": "output_format", "type": "enum", "required": false, "default": "webp", "enum": [ "webp", "jpg", "png" ] }, { "name": "output_quality", "type": "integer", "required": false, "default": 80 } ] }, { "id": "flux-2-klein-4b/image-to-image", "title": "FLUX.2 [klein] 4B Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "FLUX.2 [klein] 4B image-to-image API for single-reference instruction editing up to 4 MP, with resolution-tier pricing for fast, low-cost iteration.", "bestFor": [ "Product-image variants", "Low-cost iteration", "Preserve composition", "Reproducible edits" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2-klein-4b-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2-klein-4b-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "1 MP", "enum": [ "0.25 MP", "0.5 MP", "1 MP", "2 MP", "4 MP" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "match_input_image", "enum": [ "match_input_image", "1:1", "16:9", "9:16", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "21:9", "9:21" ] }, { "name": "seed", "type": "integer", "required": false }, { "name": "output_format", "type": "enum", "required": false, "default": "jpg", "enum": [ "webp", "jpg", "png" ] }, { "name": "output_quality", "type": "integer", "required": false, "default": 95 } ] }, { "id": "flux-2-klein-4b/text-to-image", "title": "FLUX.2 [klein] 4B API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "A compact, fast, and cost-efficient FLUX.2 text-to-image model with tiered 0.25-4 MP output for volume production and flexible publishing formats.", "bestFor": [ "Batch product and ad creatives", "Social and editorial artwork", "Higher-resolution delivery", "Repeatable creative iteration" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2-klein-4b/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2-klein-4b/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "1 MP", "enum": [ "0.25 MP", "0.5 MP", "1 MP", "2 MP", "4 MP" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "9:16", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "21:9", "9:21" ] }, { "name": "seed", "type": "integer", "required": false }, { "name": "output_format", "type": "enum", "required": false, "default": "jpg", "enum": [ "webp", "jpg", "png" ] }, { "name": "output_quality", "type": "integer", "required": false, "default": 95 } ] }, { "id": "flux-2-klein-9b/image-to-image", "title": "FLUX.2 [klein] 9B Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "FLUX.2 [klein] 9B image-to-image API for fast four-step single-reference editing with stronger detail preservation, text rendering, and commercial finish.", "bestFor": [ "Premium commercial retouching", "Text and fine-detail edits", "Fast four-step generation", "Common marketing ratios" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2-klein-9b-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2-klein-9b-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16" ] }, { "name": "seed", "type": "integer", "required": false }, { "name": "num_inference_steps", "type": "integer", "required": false, "default": 4 }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "jpeg", "png", "webp" ] } ] }, { "id": "flux-2-klein-9b/text-to-image", "title": "FLUX.2 [klein] 9B API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "A fast four-step FLUX.2 text-to-image model that balances speed and image quality for commercial visuals, complex scenes, and posters with English titles.", "bestFor": [ "Posters and covers with text", "Realistic commercial visuals", "Fast, polished concepts", "Stable composition iteration" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2-klein-9b/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2-klein-9b/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "4:3", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16" ] }, { "name": "seed", "type": "integer", "required": false }, { "name": "num_inference_steps", "type": "integer", "required": false, "default": 4 }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "jpeg", "png", "webp" ] } ] }, { "id": "flux-2/image-to-image", "title": "FLUX.2 Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "FLUX.2 pro-tier image editing: multi-reference composition (up to 8 images), background replacement, style and material edits with strong subject consistency; 1K/2K, billed per image.", "bestFor": [ "Multi-reference composition", "Background replacement", "Style & material edits", "Predictable per-image pricing" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "3:2", "2:3", "auto" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "1K", "enum": [ "1K", "2K" ] } ] }, { "id": "flux-2/text-to-image", "title": "FLUX.2 Pro API Documentation", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Black Forest Labs' flagship text-to-image model: photorealistic fidelity with consistent lighting, strong adherence to complex multi-part prompts, legible in-image text down to small sizes with hex-code color control, priced by 0.5-4 MP resolution tier.", "bestFor": [ "Product shots and commercial photography", "Posters and UI mockups with text", "Exact brand colors", "Complex multi-element compositions" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-2/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-2/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "3:2", "2:3", "4:5", "5:4", "9:16", "3:4", "4:3", "custom" ] }, { "name": "width", "type": "integer", "required": false }, { "name": "height", "type": "integer", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "1 MP", "enum": [ "0.5 MP", "1 MP", "2 MP", "4 MP" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "webp", "enum": [ "webp", "jpg", "png" ] }, { "name": "output_quality", "type": "integer", "required": false, "default": 80 }, { "name": "safety_tolerance", "type": "integer", "required": false, "default": 2 }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "flux-3", "title": "FLUX.3 Video API", "category": "video", "capability": "Text-to-video / image-to-video / video continuation", "availability": "online", "summary": "FLUX.3 Video combines text-to-video, 1-10 image keyframe control, and video continuation in one model, with clips up to 20 seconds, 720p/1080p output, and optional synchronized audio.", "bestFor": [ "Sound-on narrative clips", "Keyframe and storyboard control", "Video continuation", "Low-cost prompt previews" ], "docs": "https://www.hiapi.ai/docs/models/video/flux-3/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/flux-3/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "images", "type": "string[]", "required": false }, { "name": "start_video", "type": "string", "required": false }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "draft", "type": "boolean", "required": false, "default": false } ] }, { "id": "flux-schnell/text-to-image", "title": "FLUX.1 Schnell API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "FLUX.1 Schnell is the open-source 12B rapid text-to-image model from Black Forest Labs: 1-4 step inference returns images in seconds, it sits in the lowest price tier across HiAPI, and the Apache 2.0 license permits commercial use — built for batch generation and fast iteration.", "bestFor": [ "High-volume asset generation", "Rapid iteration and draft previews", "Low-latency, high-throughput services", "Cost-sensitive commercial projects" ], "docs": "https://www.hiapi.ai/docs/models/image/flux-schnell/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/flux-schnell/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "4:3", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16" ] }, { "name": "num_inference_steps", "type": "integer", "required": false, "default": 4 }, { "name": "guidance_scale", "type": "number", "required": false, "default": 3.5 }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png" ] }, { "name": "seed", "type": "integer", "required": false }, { "name": "enable_safety_checker", "type": "boolean", "required": false, "default": true } ] }, { "id": "gemini-omni-1.1-flash", "title": "Gemini Omni 1.1 Flash Video Generation API", "category": "video", "capability": "video generation", "availability": "online", "summary": "One unified model ID for video generation with text, image, and reference-video inputs.", "bestFor": [ "Standard video generation" ], "docs": "https://www.hiapi.ai/docs/models/video/gemini-omni-1-1-flash/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/gemini-omni-1-1-flash/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": false }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "video_list", "type": "object[]", "required": false, "children": [ { "name": "url", "type": "string", "required": true }, { "name": "start", "type": "number", "required": false, "default": 0 }, { "name": "ends", "type": "number", "required": false } ] }, { "name": "duration", "type": "string", "required": false, "default": "8", "enum": [ "4", "6", "8", "10" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "360p", "720p", "1080p", "4k" ] }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "gpt-6-astra", "title": "GPT-6 Astra API", "category": "text", "capability": "Text generation · streaming Responses", "availability": "online", "summary": "Integrate OpenAI GPT-6 Astra through HiAPI streaming Responses for text generation, reasoning, function calls, and strict JSON Schema output.", "bestFor": [ "Reasoning and code review", "Application workflows" ], "docs": "https://www.hiapi.ai/docs/models/text/gpt-6-astra/", "docsZh": "https://www.hiapi.ai/docs/zh/models/text/gpt-6-astra/", "protocol": "responses", "endpoint": "https://api.hiapi.ai/v1/responses", "request": [ { "name": "model", "type": "string", "required": true, "enum": [ "gpt-6-astra" ] }, { "name": "input", "type": "array", "required": true }, { "name": "stream", "type": "boolean", "required": true, "default": true }, { "name": "store", "type": "boolean", "required": true, "default": false }, { "name": "instructions", "type": "string", "required": false }, { "name": "reasoning", "type": "object", "required": false, "children": [ { "name": "effort", "type": "enum", "required": false, "enum": [ "low", "medium", "high", "xhigh", "max" ] } ] }, { "name": "text", "type": "object", "required": false, "children": [ { "name": "format", "type": "object", "required": false, "children": [ { "name": "type", "type": "enum", "required": true, "enum": [ "json_object", "json_schema" ] }, { "name": "name", "type": "string", "required": false }, { "name": "strict", "type": "boolean", "required": false }, { "name": "schema", "type": "object", "required": false } ] } ] }, { "name": "tools", "type": "array", "required": false }, { "name": "tool_choice", "type": "string | object", "required": false } ], "textContract": { "chatCompletions": false, "nonStreaming": false }, "requestExample": { "model": "gpt-6-astra", "input": [ { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "Review this service design and list the top three risks." } ] } ], "stream": true, "store": false, "reasoning": { "effort": "medium" } } }, { "id": "gpt-image-2.5-flare/image-to-image", "title": "gpt-image-2.5-flare/image-to-image", "category": "image", "capability": "Image to image", "availability": "online", "summary": "gpt-image-2.5-flare Image to image mode.", "bestFor": [ "Image to image" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-flare-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-flare-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": true }, { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9", "27:16", "16:27", "9:8", "8:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "transparent", "opaque", "auto" ] } ] }, { "id": "gpt-image-2.5-flare/text-to-image", "title": "gpt-image-2.5-flare/text-to-image", "category": "image", "capability": "Text to image", "availability": "online", "summary": "gpt-image-2.5-flare Text to image mode.", "bestFor": [ "Text to image" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-flare-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-flare-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9", "27:16", "16:27", "9:8", "8:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "transparent", "opaque", "auto" ] } ] }, { "id": "gpt-image-2.5-flare@pro", "title": "gpt-image-2.5-flare@pro", "category": "image", "capability": "Pro", "availability": "online", "summary": "gpt-image-2.5-flare Pro mode.", "bestFor": [ "Pro" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-flare-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-flare-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": false }, { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "auto", "1024x1024", "1536x1024", "1024x1536", "1536x1152", "1152x1536", "2048x2048", "2048x1152", "1152x2048", "3840x2160", "2160x3840" ] }, { "name": "quality", "type": "enum", "required": false, "default": "medium", "enum": [ "low", "medium", "high", "xhigh", "max", "auto" ] }, { "name": "background", "type": "enum", "required": false, "default": "auto", "enum": [ "transparent", "opaque", "auto" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "webp", "enum": [ "png", "jpeg", "webp" ] } ] }, { "id": "gpt-image-2.5-sunburst/image-to-image", "title": "gpt-image-2.5-sunburst/image-to-image", "category": "image", "capability": "Image to image", "availability": "online", "summary": "gpt-image-2.5-sunburst Image to image mode.", "bestFor": [ "Image to image" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-sunburst-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-sunburst-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": true }, { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9", "27:16", "16:27", "9:8", "8:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "transparent", "opaque", "auto" ] } ] }, { "id": "gpt-image-2.5-sunburst/text-to-image", "title": "gpt-image-2.5-sunburst/text-to-image", "category": "image", "capability": "Text to image", "availability": "online", "summary": "gpt-image-2.5-sunburst Text to image mode.", "bestFor": [ "Text to image" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-sunburst-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-sunburst-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9", "27:16", "16:27", "9:8", "8:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "transparent", "opaque", "auto" ] } ] }, { "id": "gpt-image-2.5-sunburst@pro", "title": "gpt-image-2.5-sunburst@pro", "category": "image", "capability": "Pro", "availability": "online", "summary": "gpt-image-2.5-sunburst Pro mode.", "bestFor": [ "Pro" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-5-sunburst-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-5-sunburst-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": false }, { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "auto", "1024x1024", "1536x1024", "1024x1536", "1536x1152", "1152x1536", "2048x2048", "2048x1152", "1152x2048", "3840x2160", "2160x3840" ] }, { "name": "quality", "type": "enum", "required": false, "default": "medium", "enum": [ "low", "medium", "high", "xhigh", "max", "auto" ] }, { "name": "background", "type": "enum", "required": false, "default": "auto", "enum": [ "transparent", "opaque", "auto" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "webp", "enum": [ "png", "jpeg", "webp" ] } ] }, { "id": "gpt-image-2/image-to-image", "title": "GPT Image 2 Image-to-Image", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "Send model=gpt-image-2/image-to-image to POST /v1/tasks to edit images from 1–6 references. This reference covers input fields, route differences, callbacks, polling, and code examples.", "bestFor": [ "Reference rewriting", "Product image cleanup", "Multi-ratio delivery", "Detailed constraints", "Multiple routes" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "input_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "auto", "opaque", "transparent" ] } ], "routes": [ { "route": "default", "label": "Standard", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "input_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "auto", "opaque", "transparent" ] } ] }, { "route": "ext", "label": "ext · multi-ratio 4K", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "quality", "type": "enum", "required": true, "default": "low", "enum": [ "low", "medium", "high" ] } ] } ] }, { "id": "gpt-image-2/text-to-image", "title": "GPT Image 2 API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Send model=gpt-image-2/text-to-image to POST /v1/tasks to call GPT Image 2. This reference covers every request field, route difference, callback, polling step, and code example.", "bestFor": [ "Accurate text rendering", "Poster and layout work", "Product and commerce images", "Long-prompt creative drafts", "Multi-format delivery", "Multiple routes" ], "docs": "https://www.hiapi.ai/docs/models/image/gpt-image-2/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/gpt-image-2/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "auto", "opaque", "transparent" ] } ], "routes": [ { "route": "default", "label": "Standard", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "background", "type": "enum", "required": false, "enum": [ "auto", "opaque", "transparent" ] } ] }, { "route": "beta", "label": "beta", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "size", "type": "string", "required": false, "default": "auto" } ] }, { "route": "ext", "label": "ext · multi-ratio 4K", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "auto", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "2:1", "1:2", "3:1", "1:3", "21:9", "9:21" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "1K", "enum": [ "1K", "2K", "4K" ] }, { "name": "quality", "type": "enum", "required": true, "default": "low", "enum": [ "low", "medium", "high" ] } ] } ] }, { "id": "grok-imagine-1.5/image-to-video", "title": "Grok Imagine 1.5 Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "xAI Grok Imagine 1.5 image-to-video: upgraded motion quality over 1.0, flexible 1-15 second clips at 480p/720p, billed per second at the same price as 1.0.", "bestFor": [ "Upgraded image animation", "Flexible 1-15s duration", "Cheap iteration", "Follows input framing" ], "docs": "https://www.hiapi.ai/docs/models/video/grok-imagine-1-5-image-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/grok-imagine-1-5-image-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": false }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "1:1", "16:9", "9:16", "3:2", "2:3" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "480p", "enum": [ "480p", "720p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 8 } ] }, { "id": "grok-imagine-image-2.0/image-to-image", "title": "Grok Image 2.0 Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "xAI Grok Imagine Image 2.0 edits one public reference image with natural-language instructions for recoloring, restyling, scene changes, and refinements.", "bestFor": [ "Product-image changes", "Style transfer", "Single-image refinement" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-image-2-0-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-image-2-0-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image", "type": "string", "required": true }, { "name": "quality", "type": "enum", "required": false, "default": "medium", "enum": [ "low", "medium" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "2:1", "1:2", "19.5:9", "9:19.5", "20:9", "9:20", "auto" ] } ] }, { "id": "grok-imagine-image-2.0/text-to-image", "title": "Grok Image 2.0 Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "xAI Grok Imagine Image 2.0 for natural-language image generation with 1k/2k output and flexible square-to-ultrawide framing.", "bestFor": [ "Fast visual ideation", "Banners and wide layouts", "Selectable output size" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-image-2-0-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-image-2-0-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "quality", "type": "enum", "required": false, "default": "medium", "enum": [ "low", "medium" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "2:1", "1:2", "19.5:9", "9:19.5", "20:9", "9:20", "auto" ] } ] }, { "id": "grok-imagine-quality/image-to-image", "title": "Grok Imagine Quality Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "Grok Imagine quality-tier image editing (xAI official quality model): stronger subject consistency and detail preservation with up to 3 references, priced per image in 1k/2k resolution tiers.", "bestFor": [ "High-consistency editing", "Multi-reference blending", "Auto aspect", "Standard-tier sibling model" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-quality-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-quality-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png", "webp" ] }, { "name": "image_urls", "type": "string[]", "required": true } ] }, { "id": "grok-imagine-quality/text-to-image", "title": "Grok Imagine Quality Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Grok Imagine quality-tier text-to-image (xAI official quality model): hero-grade detail, materials, and lighting with 13 aspect ratios, priced per image in 1k/2k resolution tiers.", "bestFor": [ "Hero-grade output", "13 aspect ratios", "1k/2k tiered pricing", "Standard-tier sibling model" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-quality-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-quality-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png", "webp" ] } ] }, { "id": "grok-imagine/image-to-image", "title": "Grok Imagine Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "Grok Imagine image editing: blends up to 3 references at a flat per-image price; the standalone quality-tier model (grok-imagine-quality/image-to-image) adds stronger consistency with tiered pricing.", "bestFor": [ "Multi-reference blending", "Auto aspect", "Per-image billing", "Quality-tier sibling model" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png", "webp" ] }, { "name": "image_urls", "type": "string[]", "required": true } ] }, { "id": "grok-imagine/image-to-video", "title": "Grok Imagine Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Grok Imagine image-to-video animates one or more reference images into a cinematic short clip, guided by an optional motion prompt, with selectable aspect ratio, motion mode, and duration (6-30s), all through one HiAPI API key.", "bestFor": [ "Animate product shots", "Dynamic portrait clips", "Add motion to static scenes", "Multi-image reference" ], "docs": "https://www.hiapi.ai/docs/models/video/grok-imagine-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/grok-imagine-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": true }, { "name": "prompt", "type": "string", "required": false }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "2:3", "enum": [ "2:3", "3:2", "1:1", "16:9", "9:16" ] }, { "name": "mode", "type": "enum", "required": false, "default": "normal", "enum": [ "fun", "normal" ] }, { "name": "duration", "type": "integer", "required": false, "default": 6 }, { "name": "resolution", "type": "enum", "required": false, "default": "480p", "enum": [ "480p", "720p" ] } ] }, { "id": "grok-imagine/text-to-image", "title": "Grok Imagine Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Grok Imagine text-to-image: fast and low-cost with 13 aspect ratios and flat 1k/2k pricing; the standalone quality-tier model (grok-imagine-quality/text-to-image) delivers hero-grade output with resolution-tiered pricing.", "bestFor": [ "Fast, low-cost generation", "13 aspect ratios", "1k/2k same price", "Quality-tier sibling model" ], "docs": "https://www.hiapi.ai/docs/models/image/grok-imagine-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/grok-imagine-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1k", "enum": [ "1k", "2k" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png", "webp" ] } ] }, { "id": "grok-imagine/text-to-video", "title": "Grok Imagine Text to Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Grok Imagine text-to-video turns a single text prompt into a cinematic short clip, with selectable motion mode, aspect ratio, duration (6-30s), and 480p/720p resolution, all through one HiAPI API key.", "bestFor": [ "Ads and brand films", "Vertical social clips", "Motion style control", "Storyboards and previews" ], "docs": "https://www.hiapi.ai/docs/models/video/grok-imagine-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/grok-imagine-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "2:3", "enum": [ "2:3", "3:2", "1:1", "16:9", "9:16" ] }, { "name": "mode", "type": "enum", "required": false, "default": "normal", "enum": [ "fun", "normal" ] }, { "name": "duration", "type": "integer", "required": false, "default": 6 }, { "name": "resolution", "type": "enum", "required": false, "default": "480p", "enum": [ "480p", "720p" ] } ] }, { "id": "hailuo-2.3-fast/image-to-video", "title": "Hailuo 2.3 Fast Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Hailuo 2.3 Fast image-to-video: the family price floor with 6s/10s per-video billing.", "bestFor": [ "Lowest price in the family", "Fast turnaround" ], "docs": "https://www.hiapi.ai/docs/models/video/hailuo-2-3-fast-image-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/hailuo-2-3-fast-image-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_url", "type": "string", "required": true }, { "name": "duration", "type": "enum", "required": false, "default": "6", "enum": [ "6", "10" ] }, { "name": "prompt_optimizer", "type": "boolean", "required": false, "default": true } ] }, { "id": "hailuo-2.3/image-to-video", "title": "Hailuo 2.3 Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "MiniMax Hailuo 2.3 image-to-video: first-frame driven with natural motion and 6s/10s per-video pricing on the standard route.", "bestFor": [ "Animate stills", "Natural motion", "6/10s tiers" ], "docs": "https://www.hiapi.ai/docs/models/video/hailuo-2-3-image-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/hailuo-2-3-image-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_url", "type": "string", "required": true }, { "name": "duration", "type": "enum", "required": false, "default": "6", "enum": [ "6", "10" ] }, { "name": "prompt_optimizer", "type": "boolean", "required": false, "default": true } ] }, { "id": "hailuo-2.3/text-to-video", "title": "Hailuo 2.3 Text to Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "MiniMax Hailuo 2.3 text-to-video: excellent motion physics with 6s/10s per-video pricing on the standard route.", "bestFor": [ "Physical motion", "6/10s per-video pricing" ], "docs": "https://www.hiapi.ai/docs/models/video/hailuo-2-3-text-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/hailuo-2-3-text-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "duration", "type": "enum", "required": false, "default": "6", "enum": [ "6", "10" ] }, { "name": "prompt_optimizer", "type": "boolean", "required": false, "default": true } ] }, { "id": "happyhorse-1-0", "title": "HappyHorse 1.0", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "HappyHorse 1.0 is a fast text-to-video model for 3-15 second drafts, social clips, and low-cost video validation.", "bestFor": [ "Short video output", "Ratio and resolution control", "Low-cost debugging", "Production callbacks" ], "docs": "https://www.hiapi.ai/docs/models/video/happyhorse-1-0/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/happyhorse-1-0/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "1:1", "16:9", "3:4", "4:3", "9:16" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p" ] }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "happyhorse-1.1/image-to-video", "title": "HappyHorse 1.1 I2V API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "HappyHorse 1.1 image-to-video API by Alibaba. Animate a single first-frame image into a short video, preserving subject, style and scene, with native audio, at 720p / 1080p and 3-15 seconds.", "bestFor": [ "First-frame driven clips", "Prompt-guided motion", "Still to motion", "Pick resolution and length" ], "docs": "https://www.hiapi.ai/docs/models/video/happyhorse-1-1-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/happyhorse-1-1-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": true }, { "name": "prompt", "type": "string", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 } ] }, { "id": "happyhorse-1.1/reference-to-video", "title": "HappyHorse 1.1 R2V API", "category": "video", "capability": "Video generation (reference-to-video)", "availability": "online", "summary": "HappyHorse 1.1 reference-to-video API by Alibaba. Generate short videos from up to 9 reference images, referenced in the prompt as [Image 1], [Image 2], keeping subject, scene and style consistent across shots, with native audio.", "bestFor": [ "Precise multi-reference control", "Name references in the prompt", "Cross-shot consistency", "Landscape and portrait ratios" ], "docs": "https://www.hiapi.ai/docs/models/video/happyhorse-1-1-r2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/happyhorse-1-1-r2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "reference_image", "type": "string[]", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "3:4", "4:3", "4:5", "5:4", "1:1", "9:21", "21:9" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 } ] }, { "id": "happyhorse-1.1/text-to-video", "title": "HappyHorse 1.1 T2V API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "HappyHorse 1.1 text-to-video API by Alibaba. Generate short videos with native audio from a text prompt, with natural motion and strong prompt adherence, at 720p / 1080p and 3-15 seconds.", "bestFor": [ "Sound-on short videos", "Text-to-clip creative drafts", "Landscape and portrait ratios", "Pick resolution and length" ], "docs": "https://www.hiapi.ai/docs/models/video/happyhorse-1-1-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/happyhorse-1-1-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "3:4", "4:3", "4:5", "5:4", "1:1", "9:21", "21:9" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 } ] }, { "id": "heygen-avatar-v", "title": "HeyGen Avatar V", "category": "video", "capability": "Avatar video", "availability": "online", "summary": "Generate lip-synced avatar video from a script and preset voice or from driving audio.", "bestFor": [ "Script and voice", "Driving audio" ], "docs": "https://www.hiapi.ai/docs/models/video/heygen-avatar-v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/heygen-avatar-v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "avatar", "type": "string", "required": true, "default": "Abigail Sofa Front", "enum": [ "Abigail Office Front", "Abigail Office Side", "Abigail Sofa Front", "Abigail Sofa Side", "Amelia Business Training Front 2", "Amelia Business Training Front", "Amelia Business Training Side 2", "Amelia Business Training Side", "Amelia Lounge Front 2", "Amelia Lounge Front", "Amelia Lounge Side 2", "Amelia Lounge Side", "Amelia Yoga Front 2", "Amelia Yoga Front", "Amelia Yoga Side 2", "Amelia Yoga Side", "Anja Office Front", "Anja Office Side ", "Anja Sofa Front", "Anja Sofa Side ", "Ann Doctor Sitting", "Ann Doctor Standing", "Ann Therapist", "Annie Bar Sitting Front", "Annie Bar Sitting Side", "Annie Bar Standing Front 2", "Annie Bar Standing Front 3", "Annie Bar Standing Front", "Annie Bar Standing Side 2", "Annie Bar Standing Side 3", "Annie Bar Standing Side", "Annie Business Casual Standing Front 2", "Annie Business Casual Standing Front", "Annie Business Casual Standing Side 2", "Annie Business Casual Standing Side", "Annie Casual Sitting Front 2", "Annie Casual Sitting Front", "Annie Casual Sitting Side 2", "Annie Casual Sitting Side", "Annie Casual Standing Front 2", "Annie Casual Standing Front", "Annie Casual Standing Side 2", "Annie Casual Standing Side", "Annie Desk Sitting Front 2", "Annie Desk Sitting Front", "Annie Desk Sitting Side 2", "Annie Desk Sitting Side", "Annie Lounge Standing Front", "Annie Lounge Standing Side", "Annie Office Sitting Front 2", "Annie Office Sitting Front", "Annie Office Sitting Side 2", "Annie Office Sitting Side", "Annie Office Standing Front", "Annie Office Standing Side", "Annie Sofa Sitting Front 3", "Annie Sofa Sitting Front", "Annie Sofa Sitting Side 2", "Annie Sofa Sitting Side 3", "Annie Sofa Sitting Side", "Annie Sofa Sitting Front 2", "Annie Studio Pink Sitting Front", "Annie Studio Pink Sitting Side", "Annie Studio Pink Standing Front", "Annie Studio Pink Standing Side", "Artur Office Front 2", "Artur Office Front", "Artur Office Side 2", "Artur Office Side", "Artur Sofa Casual Front 2", "Artur Sofa Casual Front", "Artur Sofa Casual Side 2", "Artur Sofa Causal Side", "Aubrey Sofa Side", "Aubrey Night Scene Front", "Aubrey Outdoor Sport Front", "Aubrey Outdoor Sport Side", "Aubrey Sofa Front", "Blanka Lounge Front", "Blanka Lounge Side", "Blanka Outdoor Business Front", "Blanka Outdoor Business Side", "Blanka Outdoor Reading Front", "Blanka Outdoor Reading Side", "Blanka Picnic Front", "Blanka Picnic Side", "Bojan Business Training Front 2", "Bojan Business Training Front", "Bojan Business Training Side 2", "Bojan Business Training Side", "Bojan Lounge Front 2", "Bojan Lounge Front", "Bojan Lounge Side 2", "Bojan Lounge Side", "Bojan Sport Front 2", "Bojan Sport Front", "Bojan Sport Side 2", "Bojan Sport Side", "Brandon Business Sitting Front", "Brandon Business Sitting Side", "Brandon Business Standing Front", "Brandon Business Standing Side", "Brandon Casual Sitting Front", "Brandon Casual Sitting Side", "Brandon Kitchen Standing Front", "Brandon Kitchen Standing Side", "Brandon Lobby Sitting Front", "Brandon Lobby Sitting Side", "Brandon Lobby Standing Front", "Brandon Lobby Standing Side", "Brandon Office Sitting Front", "Brandon Office Sitting Side", "Brandon Office Standing Front", "Brandon Office Standing Side", "Brandon Sofa Sitting Front", "Brandon Sofa Sitting Side", "Brent Office Front 2", "Brent Office Front", "Brent Office Side 2", "Brent Office Side", "Brent Sofa Front 2", "Brent Sofa Front", "Brent Sofa Side 2", "Brent Sofa Side", "Bryan Fitness Coach", "Bryan Tech Expert", "Caroline Business Sitting Front", "Caroline Business Sitting Side", "Caroline Business Standing Front", "Caroline Business Standing Side", "Caroline Casual Sitting Front", "Caroline Casual Sitting Side", "Caroline Kitchen Standing Front", "Caroline Kitchen Standing Side", "Caroline Lobby Sitting Front", "Caroline Lobby Sitting Side", "Caroline Lobby Standing Front", "Caroline Lobby Standing Side", "Caroline Office Sitting Front", "Caroline Office Sitting Side", "Caroline Office Standing Front", "Caroline Office Standing Side", "Caroline Sofa Sitting Front", "Caroline Sofa Sitting Side", "Chloe Lounge Front", "Chloe Lounge Side", "Chloe Outdoor Side", "Conrad House Front", "Conrad House Side", "Conrad Sofa Front", "Conrad Sofa Side", "Derya Indoor Front 2", "Derya Indoor Front", "Derya Indoor Side 2", "Derya Indoor Side", "Derya Office Front 2", "Derya Office Front", "Derya Office Side 2", "Derya Office Side", "Dexter Doctor Sitting", "Dexter Doctor Standing", "Dexter Lawyer", "Elenora Fitness Coach", "Elenora Fitness Coach 2", "Elenora Tech Expert", "Emanuel Office Front", "Emanuel Office Side", "Emanuel Sofa Front", "Emanuel Sofa Side", "Emilia Outdoor Business Front", "Emilia Outdoor Business Side", "Emilia Outdoor Yoga Front 2", "Emilia Outdoor Yoga Front", "Emilia Outdoor Yoga Side", "Emilia Picnic Front", "Emilia Picnic Side", "Fernando Business Indoor Front", "Fernando Business Indoor Side", "Fernando OutdoorChair Front 2", "Fernando Outdoor Chair Front", "Fernando Outdoor Chair Side", "Fernando Outdoor Front", "Fernando Outdoor Side", "Fernando Outdoor Table Front", "Fernando Outdoor Table Side", "Gala Bedroom Front", "Gala Business Sofa Front 2", "Gala Business Sofa Front 3", "Gala Business Sofa Front", "Gala Business Sofa Side 2", "Gala Business Sofa Side 3", "Gala Business Sofa Side", "Gala Casual Sofa with iPad Front", "Gala Casual Sofa with iPad Side 2", "Gala Casual Sofa with iPad Side", "Gala Office Front", "Gala Office Side", "Gala Sofa Front 2", "Gala Sofa Front 3", "Gala Sofa Front", "Gala Sofa Side 2", "Gala Sofa Side 3", "Gala Sofa Side", "Georgia Casual Front", "Georgia Casual Side", "Georgia Office Front", "Georgia Office Side", "Gerardo Sofa Side", "Gerardo Indoor Front", "Gerardo Indoor Side", "Gerardo Night Scene Front 2", "Gerardo Night Scene Front", "Gerardo Outdoor Sport Front", "Gerardo Outdoor Sport Side", "Gerardo Sofa Front", "Giulia Office Front 2", "Giulia Office Front", "Giulia Office Side 2", "Giulia Office Side", "Giulia Sofa Front", "Giulia Sofa Side", "Giulia Sofa Front 2", "Giulia Sofa Side 3", "Ida Lounge Front 2", "Ida Lounge Front", "Ida Lounge Side 2", "Ida Lounge Side", "Ida Sofa Front 2", "Ida Sofa Front", "Ida Sofa Side 2", "Ida Sofa Side", "Jocelyn Office Front 2", "Jocelyn Office Front", "Jocelyn Office Side 2", "Jocelyn Office Side", "Jocelyn Sofa Front 2", "Jocelyn Sofa Front", "Jocelyn Sofa Side 2", "Jocelyn Sofa Side", "Joel Couch Front", "Joel Couch Side", "Joel Gym Front", "Joel Gym Side", "Joel Mountain Front", "Joel Mountain Side", "Jonas Gym Front 2", "Jonas Gym Front", "Jonas Gym Side 2", "Jonas Gym Side ", "June Office Front 2", "Juan Office Front", "Juan Office Side 2", "Juan Office Side", "Juan Sofa Front 2", "Juan Sofa Front", "Juan Sofa Side 2", "Juan Sofa Side", "Judita Yoga Front 2", "Judita Yoga Front", "Judita Yoga Side 2", "Judita Yoga Side", "Judy Doctor Sitting", "Judy Doctor Standing", "Judy Lawyer", "Judy Teacher Sitting", "Judy HR", "Judy Teacher Standing", "June HR", "June Office Front", "June Office Side 2", "June Office Side", "June Sofa Casual Front 2", "June Sofa Casual Front", "June Sofa Casual Side 2", "June Sofa Casual Side", "Kavya Indoor Front", "Kavya Indoor Side", "Kavya Outdoor Side", "Kavya Outdoor Sport Front", "Kavya Outdoor Sport Side", "Kavya Sofa Front", "Kavya Sofa Side", "Leos Office Front 2", "Leos Office Front", "Leos Office Side 2", "Leos Office Side", "Leos Sofa Front 2", "Leos Sofa Front", "Leos Sofa Side 2", "Leos Sofa Side", "Leszek Lounge Front", "Leszek Lounge Side", "Leszek Outdoor Business Front", "Leszek Outdoor Business Side", "Leszek Outdoor Casual Front", "Leszek Outdoor Casual Side", "Leszek Sofa Front", "Leszek Sofa Side", "Martina Office Front 2", "Martina Office Front", "Martina Office Side 2", "Martina Office Side", "Martina Sofa Front 2", "Martina Sofa Front", "Martina Sofa Side 2", "Martina Sofa Side", "Masha Office Front 2", "Masha Office Front", "Masha Office Side 2", "Masha Office Side", "Masha Sofa Casual Front 2", "Masha Sofa Casual Front", "Masha Sofa Casual Side 2", "Masha Sofa Casual Side", "Matteo Office Front 2", "Matteo Office Front", "Matteo Office Side 2", "Matteo Office Side", "Matteo Sofa Front 2", "Matteo Sofa Front", "Matteo Sofa Side 2", "Matteo Sofa Side", "Max Indoor Front", "Max Indoor Side", "Max Outdoor Sport Front", "Max Outdoor Sport Side", "Milena Office Front 2", "Milena Office Front", "Milena Office Side 2", "Milena Office Side", "Milena Sofa Front 2", "Milena Sofa Front", "Milena Sofa Side 2", "Milena Sofa Side", "Miles Outdoor Front", "Miles Outdoor Side", "Miles Sofa Front 2", "Miles Sofa Front", "Miles Sofa Side 2", "Miles Sofa Side", "Mireia Business Indoor Front", "Mireia Business Indoor Side", "Mireia Outdoor Chair Front", "Mireia Outdoor Front", "Mireia Outdoor Side", "Mireia Outdoor Table Front", "Mireia Outdoor Table Side", "Miyu Office Front 2", "Miyu Office Front", "Miyu Office Side 2", "Miyu Office Side", "Miyu Sofa Business Front", "Miyu Sofa Business Side", "Miyu Sofa Casual Front 2", "Miyu Sofa Casual Front", "Miyu Sofa Casual Side 2 ", "Miyu Sofa Casual Side", "Noah Lobby Front 2", "Noah Lobby Front", "Noah Lobby Side 2", "Noah Lobby Side", "Noah Office Front 2", "Noah Office Front", "Noah Office Side 2", "Noah Office Side", "Noah Sofa Front 2", "Noah Sofa Front ", "Noah Sofa Side 2", "Noah Sofa Side", "Oxana Gym Front 2", "Oxana Gym Front", "Oxana Gym Side 2", "Oxana Gym Side", "Oxana Office Front 2", "Oxana Office Front", "Oxana Office Side 2", "Oxana Office Side", "Oxana Sofa Front 2", "Oxana Sofa Front", "Oxana Sofa Side 2", "Oxana Sofa Side", "Oxana Yoga Front 2", "Oxana Yoga Front", "Oxana Yoga Side 2", "Oxana Yoga Side", "Patrizio Business Training Front", "Patrizio Business Training Side", "Patrizio Office Front", "Patrizio Office Side 2", "Patrizio Office Side", "Patrizio Sofa Front", "Patrizio Sofa Side", "Piper Business Sofa Front", "Piper Business Sofa Side", "Piper Education Front", "Piper Education Side", "Rasmus Lounge Front 2", "Rasmus Lounge Front", "Rasmus Lounge Side 2", "Rasmus Lounge Side", "Rasmus Sofa Front 2", "Rasmus Sofa Front", "Rasmus Sofa Side 2", "Rasmus Sofa Side", "Raul Business Sofa Front 2", "Raul Business Sofa Front", "Raul Business Sofa Side 2", "Raul Business Sofa Side", "Raul Casual Sofa Front 2", "Raul Casual Sofa Front", "Raul Casual Sofa Side 2", "Raul Casual Sofa Side", "Raul Casual Sofa no iPad Front", "Raul Casual Sofa no iPad Side", "Raul Casual Sofa with iPad Front", "Raul Casual Sofa with iPad Side", "Raul Office Front 2", "Raul Office Front", "Raul Office Side", "Raul Sofa Front 2", "Raul Sofa Front", "Raul Sofa Side 2", "Raul Sofa Side", "Ren Office Front 2", "Ren Office Front", "Ren Office Side 2", "Ren Office Side", "Ren Sofa Business Front", "Ren Sofa Business Side", "Ren Sofa Casual Front 2", "Ren Sofa Casual Front", "Ren Sofa Casual Side 2 ", "Ren Sofa Casual Side", "Riley Casual Front", "Riley Casual Side", "Riley Office Front", "Riley Office Side", "Roman Outdoor Sport Front", "Roman Outdoor Sport Side", "Sabine Office Front 2", "Sabine Office Front", "Sabine Office Side", "Sabine Sofa Side", "Santa Fireplace Front", "Santa Fireplace Side", "Scarlett Couch Front 2", "Scarlett Couch Front", "Scarlett Couch Side 2", "Scarlett Couch Side", "Scarlett Fireplace Front", "Scarlett Fireplace Side", "Scarlett Hall Front", "Scarlett Hall Side", "Scarlett Yoga Front", "Scarlett Yoga Side", "Shawn Therapist", "Silas Customer Support", "Silas HR", "Silas Lounge Front", "Silas Lounge Side", "Silas Sofa Side 2", "Silas Sofa Side", "Teodor Office Front 2", "Teodor Office Front", "Teodor Office Side 2", "Teodor Office Side", "Teodor Sofa Front 2", "Teodor Sofa Front", "Teodor Sofa Side 2", "Teodor Sofa Side", "Timothy Casual Front", "Timothy Casual Side", "Timothy Office Front", "Timothy Office Side", "Veit Office Front", "Veit Office Side", "Veit Sofa Front", "Veit Sofa Side", "Vernon Office Front 2", "Vernon Office Front", "Vernon Office Side 2", "Vernon Office Side", "Verena Office Front", "Verena Office Side", "Verena Sofa Front", "Verena Sofa Side", "Vernon Lounge Front 2", "Vernon Lounge Side 2", "Vernon Lounge Side", "Vince Business Sofa Front", "Vince Business Training Front", "Vince Business Training Side 2", "Vince Business Training Side", "Vince Sofa Casual Front 2", "Vince Sofa Casual Front", "Vince Sofa Casual Side 2", "Vince Sofa Casual Side" ] }, { "name": "prompt", "type": "string", "required": false }, { "name": "voice", "type": "string", "required": false, "default": "Warm Pro Narrator", "enum": [ "Warm Pro Narrator", "Chill Brian", "Ivy", "John Doe", "Monika Sogam", "Hope ", "Archer ", "Brittney", "Patrick", "David Castlemore", "Michael C", "Adam Stone ", "Juniper", "Cassidy ", "Jessica Anne Bogart", "Arabella", "Andrew", "Spuds Oxley ", "Grace Elder", "Helen", "Canyon Rivers", "Derya - Lifelike - Excited", "Mellow Marcus", "Jack Sterling - Broadcaster", "Brenda - UGC - 1.mp4", "Reid", "Reagan", "Terry", "Jenny", "Radio Rick", "Denise", "Tim in car - Excited", "Iskander", "Thompson", "Delicate Daisy - Excited", "Kingston", "George UGC 1", "Bold Blake", "Jane", "Expressive Evan", "Marianne - IA", "Aaron", "Modern Recipe Host - Voice 1", "Willow", "Cute Chloe - Friendly", "Rafael", "June - Lifelike", "Crisp Chloe", "Slick Simon", "Nassim - Informative", "Baritone Ben", "Maxwell", "Ellie Faye - Excited", "Milani", "Feisty Fiona - Excited", "Professor Dean", "Rose - UGC - 1.mp4", "Shona", "Hudson Wilder", "Ann - IA", "Alastair Kensington", "Oxley", "Christina", "Andrew Rizz ", "Peyton", "Gerardo - Outdoor", "Chloe - Lifelike", "Stephanie", "Anthony - IA", "Signal - Voice 1", "Luca", "Lisa - Voice 1", "T.W.Tucker", "Jack Sullivan - Serious", "Winter", "Mireia - Lifelike", "Georgia", "Stella", "Masha - Lifelike", "Charming Charles - Friendly", "Serenity", "Annie - Excited", "Ralph", "Bethany", "Dominic", "Mason Finn", "Leena", "Veteran Victor", "Tamara", "Nik Public", "Calm Chloe", "Sevik", "Reilly", "Raul", "Imposing Ian", "Relaxed Ray", "Dexter - Professional", "Relaxed Rick", "Edwin", "Rupert Blackwood", "Ginny", "Hope" ] }, { "name": "audio_url", "type": "string", "required": false }, { "name": "fit", "type": "enum", "required": false, "default": "cover", "enum": [ "contain", "cover" ] }, { "name": "remove_background", "type": "boolean", "required": false, "default": false }, { "name": "background", "type": "object", "required": false, "children": [ { "name": "type", "type": "enum", "required": true, "enum": [ "color", "image" ] }, { "name": "value", "type": "string", "required": true } ] }, { "name": "caption", "type": "boolean", "required": false, "default": false }, { "name": "output_format", "type": "enum", "required": false, "default": "mp4", "enum": [ "mp4", "webm" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "4:5", "5:4", "1:1", "auto" ] } ] }, { "id": "ideogram-v4", "title": "Ideogram V4 API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Ideogram V4: the typography specialist — best-in-class text accuracy for logos, posters and signage, with TURBO/BALANCED/QUALITY tiers priced per image.", "bestFor": [ "Logos & wordmarks", "Posters & layouts", "Signage & marquees", "Three speed tiers" ], "docs": "https://www.hiapi.ai/docs/models/image/ideogram-v4/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/ideogram-v4/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "4:3", "9:16", "3:4" ] }, { "name": "rendering_speed", "type": "enum", "required": true, "default": "BALANCED", "enum": [ "TURBO", "BALANCED", "QUALITY" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "jpeg", "enum": [ "jpeg", "png" ] }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "kling-3.0-omni/image-to-video", "title": "Kling 3.0 Omni I2V API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Kling 3.0 Omni image-to-video API by Kuaishou Kling. Drive cinematic clips from a first frame (or first/last frame) image with native audio, at 720p / 1080p / 4K resolutions and 3-15 second durations.", "bestFor": [ "First-frame-driven clips", "Image + prompt motion control", "First/last frame transition", "Sound-on and high-resolution" ], "docs": "https://www.hiapi.ai/docs/models/video/kling-3-0-omni-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/kling-3-0-omni-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_urls", "type": "string[]", "required": true }, { "name": "prompt", "type": "string", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p", "4K" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "sound", "type": "boolean", "required": false, "default": false } ] }, { "id": "kling-3.0-omni/text-to-video", "title": "Kling 3.0 Omni T2V API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Kling 3.0 Omni text-to-video API by Kuaishou Kling. Generate cinematic clips from a text prompt with native audio (multilingual dialogue and lip sync), multi-shot storytelling, 720p / 1080p / 4K resolutions, and 3-15 second durations.", "bestFor": [ "Sound-on finished clips", "Multi-shot storytelling", "4K high-resolution output", "Ratio and duration fit" ], "docs": "https://www.hiapi.ai/docs/models/video/kling-3-0-omni-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/kling-3-0-omni-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "1080p", "enum": [ "720p", "1080p", "4K" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "1:1" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "sound", "type": "boolean", "required": false, "default": false } ] }, { "id": "kling-3.0-turbo/image-to-video", "title": "Kling 3.0 Turbo Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Kling 3.0 Turbo image-to-video: first-frame driven speed tier — 3-15s, 720p/1080p, per-second tiered billing.", "bestFor": [ "Animate stills", "Flexible 3-15s", "Fast-tier economics" ], "docs": "https://www.hiapi.ai/docs/models/video/kling-3-0-turbo-image-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/kling-3-0-turbo-image-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "image_urls", "type": "string[]", "required": true } ] }, { "id": "kling-3.0-turbo/text-to-video", "title": "Kling 3.0 Turbo Text to Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Kling 3.0 Turbo text-to-video: the speed tier of the 3.0 family — 3-15s, 720p/1080p, per-second tiered billing, built for volume.", "bestFor": [ "Cost-efficient volume", "Flexible 3-15s", "Lip-synced dialogue" ], "docs": "https://www.hiapi.ai/docs/models/video/kling-3-0-turbo-text-to-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/kling-3-0-turbo-text-to-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "1:1" ] } ] }, { "id": "lyria-3-pro", "title": "Google Lyria 3 Pro API", "category": "audio", "capability": "Audio generation (text-to-music)", "availability": "online", "summary": "Generate full songs up to approximately three minutes from prompts and optional inspiration images; images guide the music and are not video frames or audio source media.", "bestFor": [ "Full song generation", "Image-inspired music", "Lyrics and section control" ], "docs": "https://www.hiapi.ai/docs/models/audio/lyria-3-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/lyria-3-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "lyria-3.5", "title": "Lyria 3.5 API", "category": "audio", "capability": "audio generation", "availability": "online", "summary": "Generate a song from a musical description and optional lyrics, with a title, tempo guidance, and a numeric seed string.", "bestFor": [], "docs": "https://www.hiapi.ai/docs/models/audio/lyria-3-5/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/lyria-3-5/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": false }, { "name": "lyrics", "type": "string", "required": false }, { "name": "title", "type": "string", "required": false }, { "name": "bpm", "type": "string", "required": false }, { "name": "length", "type": "integer", "required": false }, { "name": "seed", "type": "string", "required": false } ] }, { "id": "minimax-h3", "title": "MiniMax H3 API Reference: Parameters & Schema", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "This is the request contract for minimax-h3, covering POST /v1/tasks parameters, the three field combinations, media limits, callbacks, task results, and copyable code examples.", "bestFor": [], "docs": "https://www.hiapi.ai/docs/models/video/minimax-h3/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/minimax-h3/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "2K", "enum": [ "2K" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16", "adaptive" ] }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "first_frame_image", "type": "string", "required": false }, { "name": "last_frame_image", "type": "string", "required": false }, { "name": "image_urls", "type": "string[]", "required": false }, { "name": "video_urls", "type": "string[]", "required": false }, { "name": "audio_urls", "type": "string[]", "required": false } ] }, { "id": "minimax-h3-max", "title": "MiniMax H3 Max", "category": "video", "capability": "Text-to-video and image-to-video", "availability": "online", "summary": "Generate videos from text, or use images to guide the opening and ending frames. Supports 480P and 768P output with a duration of 5–15 seconds.", "bestFor": [ "Generate a video from text", "Animate an image" ], "docs": "https://www.hiapi.ai/docs/models/video/minimax-h3-max/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/minimax-h3-max/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "768P", "enum": [ "480P", "768P" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, { "name": "first_frame_image", "type": "string", "required": false }, { "name": "last_frame_image", "type": "string", "required": false } ] }, { "id": "minimax-music-1.5", "title": "MiniMax Music 1.5 API", "category": "audio", "capability": "Audio generation (text-to-music)", "availability": "online", "summary": "MiniMax Music 1.5: full songs up to 4 minutes with natural vocals and rich instrumentation, English or Chinese lyrics, structure tags, billed per song.", "bestFor": [ "Full song generation", "English & Chinese vocals", "Structured arrangement", "Per-song billing" ], "docs": "https://www.hiapi.ai/docs/models/audio/minimax-music-1-5/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/minimax-music-1-5/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "lyrics", "type": "string", "required": true }, { "name": "audio_format", "type": "enum", "required": false, "default": "mp3", "enum": [ "mp3", "wav", "pcm" ] }, { "name": "bitrate", "type": "enum", "required": false, "default": 256000, "enum": [ 32000, 64000, 128000, 256000 ] }, { "name": "sample_rate", "type": "enum", "required": false, "default": 44100, "enum": [ 16000, 24000, 32000, 44100 ] } ] }, { "id": "minimax-music-2.6", "title": "MiniMax Music 2.6 API", "category": "audio", "capability": "Audio generation (text-to-music)", "availability": "online", "summary": "MiniMax Music 2.6: complete songs with natural vocals and rich instrumentation; lyrics up to 3,500 characters, instrumental mode and auto-lyrics, English or Chinese, billed per song.", "bestFor": [ "Full song generation", "Instrumental / BGM", "Fine-grained structure", "Auto-lyrics" ], "docs": "https://www.hiapi.ai/docs/models/audio/minimax-music-2-6/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/minimax-music-2-6/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "lyrics", "type": "string", "required": false }, { "name": "is_instrumental", "type": "boolean", "required": false, "default": false }, { "name": "sample_rate", "type": "enum", "required": false, "default": 44100, "enum": [ 16000, 24000, 32000, 44100 ] }, { "name": "bitrate", "type": "enum", "required": false, "default": 256000, "enum": [ 32000, 64000, 128000, 256000 ] }, { "name": "audio_format", "type": "enum", "required": false, "default": "mp3", "enum": [ "mp3", "wav", "pcm" ] } ] }, { "id": "minimax-music-3", "title": "MiniMax Music 3 API", "category": "audio", "capability": "Audio generation (text-to-music)", "availability": "online", "summary": "MiniMax Music 3: high-fidelity full songs from text and lyrics with natural vocals and rich instrumentation; 1-300s length control and seed reproducibility, lossless WAV output, billed per second of requested duration.", "bestFor": [ "Full song generation", "Flexible length", "Reproducible results", "High-fidelity audio" ], "docs": "https://www.hiapi.ai/docs/models/audio/minimax-music-3/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/minimax-music-3/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "lyrics", "type": "string", "required": true }, { "name": "duration", "type": "number", "required": false, "default": 60 }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-audio-3.0-tts-flash", "title": "Qwen-Audio 3.0 TTS Flash API", "category": "audio", "capability": "Audio generation (text-to-speech)", "availability": "online", "summary": "Qwen-Audio 3.0 TTS Flash targets low-latency speech workflows for AI assistants, voice agents, and responsive interactions. HiAPI exposes complete speech controls and bills by effective character count.", "bestFor": [ "AI assistant speech", "Voice agents", "Batch notifications" ], "docs": "https://www.hiapi.ai/docs/models/audio/qwen-audio-3-0-text-to-speech-flash/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/qwen-audio-3-0-text-to-speech-flash/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "text", "type": "string", "required": true }, { "name": "voice", "type": "enum", "required": true, "default": "longanhuan_v3.6", "enum": [ "longanhuan_v3.6", "longjielidou_v3.6", "loongeva_v3.6", "loongjohn" ] }, { "name": "format", "type": "enum", "required": false, "default": "mp3", "enum": [ "pcm", "wav", "mp3", "opus" ] }, { "name": "sample_rate", "type": "enum", "required": false, "default": 22050, "enum": [ 8000, 16000, 22050, 24000, 44100, 48000 ] }, { "name": "volume", "type": "integer", "required": false, "default": 50 }, { "name": "rate", "type": "number", "required": false, "default": 1 }, { "name": "pitch", "type": "number", "required": false, "default": 1 }, { "name": "seed", "type": "integer", "required": false, "default": 0 }, { "name": "bit_rate", "type": "integer", "required": false, "default": 32 }, { "name": "language_hints", "type": "string[]", "required": false, "enum": [ "zh", "en", "fr", "de", "ja", "ko", "ru", "pt", "th", "id", "vi", "es", "it", "ms", "fil", "ar" ] }, { "name": "instruction", "type": "string", "required": false } ] }, { "id": "qwen-audio-3.0-tts-plus", "title": "Qwen-Audio 3.0 TTS Plus API", "category": "audio", "capability": "Audio generation (text-to-speech)", "availability": "online", "summary": "Qwen-Audio 3.0 TTS Plus targets high-quality speech production for voiceovers, video narration, and spoken content. HiAPI exposes complete speech controls and bills by effective character count.", "bestFor": [ "Professional voiceover", "Video narration", "Spoken content" ], "docs": "https://www.hiapi.ai/docs/models/audio/qwen-audio-3-0-text-to-speech-plus/", "docsZh": "https://www.hiapi.ai/docs/zh/models/audio/qwen-audio-3-0-text-to-speech-plus/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "text", "type": "string", "required": true }, { "name": "voice", "type": "enum", "required": true, "default": "longanlingxin", "enum": [ "longanlingxin", "longanlufeng" ] }, { "name": "format", "type": "enum", "required": false, "default": "mp3", "enum": [ "pcm", "wav", "mp3", "opus" ] }, { "name": "sample_rate", "type": "enum", "required": false, "default": 22050, "enum": [ 8000, 16000, 22050, 24000, 44100, 48000 ] }, { "name": "volume", "type": "integer", "required": false, "default": 50 }, { "name": "rate", "type": "number", "required": false, "default": 1 }, { "name": "pitch", "type": "number", "required": false, "default": 1 }, { "name": "seed", "type": "integer", "required": false, "default": 0 }, { "name": "bit_rate", "type": "integer", "required": false, "default": 32 }, { "name": "language_hints", "type": "string[]", "required": false, "enum": [ "zh", "en", "fr", "de", "ja", "ko", "ru", "pt", "th", "id", "vi", "es", "it", "ms", "fil", "ar" ] }, { "name": "instruction", "type": "string", "required": false } ] }, { "id": "qwen-image-2.0", "title": "Qwen Image 2.0", "category": "image", "capability": "Image generation", "availability": "online", "summary": "Qwen Image 2.0 is a low-cost image model with strong Chinese prompt and text-rendering behavior for posters, social images, and fast image generation.", "bestFor": [ "Chinese text rendering", "Low-cost batches", "Negative constraints", "Prompt optimization" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-2-0/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-2-0/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "size", "type": "enum", "required": false, "default": "2048*2048", "enum": [ "2688*1536", "2368*1728", "2048*2048", "1728*2368", "1536*2688" ] }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-image-2.0-pro", "title": "Qwen Image 2.0 Pro API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "The professional tier of Alibaba Qwen Image 2.0: stronger in-image text rendering, finer photorealistic detail and better adherence, up to 2048x2048, billed per image.", "bestFor": [ "Pro-grade Chinese text rendering", "Finer photorealism", "Commercial posters", "Flexible sizing" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-2-0-pro/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-2-0-pro/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "size", "type": "enum", "required": false, "default": "2048*2048", "enum": [ "2688*1536", "2368*1728", "2048*2048", "1728*2368", "1536*2688" ] }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-image-3.0-pro/image-to-image", "title": "Qwen Image 3.0 Pro Image to Image", "category": "image", "capability": "Image to image", "availability": "online", "summary": "Qwen Image 3.0 Pro Image to Image generates reference-guided images through the unified asynchronous API.", "bestFor": [ "High-fidelity refinement", "Format control" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-3-0-pro-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-3-0-pro-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-image-3.0-pro/text-to-image", "title": "Qwen Image 3.0 Pro Text to Image", "category": "image", "capability": "Text to image", "availability": "online", "summary": "Qwen Image 3.0 Pro Text to Image generates new images through the unified asynchronous API.", "bestFor": [ "High-fidelity final assets", "Format adaptation" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-3-0-pro-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-3-0-pro-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-image-3.0/image-to-image", "title": "Qwen Image 3.0 Image to Image", "category": "image", "capability": "Image to image", "availability": "online", "summary": "Qwen Image 3.0 Image to Image generates reference-guided images through the unified asynchronous API.", "bestFor": [ "Reference-guided redraws", "Format control" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-3-0-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-3-0-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "qwen-image-3.0/text-to-image", "title": "Qwen Image 3.0 Text to Image", "category": "image", "capability": "Text to image", "availability": "online", "summary": "Qwen Image 3.0 Text to Image generates new images through the unified asynchronous API.", "bestFor": [ "Fast creative iteration", "Format adaptation" ], "docs": "https://www.hiapi.ai/docs/models/image/qwen-image-3-0-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/qwen-image-3-0-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "3:2", "2:3", "4:3", "3:4", "16:9", "9:16", "21:9" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "1K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "recraft/remove-background", "title": "Recraft Remove Background API", "category": "image", "capability": "Image editing (background removal)", "availability": "online", "summary": "Recraft background removal: one image URL in, transparent-background PNG out — hair and fur-level edges preserved, built for product photos, portraits and design assets at scale.", "bestFor": [ "Product photos", "Portraits & pets", "Automated pipelines" ], "docs": "https://www.hiapi.ai/docs/models/image/recraft-remove-background/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/recraft-remove-background/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "image_url", "type": "string", "required": true } ] }, { "id": "seedance-2.0", "title": "Seedance 2.0 API", "category": "video", "capability": "Text-to-video / image-to-video / multimodal references", "availability": "online", "summary": "Seedance 2.0 exposes standard and ext routes under one model. Select a route with the top-level route field without changing the model name.", "bestFor": [ "Standard route", "ext route", "First/last frame control", "Synchronized audio" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-0/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-0/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "16:9", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "21:9", "adaptive" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "480p", "720p", "1080p", "4k" ] }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_video_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "return_last_frame", "type": "boolean", "required": false, "default": false }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "web_search", "type": "boolean", "required": false } ], "routes": [ { "route": "default", "label": "Standard", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "16:9", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "21:9", "adaptive" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "480p", "720p", "1080p", "4k" ] }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_video_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "return_last_frame", "type": "boolean", "required": false, "default": false }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "web_search", "type": "boolean", "required": false } ] }, { "route": "ext", "label": "ext", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "16:9", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "21:9", "adaptive" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "return_last_frame", "type": "boolean", "required": false, "default": false }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "web_search", "type": "boolean", "required": false } ] } ] }, { "id": "seedance-2.0-fast", "title": "Seedance 2.0 Fast API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "ByteDance Seedance 2.0 Fast is a high-speed video generation model supporting text-to-video, image-to-video (first/last frame), and multimodal reference-to-video (image/video/audio), with native audio, 480p/720p, and 4-15 second clips — all through the unified POST /v1/tasks endpoint.", "bestFor": [ "Short-form & social content", "Image-to-video (first/last frame)", "Multimodal reference-to-video", "Cost-sensitive generation at scale" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-0-fast/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-0-fast/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "21:9", "adaptive" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "480p", "720p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_video_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "web_search", "type": "boolean", "required": false, "default": false } ] }, { "id": "seedance-2.0-mini", "title": "Seedance 2.0 Mini API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "The cost-efficient member of ByteDance's Seedance 2.0 family — text-to-video and image-to-video in one model, with native synced audio and image/video/audio multimodal references, up to 720P and 4–15s, built for scalable short-video production.", "bestFor": [ "Cost-efficient short-video at scale", "Image-to-video / first-last-frame", "Multimodal reference generation", "Clips with native audio" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-0-mini/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-0-mini/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "resolution", "type": "enum", "required": true, "default": "720p", "enum": [ "480p", "720p" ] }, { "name": "duration", "type": "integer", "required": true, "default": 5 }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "21:9", "adaptive" ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_video_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false } ] }, { "id": "seedance-2.5/image-to-video", "title": "Seedance 2.5 Image to Video API", "category": "video", "capability": "First-frame / first-last-frame image-to-video", "availability": "online", "summary": "Generate up to 30 seconds from a first frame or a first/last-frame pair, with the output ratio following the first frame and optional synchronized audio.", "bestFor": [ "Animate a still", "Controlled transitions", "Sound-on video" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-5-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-5-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "adaptive", "enum": [ "adaptive" ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "output_format", "type": "enum", "required": false, "default": "mp4", "enum": [ "mp4", "mov" ] }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "web_search", "type": "boolean", "required": false, "default": false } ] }, { "id": "seedance-2.5/reference-to-video", "title": "Seedance 2.5 Reference to Video API", "category": "video", "capability": "Multimodal reference-to-video", "availability": "online", "summary": "Generate a new video using reference clips to guide action and camera movement. Add images for the subject and visual style, or audio for sound references.", "bestFor": [ "Subject and style references", "Motion and camera references", "Audio references" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-5-r2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-5-r2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "reference_video_urls", "type": "string[]", "required": true }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "480p", "enum": [ "480p", "720p", "1080p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "adaptive", "enum": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "output_format", "type": "enum", "required": false, "default": "mp4", "enum": [ "mp4", "mov" ] }, { "name": "web_search", "type": "boolean", "required": false, "default": false } ] }, { "id": "seedance-2.5/text-to-video", "title": "Seedance 2.5 Text to Video API", "category": "video", "capability": "Text-to-video", "availability": "online", "summary": "Generate a continuous clip of up to 30 seconds from text, with 720p or 1080p output, seven aspect ratios, and synchronized audio.", "bestFor": [ "Long-take storytelling", "Synchronized sound", "Multiple formats" ], "docs": "https://www.hiapi.ai/docs/models/video/seedance-2-5/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/seedance-2-5/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "adaptive", "enum": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "output_format", "type": "enum", "required": false, "default": "mp4", "enum": [ "mp4", "mov" ] }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "web_search", "type": "boolean", "required": false, "default": false } ] }, { "id": "seedream-4.5/image-to-image", "title": "Seedream 4.5 Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "Seedream 4.5 image editing: unified generation-editing with up to 14 references for edits, scene swaps and composites, consistent subjects and text, flat per-image billing.", "bestFor": [ "Multi-reference composition", "Scene & season edits", "Unified generation-editing", "Per-image billing" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-4-5-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-4-5-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "2K", "4K" ] } ] }, { "id": "seedream-4.5/text-to-image", "title": "Seedream 4.5 Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Seedream 4.5 text-to-image: ByteDance's community-favorite quality tier with solid photorealism and in-image text rendering, 8 ratios, 2K/4K at one flat per-image price.", "bestFor": [ "Photoreal & commercial assets", "In-image text rendering", "8 ratios + 4K", "Per-image billing" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-4-5-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-4-5-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "2K", "4K" ] } ] }, { "id": "seedream-5.0-lite/image-to-image", "title": "Seedream 5.0 Lite Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "ByteDance Seedream 5.0 Lite image editing: instruction-based edits with up to 14 reference images — rewrite in-image text, swap materials, blend references — while untouched areas stay intact. 2K and 4K cost the same.", "bestFor": [ "Instruction-based editing", "In-image text rewriting", "Multi-reference composites", "Material and mood swaps" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-5-0-lite-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-5-0-lite-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "2K", "4K" ] } ] }, { "id": "seedream-5.0-lite/text-to-image", "title": "Seedream 5.0 Lite Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "ByteDance Seedream 5.0 Lite text-to-image: reasoning-guided generation with real-time web knowledge and accurate multilingual text rendering — ideal for posters, menus and infographics, with 2K and 4K at the same price.", "bestFor": [ "Text-heavy layouts", "Web-grounded visuals", "4K delivery", "Flexible aspect ratios" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-5-0-lite-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-5-0-lite-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "2K", "4K" ] } ] }, { "id": "seedream-5.0-pro/image-to-image", "title": "Seedream 5.0 Pro Image to Image API", "category": "image", "capability": "Image generation (image-to-image)", "availability": "online", "summary": "HiAPI flagship image editing model: up to 10 reference images for consistent edits and composites, with 1K/2K resolution tiers.", "bestFor": [ "Consistency-preserving edits", "Multi-reference composites", "Tiered cost control" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-5-0-pro-image-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-5-0-pro-image-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_urls", "type": "string[]", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] } ] }, { "id": "seedream-5.0-pro/text-to-image", "title": "Seedream 5.0 Pro Text to Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "HiAPI flagship text-to-image model with upgraded fidelity and in-image text rendering: 1K/2K resolution tiers and 8 aspect ratios for posters, e-commerce and photorealistic work.", "bestFor": [ "Text-heavy layouts", "Photorealistic portraits and commercial finish", "Tiered cost control", "Flexible aspect ratios" ], "docs": "https://www.hiapi.ai/docs/models/image/seedream-5-0-pro-text-to-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/seedream-5-0-pro-text-to-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": true, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "2K", "enum": [ "1K", "2K" ] }, { "name": "output_format", "type": "enum", "required": false, "default": "png", "enum": [ "png", "jpeg" ] } ] }, { "id": "veo-3.1-fast/image-to-video", "title": "Veo 3.1 Fast Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Google Veo 3.1 Fast image-to-video API: fast, cost-efficient image animation with native audio, up to 4K, and 4 / 6 / 8-second clips — built for high-volume production and quick iteration.", "bestFor": [ "Batch image-to-video", "Cost-sensitive production", "Rapid motion iteration", "Aspect ratio control" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-fast-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-fast-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_url", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "duration", "type": "enum", "required": true, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "veo-3.1-fast/text-to-video", "title": "Veo 3.1 Fast API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Google Veo 3.1 Fast text-to-video API with native audio and up to 4K resolution. Generates 4 / 6 / 8-second clips that balance quality and speed for fast sound-on short videos.", "bestFor": [ "Sound-on short videos", "Fast creative validation", "Up to 4K delivery", "Landscape and portrait" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-fast-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-fast-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "duration", "type": "enum", "required": true, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "veo-3.1-lite/image-to-video", "title": "Veo 3.1 Lite Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Veo 3.1 Lite image-to-video animates one input image into a short clip with native audio at 720p or 1080p.", "bestFor": [ "Animate a still image", "Short social clips" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-lite-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-lite-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_url", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "enum", "required": false, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false }, { "name": "auto_fix", "type": "boolean", "required": false, "default": false }, { "name": "safety_tolerance", "type": "enum", "required": false, "default": "4", "enum": [ "1", "2", "3", "4", "5", "6" ] } ] }, { "id": "veo-3.1-lite/text-to-video", "title": "Veo 3.1 Lite Text to Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Veo 3.1 Lite text-to-video generates short clips with native audio at 720p or 1080p for fast creative iteration.", "bestFor": [ "Fast creative validation", "Short clips with native audio" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-lite-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-lite-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "720p", "enum": [ "720p", "1080p" ] }, { "name": "duration", "type": "enum", "required": false, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false }, { "name": "auto_fix", "type": "boolean", "required": false, "default": true }, { "name": "safety_tolerance", "type": "enum", "required": false, "default": "4", "enum": [ "1", "2", "3", "4", "5", "6" ] } ] }, { "id": "veo-3.1/image-to-video", "title": "Veo 3.1 Image to Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Google Veo 3.1 image-to-video API animates a still image into a cinematic clip with native audio, up to 4K, 4 / 6 / 8-second durations, and aspect ratio that follows the input.", "bestFor": [ "Animate product shots and posters", "Mood clips with native audio", "Up to 4K delivery", "Aspect ratio follows the input" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "image_url", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "auto", "enum": [ "auto", "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "duration", "type": "enum", "required": true, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "veo-3.1/text-to-video", "title": "Veo 3.1 Text to Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Google Veo 3.1 flagship text-to-video API with cinematic quality and native audio, up to 4K resolution, generating 4 / 6 / 8-second clips for ad-grade shorts and demanding creative work.", "bestFor": [ "Cinematic footage", "Narrative clips with native audio", "Up to 4K delivery", "Landscape and portrait" ], "docs": "https://www.hiapi.ai/docs/models/video/veo-3-1-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/veo-3-1-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16" ] }, { "name": "resolution", "type": "enum", "required": true, "default": "720p", "enum": [ "720p", "1080p", "4k" ] }, { "name": "duration", "type": "enum", "required": true, "default": 8, "enum": [ 4, 6, 8 ] }, { "name": "generate_audio", "type": "boolean", "required": false, "default": true }, { "name": "negative_prompt", "type": "string", "required": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "wan2.7-image/text-to-image", "title": "Wan 2.7 Image Pro API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Alibaba Tongyi Wanxiang Wan 2.7 Pro text-to-image: up to 4K (~4096² pixels) output, strong prompt adherence, prompts in both Chinese and English, with in-image long-text rendering as an officially highlighted capability — built for posters, e-commerce shots and text-heavy design assets.", "bestFor": [ "Chinese-language posters and e-commerce imagery", "4K print-grade output", "Design assets with in-image text", "Ultra-wide banners" ], "docs": "https://www.hiapi.ai/docs/models/image/wan2-7-t2i/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/wan2-7-t2i/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "16:9", "4:3", "21:9", "3:4", "9:16", "8:1", "1:8" ] }, { "name": "resolution", "type": "enum", "required": false, "default": "2K", "enum": [ "1K", "2K", "4K" ] }, { "name": "thinking_mode", "type": "boolean", "required": false, "default": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "wan2.7-video/image-to-video", "title": "Wan 2.7 Image-to-Video API", "category": "video", "capability": "Video generation (image-to-video)", "availability": "online", "summary": "Wan 2.7 Image-to-Video API animates a first frame into video and also supports last-frame, driving-audio, or first-clip media inputs.", "bestFor": [ "First-frame animation", "First-last transition", "Low-cost testing", "Stable media input" ], "docs": "https://www.hiapi.ai/docs/models/video/wan2-7-i2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/wan2-7-i2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "media", "type": "array", "required": true, "children": [ { "name": "type", "type": "enum", "required": true, "enum": [ "first_frame", "last_frame", "driving_audio", "first_clip" ] }, { "name": "url", "type": "string", "required": true } ] }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "resolution", "type": "enum", "required": false, "default": "1080P", "enum": [ "720P", "1080P" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "wan2.7-video/text-to-video", "title": "Wan 2.7 Text-to-Video API", "category": "video", "capability": "Video generation (text-to-video)", "availability": "online", "summary": "Wan 2.7 Text-to-Video API generates video directly from text and uses resolution plus ratio for quality, framing, and cost control.", "bestFor": [ "Text-to-video drafts", "Resolution cost control", "Ratio control", "Audio input" ], "docs": "https://www.hiapi.ai/docs/models/video/wan2-7-t2v/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/wan2-7-t2v/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "negative_prompt", "type": "string", "required": false, "default": "" }, { "name": "audio_url", "type": "string", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "1080P", "enum": [ "720P", "1080P" ] }, { "name": "ratio", "type": "enum", "required": false, "default": "16:9", "enum": [ "16:9", "9:16", "1:1", "4:3", "3:4" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "prompt_extend", "type": "boolean", "required": false, "default": true }, { "name": "watermark", "type": "boolean", "required": false, "default": false }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "wan3.0-video", "title": "Wan 3.0 Video API", "category": "video", "capability": "Video generation (all-purpose reference)", "availability": "online", "summary": "Wan 3.0 all-purpose video generation API for text, first/last frames, reference images, videos, audio, files, and webpages, with 480P, 720P, or 1080P output and optional synchronized audio.", "bestFor": [ "Text-to-video clips", "Multimodal reference control", "First/last-frame transitions" ], "docs": "https://www.hiapi.ai/docs/models/video/wan3-0-video/", "docsZh": "https://www.hiapi.ai/docs/zh/models/video/wan3-0-video/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "first_frame_url", "type": "string", "required": false }, { "name": "last_frame_url", "type": "string", "required": false }, { "name": "reference_image_urls", "type": "string[]", "required": false }, { "name": "reference_video_urls", "type": "string[]", "required": false }, { "name": "reference_audio_urls", "type": "string[]", "required": false }, { "name": "reference_file_urls", "type": "string[]", "required": false }, { "name": "reference_link_urls", "type": "string[]", "required": false }, { "name": "resolution", "type": "enum", "required": false, "default": "1080P", "enum": [ "480P", "720P", "1080P" ] }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "adaptive", "enum": [ "adaptive", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, { "name": "duration", "type": "integer", "required": false, "default": 5 }, { "name": "audio", "type": "boolean", "required": false, "default": true }, { "name": "seed", "type": "integer", "required": false } ] }, { "id": "z-image", "title": "Z-Image API", "category": "image", "capability": "Image generation (text-to-image)", "availability": "online", "summary": "Tongyi Z-Image Turbo: an efficient 6B photorealistic text-to-image model with 8-step distilled inference for near-instant generation, accurate bilingual (Chinese and English) in-image text rendering, and one of the lowest per-image prices — built for high-volume and latency-sensitive workloads.", "bestFor": [ "High-volume, low-cost generation", "Photorealistic portraits and photography looks", "Short Chinese and English in-image text", "Latency-sensitive real-time apps" ], "docs": "https://www.hiapi.ai/docs/models/image/z-image/", "docsZh": "https://www.hiapi.ai/docs/zh/models/image/z-image/", "protocol": "tasks", "endpoint": "https://api.hiapi.ai/v1/tasks", "input": [ { "name": "prompt", "type": "string", "required": true }, { "name": "aspect_ratio", "type": "enum", "required": false, "default": "1:1", "enum": [ "1:1", "4:3", "3:4", "16:9", "9:16" ] } ] } ] }