# Glio API The most cost-effective unified API for AI media generation. One interface to 90+ models from multiple providers (Kling, Midjourney, Veo3, Suno, ElevenLabs, and more). - Generate videos, images, and audio with a single API - Async workflow: create job -> poll -> get result - Pay per generation in GL tokens (1 GL = $0.01 USD) ## Quick Start Base URL: https://api.glio.io Auth Header: Authorization: Bearer YOUR_API_KEY ## Endpoints ### Jobs API (requires auth) POST /v1/jobs - Create generation job Body: {"model": "model-alias", "params": {...}} Returns: {"id": "job_xxx", "status": "pending"} GET /v1/jobs/{id} - Get job status Poll every 10-15s until status = "completed" or "failed" Returns: {"id": "...", "status": "completed", "result": {...}} ### LLM Sync API (requires auth) POST /v1/chat/completions - OpenAI-compatible chat completions (sync/stream) Body: {"model": "gpt-5-2", "messages": [...], "stream": false} POST /v1/embeddings - OpenAI-compatible embeddings Body: {"model": "...", "input": "text or text[]"} ### Discovery API GET /v1/account/ - Get account balance and tier (requires auth) GET /v1/models/ - List models with filtering (?type=video&brand=kling) GET /v1/taxonomy/ - Category hierarchy for dynamic UI building POST /api/estimate-cost/ - Calculate exact cost for specific params ## Model Parameters For exact parameters and example request for any model: https://api.glio.io/openapi/models/{model-alias}.json Example: https://api.glio.io/openapi/models/kling-v2.6-pro-t2v.json ## Available Models ### Video Generation - kling-3.0 - Kling 3.0 with single-shot and multi-shot generation modes. - kling-v2.6-pro-t2v - High-end cinematic video generation with native audio support. - kling-v2.6-pro-i2v - High-end cinematic video from source image with native audio support. - kling-v2.1-standard-i2v - Cost-effective video from images with the Standard tier - kling-v2.1-pro-i2v - High-quality video from images with the Pro tier - kling-v2.1-master-t2v - Premium quality video generation with the Master tier - kling-v2.1-master-i2v - Premium quality video from images with the Master tier - kling-v2.5-turbo-i2v - Fast video generation from source image. Optimized for physics and ... - kling-v2.5-turbo-t2v - Fast video generation optimized for physics and motion. No native a... - kling-o1-i2v - Kling O1 high-quality video from image with optional end frame cont... - kling-o1-v2v-edit - Transform existing video with text-guided edits. - kling-o1-v2v-ref - Generate video using source video and reference images. - kling-o1-ref2v - Generate video from multiple reference images and character elements. - kling-avatar-pro - Premium lip sync video generation from image and audio (1080p) - kling-avatar-standard - Lip sync video generation from image and audio (720p) - kling-v2.6-motion-control - Transfer motion from a reference video to a character image - grok-imagine-t2v - Generate videos from text prompts using Grok Imagine - grok-imagine-i2v - Generate videos from images using Grok Imagine - veo3-t2v - Google Veo 3.1 text-to-video generation with quality and fast modes - veo3-i2v - Google Veo 3.1 image-to-video generation. Use 1 image for dynamic e... - veo3-ref2v - Google Veo 3.1 reference-to-video generation. Generate videos based... - sora-2-t2v - OpenAI Sora 2 text-to-video generation - sora-2-i2v - OpenAI Sora 2 image-to-video generation - midjourney-video - Generate standard definition video from images using Midjourney AI - midjourney-video-hd - Generate high definition video from images using Midjourney AI - runway-t2v - Runway Gen-3 Alpha text-to-video generation with 5-10 second clips - runway-i2v - Runway Gen-3 Alpha image-to-video generation - animate your images - luma-ray2-v2v - Modify video using AI based on text prompt. Max 10s input video. - hailuo-02-standard-i2v - Budget-friendly image-to-video with duration and resolution control. - hailuo-02-pro-t2v - High-quality text-to-video generation with 1080p output. - hailuo-02-pro-i2v - High-quality image-to-video with start/end frame support. - hailuo-02-standard-t2v - Budget-friendly text-to-video generation with duration control. - hailuo-2.3-standard-i2v - Latest Hailuo 2.3 Standard with 1080p support at budget price. - hailuo-2.3-pro-i2v - Latest Hailuo 2.3 Pro with 1080p support and improved quality. - seedance-v1.5-pro-t2v - High-quality text-to-video generation with optional audio. - seedance-v1.5-pro-i2v - High-quality image-to-video generation with optional audio. Support... - seedance-v1-pro-t2v - High-quality text-to-video generation with full parameter control. - seedance-v1-pro-i2v - High-quality image-to-video generation with full parameter control. - seedance-v1-pro-fast-i2v - Fast video generation from images with simplified parameters. Limit... - seedance-v1-lite-t2v - Budget-friendly text-to-video generation with good quality. - seedance-v1-lite-i2v - Budget-friendly image-to-video with start/end image support. - wan-2-6-t2v - High-quality video generation from text prompts with 5-15 second du... - wan-2-6-i2v - Generate videos from images with 5-15 second duration - wan-2-2-speech-to-video - Generate lip-synced video from image and audio - wan-2-6-v2v - Transform videos with text prompts, 5-10 second duration - wan-2-2-animate-move - Transfer motion from video to image - wan-2-2-turbo-t2v - Fast video generation from text with acceleration options - wan-2-2-animate-replace - Replace character in video with image - wan-2-2-turbo-i2v - Fast video generation from image with acceleration options - topaz-video-upscale - AI-powered video upscaling up to 4x resolution - ltxv-2 - High-quality video generation with audio and up to 4K resolution. - ltxv-2-fast - Fast video generation with audio and up to 4K resolution. - infinitalk-from-audio - MeiGen-AI InfiniteTalk lip-sync video generation from audio and image ### Image Generation - grok-imagine-t2i - Generate high-quality photorealistic images from text prompts using... - grok-imagine-i2i - Transform images with text prompts using Grok Imagine - grok-imagine-upscale - Upscale previously generated Grok Imagine images to higher resolution - nano-banana-pro-t2i - High-quality image generation with sharp structural accuracy and pr... - nano-banana-pro-i2i - Image editing with inpainting, outpainting, and style transfer capa... - google-imagen4 - Google Imagen 4 text-to-image with Standard, Fast, and Ultra qualit... - gpt-image-1.5-t2i - Generate photorealistic images from text prompts using GPT Image 1.5 - gpt-image-1.5-i2i - Transform and edit images with text prompts using GPT Image 1.5 - midjourney - High-quality artistic image generation with multiple version support - midjourney-i2i - Transform images using Midjourney AI with style and content preserv... - midjourney-style - Generate images using another image's style as reference - midjourney-omni - Place characters and objects from reference image into new scenes - seedream-4-5-text-to-image - Latest Seedream 4.5 with premium image quality from ByteDance. - seedream-4-5-edit - Latest Seedream 4.5 image editing with premium quality from ByteDance. - bytedance-seedream-v4-text-to-image - ByteDance Seedream v4 with enhanced image quality and resolution op... - bytedance-seedream-v4-edit - ByteDance Seedream v4 image editing with enhanced quality and resol... - bytedance-seedream - High-quality image generation from ByteDance Seedream v3. - qwen-t2i - Qwen image generation from text prompts - qwen-i2i - Transform images with text prompts - qwen-image-edit - Edit images with natural language instructions - topaz-image-upscale - AI-powered image upscaling with Topaz technology. Upscale images up... - ideogram-v3-reframe - Reframe images to different aspect ratios with AI-generated fill - ideogram-character - Generate images featuring a character from a reference photo - ideogram-character-edit - Edit images with character-consistent inpainting using a mask - ideogram-character-remix - Remix an image with a consistent character from a reference photo - recraft-crisp-upscale - AI-powered crisp image upscaling by Recraft - recraft-remove-background - AI-powered background removal by Recraft - flux-2-pro-t2i - High-quality text-to-image generation with Flux 2 Pro - flux-2-pro-i2i - Transform and edit images with Flux 2 Pro - flux-2-flex-t2i - Flexible text-to-image generation with Flux 2 Flex - flux-2-flex-i2i - Flexible image transformation with Flux 2 Flex ### Audio Generation - suno - AI-powered music generation with multi-track output and custom styl... - suno-add-vocals - Add vocal singing to existing audio files - suno-add-instrumental - Add instrumental accompaniment to existing audio - elevenlabs-tts-multilingual - High-quality multilingual text-to-speech with 21 voices and adjusta... - elevenlabs-tts-turbo - Fast, low-latency text-to-speech with language enforcement support - elevenlabs-sfx - AI-generated sound effects from text descriptions with looping and ... - elevenlabs-isolation - Isolate voice from background noise and music in audio files ### Text Generation - gpt-5-2 - Latest OpenAI reasoning and chat model. - text-embedding-3-large - OpenAI high-quality embedding model. - suno-lyrics - AI-powered lyrics generation with multiple variations - elevenlabs-stt - High-quality speech-to-text transcription with speaker diarization ... - claude-4-5-opus - Anthropic flagship model for advanced reasoning. ## Source of Truth OpenAPI specs are the single source of truth for parameters. - Full spec: https://api.glio.io/openapi.json - Per-model: https://api.glio.io/openapi/models/{model-alias}.json ## Links - API Base URL: https://api.glio.io - Documentation: https://glio.io/docs/ - Dashboard: https://glio.io/app/ --- Generated: 2026-02-17T23:54:30Z