# inference.sh - Complete Documentation & Blog > The AI agent runtime. Build agents that can actually do things—with durable execution, human-in-the-loop approval, and real-time observability. This file contains the complete text content of all inference.sh documentation and blog pages. For the summary version, see: https://inference.sh/llms.txt --- # DOCUMENTATION --- # BLOG Articles, tutorials, and insights on building production AI agents. --- # APPS Pre-built AI apps and tools available on the inference.sh platform. --- ## Featured Apps ### google/veo-3-1-fast **URL:** https://app.inference.sh/apps/google/veo-3-1-fast **Category:** video Veo 3.1 Fast via Vertex AI - Generate videos from text prompts or images with optional audio --- ### infsh/hunyuanvideo-foley **URL:** https://app.inference.sh/apps/infsh/hunyuanvideo-foley **Category:** video Synthesizes realistic sound effects and audio tracks based on your video content and written descriptions. --- ## All Apps ### infsh/remotion-render **URL:** https://app.inference.sh/apps/infsh/remotion-render **Category:** video Render videos from React/Remotion component code — pass TSX, get MP4 --- ### openrouter/minimax-m-25 **URL:** https://app.inference.sh/apps/openrouter/minimax-m-25 **Category:** chat MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. --- ### falai/kokoro-tts **URL:** https://app.inference.sh/apps/falai/kokoro-tts **Category:** audio Kokoro TTS - Lightweight text-to-speech with multiple languages and voices --- ### xai/grok-imagine-image-pro **URL:** https://app.inference.sh/apps/xai/grok-imagine-image-pro **Category:** image Generate and edit images using xAI's Grok Imagine Pro model. Supports text-to-image and image editing with multiple aspect ratios. --- ### openrouter/claude-opus-46 **URL:** https://app.inference.sh/apps/openrouter/claude-opus-46 **Category:** chat Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. --- ### falai/dia-tts **URL:** https://app.inference.sh/apps/falai/dia-tts **Category:** audio Dia TTS - Generate realistic dialogue with emotion control, natural nonverbals, and voice cloning --- ### infsh/agent-browser **URL:** https://app.inference.sh/apps/infsh/agent-browser **Category:** other Browser automation for AI agents. Navigate, interact with @e refs, take screenshots, record video with cursor indicator, execute JavaScript. Supports proxy configuration. --- ### x/post-tweet **URL:** https://app.inference.sh/apps/x/post-tweet **Category:** social Post tweets to X.com with text (280 char limit) and optional media. Supports up to 4 images or 1 video/GIF. Can reply to or quote other tweets. Images over 5MB are auto-resized. --- ### x/dm-send **URL:** https://app.inference.sh/apps/x/dm-send **Category:** social Send a direct message on X.com. Requires the recipient's user ID (not username). Text-only messages; media attachments are not supported. --- ### x/user-follow **URL:** https://app.inference.sh/apps/x/user-follow **Category:** social Follow a user on X.com by user ID. Succeeds silently if already following. --- ### x/user-get **URL:** https://app.inference.sh/apps/x/user-get **Category:** social Get a user profile from X.com by ID or username. Returns bio, follower/following counts, tweet count, verified status, and profile image URL. --- ### x/post-retweet **URL:** https://app.inference.sh/apps/x/post-retweet **Category:** social Retweet a post on X.com by post ID. Succeeds silently if already retweeted. --- ### x/post-like **URL:** https://app.inference.sh/apps/x/post-like **Category:** social Like a post on X.com by post ID. Succeeds silently if already liked. --- ### x/post-delete **URL:** https://app.inference.sh/apps/x/post-delete **Category:** social Delete a post from X.com by post ID. Can only delete posts authored by the authenticated account. --- ### x/post-get **URL:** https://app.inference.sh/apps/x/post-get **Category:** social Get a post by ID from X.com. Returns text, author ID, creation date, and engagement metrics (likes, retweets, replies, quotes). --- ### x/post-create **URL:** https://app.inference.sh/apps/x/post-create **Category:** social Create posts on X.com with text (280 char limit) and optional media. Supports up to 4 images or 1 video/GIF. Can reply to or quote other posts. Images over 5MB are auto-resized. --- ### xai/grok-imagine-video **URL:** https://app.inference.sh/apps/xai/grok-imagine-video **Category:** video Generate and edit videos using xAI's Grok Imagine Video model. Supports text-to-video, image-to-video, and video editing with configurable duration and resolution. --- ### xai/grok-imagine-image **URL:** https://app.inference.sh/apps/xai/grok-imagine-image **Category:** image Generate and edit images using xAI's Grok Imagine model. Supports text-to-image and image editing with multiple aspect ratios. --- ### google/veo-3-1 **URL:** https://app.inference.sh/apps/google/veo-3-1 **Category:** video Veo 3.1 via Vertex AI - Advanced video generation with frame interpolation, reference images, and audio generation --- ### google/veo-3-fast **URL:** https://app.inference.sh/apps/google/veo-3-fast **Category:** video Veo 3 Fast via Vertex AI - Fast video generation with audio from text prompts and images --- ### google/veo-3 **URL:** https://app.inference.sh/apps/google/veo-3 **Category:** video Veo 3 via Vertex AI - Generate videos with audio from text prompts and images --- ### google/veo-2 **URL:** https://app.inference.sh/apps/google/veo-2 **Category:** video Veo 2 via Vertex AI - Generate high-quality realistic videos from text prompts --- ### falai/flux-dev-lora **URL:** https://app.inference.sh/apps/falai/flux-dev-lora **Category:** image Text-to-image and image-to-image generation with FLUX.1 [dev] LoRA support. Custom style adaptation and fine-tuned model variations from Black Forest Labs. --- ### falai/flux-2-klein-lora **URL:** https://app.inference.sh/apps/falai/flux-2-klein-lora **Category:** image Text-to-image and image-to-image generation with FLUX.2 [klein] LoRA support. Available in 4B and 9B parameter sizes. Custom style adaptation and fine-tuned model variations from Black Forest Labs. --- ### bytedance/omnihuman-1-5 **URL:** https://app.inference.sh/apps/bytedance/omnihuman-1-5 **Category:** video Multi-character audio-driven avatar video generation. Takes a portrait image + audio and generates a video where the person speaks/sings in sync. Supports specifying which character to drive. --- ### bytedance/omnihuman-1-0 **URL:** https://app.inference.sh/apps/bytedance/omnihuman-1-0 **Category:** video Audio-driven avatar video generation. Takes a portrait image + audio and generates a video where the person speaks/sings in sync with the audio. --- ### bytedance/seedream-3-0-t2i **URL:** https://app.inference.sh/apps/bytedance/seedream-3-0-t2i **Category:** image Generate cinematic quality images from text prompts with accurate text rendering using ByteDance's Seedream 3.0 T2I model via BytePlus ARK API. --- ### bytedance/seedream-4-0 **URL:** https://app.inference.sh/apps/bytedance/seedream-4-0 **Category:** image Generate high-quality 2K-4K images from text prompts with optional image-to-image generation using ByteDance's Seedream 4.0 model via BytePlus ARK API. --- ### bytedance/seedream-4-5 **URL:** https://app.inference.sh/apps/bytedance/seedream-4-5 **Category:** image Generate high-quality 2K-4K images from text prompts with optional image-to-image generation using ByteDance's Seedream 4.5 model via BytePlus ARK API. --- ### bytedance/seedance-1-0-lite **URL:** https://app.inference.sh/apps/bytedance/seedance-1-0-lite **Category:** video Lightweight 720p video generation. Automatically uses image-to-video mode when an image is provided, or text-to-video mode otherwise. --- ### bytedance/seedance-1-0-pro **URL:** https://app.inference.sh/apps/bytedance/seedance-1-0-pro **Category:** video Generate high-quality videos up to 1080p from text prompts with optional first-frame image control using ByteDance's Seedance 1.0 Pro model. --- ### bytedance/seedance-1-0-pro-fast **URL:** https://app.inference.sh/apps/bytedance/seedance-1-0-pro-fast **Category:** video Fast high-quality video generation up to 1080p from text prompts with optional first-frame image control using ByteDance's Seedance 1.0 Pro Fast model. --- ### bytedance/seedance-1-5-pro **URL:** https://app.inference.sh/apps/bytedance/seedance-1-5-pro **Category:** video Generate high-quality videos from text prompts with optional first-frame image control using ByteDance's Seedance 1.5 Pro model via BytePlus ARK API. --- ### falai/imagine-art-1-5-pro-preview **URL:** https://app.inference.sh/apps/falai/imagine-art-1-5-pro-preview **Category:** image Advanced text-to-image model creating ultra-high-fidelity 4K visuals with lifelike realism and refined aesthetics. --- ### infsh/youtube-downloader **URL:** https://app.inference.sh/apps/infsh/youtube-downloader **Category:** audio Download YouTube videos and audio with customizable quality, format, and codec options. Supports audio-only extraction, video+audio, or video-only downloads. --- ### google/gemini-2-5-flash-image **URL:** https://app.inference.sh/apps/google/gemini-2-5-flash-image **Category:** image Gemini 2.5 Flash Image via Vertex AI - Advanced image generation model powered by Google Cloud --- ### google/gemini-3-pro-image-preview **URL:** https://app.inference.sh/apps/google/gemini-3-pro-image-preview **Category:** image Gemini 3 Pro Image Preview via Vertex AI - Advanced image generation model powered by Google Cloud --- ### infsh/post-tweet **URL:** https://app.inference.sh/apps/infsh/post-tweet **Category:** social Post tweets to X.com (Twitter) --- ### tavily/search-assistant **URL:** https://app.inference.sh/apps/tavily/search-assistant **Category:** text A search assistant that browses the internet to deliver comprehensive results, including AI-generated answers, images, and detailed sources. --- ### openrouter/kimi-k2-thinking **URL:** https://app.inference.sh/apps/openrouter/kimi-k2-thinking **Category:** chat A powerful open-source thinking agent that excels at complex, multi-step problem-solving and consistently uses tools effectively over extended operations. --- ### infsh/caption-videos **URL:** https://app.inference.sh/apps/infsh/caption-videos **Category:** other Add captions to videos using an existing caption file, such as those generated by a speech-to-text service. --- ### tavily/extract **URL:** https://app.inference.sh/apps/tavily/extract **Category:** text Extracts clean, readable content, including text and images, from specified webpages, supporting batch processing for multiple URLs. --- ### infsh/array-switch **URL:** https://app.inference.sh/apps/infsh/array-switch **Category:** other Allows you to choose between two different inputs based on a condition applied to an array of data. --- ### infsh/extract-last-frame **URL:** https://app.inference.sh/apps/infsh/extract-last-frame **Category:** video Save a specific frame from the end of a video as a static image file. --- ### infsh/media-merger **URL:** https://app.inference.sh/apps/infsh/media-merger **Category:** video Merges multiple videos and images together using customized transitions. --- ### infsh/array-element-switch **URL:** https://app.inference.sh/apps/infsh/array-element-switch **Category:** other Selects one of two possible inputs based on a comparison check within an array. --- ### infsh/mask-image **URL:** https://app.inference.sh/apps/infsh/mask-image **Category:** other Combines two images—a main image and a semi-transparent mask—to selectively hide or reveal parts of the main image, creating a partially transparent result. --- ### infsh/falconsai-nsfw-detection **URL:** https://app.inference.sh/apps/infsh/falconsai-nsfw-detection **Category:** image Detects NSFW content in images and videos using Falconsai/nsfw_image_detection model. For videos, samples frames at configurable intervals. --- ### infsh/video-audio-merger **URL:** https://app.inference.sh/apps/infsh/video-audio-merger **Category:** other Merge video and audio files easily, with the flexibility to keep the original audio from the video. --- ### infsh/text-to-file **URL:** https://app.inference.sh/apps/infsh/text-to-file **Category:** other Creates a new document using the text and file name you specify. --- ### infsh/python-executor **URL:** https://app.inference.sh/apps/infsh/python-executor **Category:** text Runs and executes Python programming code in a safe environment. --- ### infsh/search-assistant **URL:** https://app.inference.sh/apps/infsh/search-assistant **Category:** text Helps users create and refine search queries, retrieve relevant results from various sources, and generate overviews or summaries of the information found. --- ### exa/answer **URL:** https://app.inference.sh/apps/exa/answer **Category:** text Provides direct, factual answers to your questions by analyzing and summarizing relevant information from web search results. --- ### falai/fabric-1-0 **URL:** https://app.inference.sh/apps/falai/fabric-1-0 **Category:** video Creates videos where an image appears to talk using advanced lip-sync technology. --- ### infsh/boolean-switch **URL:** https://app.inference.sh/apps/infsh/boolean-switch **Category:** other Selects one of two possible inputs based on whether a condition is true or false. --- ### falai/pixverse-lipsync **URL:** https://app.inference.sh/apps/falai/pixverse-lipsync **Category:** video Generates highly realistic lipsync animations from any audio input. --- ### openrouter/intellect-3 **URL:** https://app.inference.sh/apps/openrouter/intellect-3 **Category:** chat Intellect 3 --- ### infsh/wan2-2-i2i-a14b **URL:** https://app.inference.sh/apps/infsh/wan2-2-i2i-a14b **Category:** image Creates videos from images and enhances video quality using a built-in upscaler. --- ### exa/extract **URL:** https://app.inference.sh/apps/exa/extract **Category:** text Retrieves and analyzes content from web pages using sophisticated technology to provide accurate insights. --- ### openrouter/claude-opus-45 **URL:** https://app.inference.sh/apps/openrouter/claude-opus-45 **Category:** chat Claude Opus 4.5 --- ### openrouter/gemini-3-pro-preview **URL:** https://app.inference.sh/apps/openrouter/gemini-3-pro-preview **Category:** chat Gemini 3 Pro Preview --- ### openrouter/claude-sonnet-45 **URL:** https://app.inference.sh/apps/openrouter/claude-sonnet-45 **Category:** chat Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. --- ### infsh/numerical-switch **URL:** https://app.inference.sh/apps/infsh/numerical-switch **Category:** other Selects one of two inputs based on a condition involving numerical comparison. --- ### falai/topaz-video-upscaler **URL:** https://app.inference.sh/apps/falai/topaz-video-upscaler **Category:** video Enhances and increases the resolution of your videos, turning lower quality footage into sharp, high-definition results. --- ### infsh/get-item-in-list **URL:** https://app.inference.sh/apps/infsh/get-item-in-list **Category:** other Returns a specific element from a list based on its position. --- ### infsh/html-to-image **URL:** https://app.inference.sh/apps/infsh/html-to-image **Category:** other Turns web content into customizable PNG or JPEG images. --- ### infsh/extract-media-duration **URL:** https://app.inference.sh/apps/infsh/extract-media-duration **Category:** other Extracts the length of video and audio files. --- ### infsh/text-templating **URL:** https://app.inference.sh/apps/infsh/text-templating **Category:** other Dynamically generate content by combining a fixed template with specific data inputs. --- ### infsh/video-audio-extractor **URL:** https://app.inference.sh/apps/infsh/video-audio-extractor **Category:** other Extracts audio from video files and removes the original audio to create silent videos. --- ### infsh/string-switch **URL:** https://app.inference.sh/apps/infsh/string-switch **Category:** other Compares strings to decide which of two inputs to use. --- ### falai/wan-2-5 **URL:** https://app.inference.sh/apps/falai/wan-2-5 **Category:** video Creates high-quality, animated videos instantly from any static image. --- ### infsh/text-split **URL:** https://app.inference.sh/apps/infsh/text-split **Category:** other Splits a piece of text into smaller sections based on a specified separating character or phrase. --- ### infsh/stitch-images **URL:** https://app.inference.sh/apps/infsh/stitch-images **Category:** image Combine multiple photos horizontally or vertically into a single image or collage. --- ### infsh/media-analyzer **URL:** https://app.inference.sh/apps/infsh/media-analyzer **Category:** multimodal Analyzes images and audio files to provide detailed insights based on your questions. --- ### openrouter/claude-haiku-45 **URL:** https://app.inference.sh/apps/openrouter/claude-haiku-45 **Category:** chat A very fast and economical AI designed for real-time uses and everyday business and coding tasks, offering performance similar to much larger, pricier options. --- ### falai/wan-2-5-i2v **URL:** https://app.inference.sh/apps/falai/wan-2-5-i2v **Category:** video Generates high-quality video content from static images. --- ### infsh/bounce-repeat-videos **URL:** https://app.inference.sh/apps/infsh/bounce-repeat-videos **Category:** other Repeats a video segment by playing it forward and then immediately backward to create a bouncing, looping effect. --- ### infsh/rodin-3d-generator **URL:** https://app.inference.sh/apps/infsh/rodin-3d-generator **Category:** 3d Generates high-quality 3D models simply by using text descriptions or uploading an image. --- ### exa/search **URL:** https://app.inference.sh/apps/exa/search **Category:** text A smart web search that combines different methods, including AI, to find highly relevant links and context, especially useful for complex or exploratory queries. --- ### openrouter/glm-46 **URL:** https://app.inference.sh/apps/openrouter/glm-46 **Category:** chat A powerful, open-source language system excelling in advanced coding, complex reasoning, and integrating tools for sophisticated tasks. --- ### falai/reve **URL:** https://app.inference.sh/apps/falai/reve **Category:** image Reve - Image generation, editing, and style remix via text prompts --- ### falai/topaz-image-upscaler **URL:** https://app.inference.sh/apps/falai/topaz-image-upscaler **Category:** image Enhance and increase the size of images without losing quality, making your photos look sharper and more detailed. --- # Additional Resources - Website: https://inference.sh - Documentation: https://inference.sh/docs - Blog: https://inference.sh/blog - Apps: https://inference.sh/apps - GitHub: https://github.com/inference-sh - Python SDK: https://pypi.org/project/inferencesh/ - npm SDK: https://www.npmjs.com/package/inferencesh/