# API Stock documentation

> One API key, prepaid balance, and integration surface for AI media and chat models.

- [Agent API](https://docs.api-stock.com/en/docs/agent): Run tasks across models with a shared spending limit, persistent conversations and validated JSON results.
- [Authentication](https://docs.api-stock.com/en/docs/authentication): Authenticate API Stock requests and protect or rotate API keys.
- [API endpoints](https://docs.api-stock.com/en/docs/endpoints): Every endpoint of the API Stock API, grouped by area.
- [Errors and limits](https://docs.api-stock.com/en/docs/errors): Handle request errors, failed tasks, rate limits, and retries.
- [Files and media URLs](https://docs.api-stock.com/en/docs/files): Supply public input URLs and persist generated files safely.
- [Quick start](https://docs.api-stock.com/en/docs/getting-started): Create an API key, run a model and retrieve the result.
- [MCP server](https://docs.api-stock.com/en/docs/mcp): Connect Codex, Claude Code and other MCP clients to API Stock and generate media from an AI agent.
- [FLUX 3 Image](https://docs.api-stock.com/en/docs/models/image/flux-3-image): Generate and edit images with up to 10 references, flexible framing, web search and resolution tiers up to 4K.
- [GPT Image 2.5 Flare](https://docs.api-stock.com/en/docs/models/image/gpt-image-2.5-flare): Generate and edit images with the Flare variant of GPT Image 2.5, with output up to 4K.
- [GPT Image 2.5 Sunburst](https://docs.api-stock.com/en/docs/models/image/gpt-image-2.5-sunburst): Generate and edit images with the Sunburst variant of GPT Image 2.5, with output up to 4K.
- [GPT Image 2](https://docs.api-stock.com/en/docs/models/image/gpt-image-2): Generate and edit images with flexible aspect ratios, resolution, and quality controls.
- [Grok Imagine 1.5 Image](https://docs.api-stock.com/en/docs/models/image/grok-imagine-1.5-image): Generate or transform images from a prompt and optional reference image.
- [Grok Imagine 2.0 Image](https://docs.api-stock.com/en/docs/models/image/grok-imagine-2.0-image): Generate batches of images from a text prompt in common aspect ratios.
- [Image models](https://docs.api-stock.com/en/docs/models/image): All active image models and their integration pages.
- [Nano Banana 2 Lite](https://docs.api-stock.com/en/docs/models/image/nano-banana-2-lite): Fast 1K image generation and editing from text and reference images.
- [Nano Banana 2.1](https://docs.api-stock.com/en/docs/models/image/nano-banana-2.1): Generate and edit images from prompts and reference images at multiple resolutions.
- [Nano Banana 2](https://docs.api-stock.com/en/docs/models/image/nano-banana-2): Generate and edit images from prompts and reference images at multiple resolutions.
- [Nano Banana Pro](https://docs.api-stock.com/en/docs/models/image/nano-banana-pro): Quality-focused image generation and editing with reference-image support.
- [Nano Banana](https://docs.api-stock.com/en/docs/models/image/nano-banana): Create and edit images from a prompt and optional reference images.
- [Seedream 4.5](https://docs.api-stock.com/en/docs/models/image/seedream-4-5): Generate and edit detailed images from prompts and reference images.
- [Seedream 5.0 Flash](https://docs.api-stock.com/en/docs/models/image/seedream-5-0-flash): Fast image generation and editing at 1K, 1.5K or 2K, with up to 10 reference images.
- [Seedream 5.0 Lite](https://docs.api-stock.com/en/docs/models/image/seedream-5-0-lite): Fast image generation and editing from text and reference images.
- [Seedream 5.0 Pro](https://docs.api-stock.com/en/docs/models/image/seedream-5-0-pro): Quality-focused image generation and editing with up to 2K output.
- [Wan 2.7 Image](https://docs.api-stock.com/en/docs/models/image/wan2.7-image): Generate and edit images with aspect-ratio, pixel-size, and seed controls.
- [Z-Image](https://docs.api-stock.com/en/docs/models/image/z-image): Generate and edit images from text with optional reference images and safety control.
- [Models](https://docs.api-stock.com/en/docs/models): Active API Stock models with complete per-model integration guides.
- [Music models](https://docs.api-stock.com/en/docs/models/music): All active music models and their integration pages.
- [Suno: add-instrumental](https://docs.api-stock.com/en/docs/models/music/suno/add-instrumental): Add an instrumental arrangement to audio. Complete request and parameter reference.
- [Suno: add-stem](https://docs.api-stock.com/en/docs/models/music/suno/add-stem): Layer a new stem onto a prior track. Complete request and parameter reference.
- [Suno: add-vocals](https://docs.api-stock.com/en/docs/models/music/suno/add-vocals): Add vocals to an instrumental track. Complete request and parameter reference.
- [Suno: adjust-speed](https://docs.api-stock.com/en/docs/models/music/suno/adjust-speed): Change the playback speed of a prior track. Complete request and parameter reference.
- [Suno: boost-style](https://docs.api-stock.com/en/docs/models/music/suno/boost-style): Expand a short style description. Complete request and parameter reference.
- [Suno: bpm](https://docs.api-stock.com/en/docs/models/music/suno/bpm): Analyze the BPM of a prior track. Complete request and parameter reference.
- [Suno: concat](https://docs.api-stock.com/en/docs/models/music/suno/concat): Combine extend segments into a complete song. Complete request and parameter reference.
- [Suno: cover](https://docs.api-stock.com/en/docs/models/music/suno/cover): Create a cover of an existing track. Complete request and parameter reference.
- [Suno: crop](https://docs.api-stock.com/en/docs/models/music/suno/crop): Keep only a selected time range from a prior track. Complete request and parameter reference.
- [Suno: custom-model](https://docs.api-stock.com/en/docs/models/music/suno/custom-model): Train a reusable custom model from your own tracks. Complete request and parameter reference.
- [Suno: extend](https://docs.api-stock.com/en/docs/models/music/suno/extend): Continue an existing track. Complete request and parameter reference.
- [Suno: fade-in](https://docs.api-stock.com/en/docs/models/music/suno/fade-in): Apply a fade-in to a prior track. Complete request and parameter reference.
- [Suno: fade-out](https://docs.api-stock.com/en/docs/models/music/suno/fade-out): Apply a fade-out to a prior track. Complete request and parameter reference.
- [Suno actions](https://docs.api-stock.com/en/docs/models/music/suno): All Suno music-generation and audio-processing actions available through API Stock.
- [Suno: inspo](https://docs.api-stock.com/en/docs/models/music/suno/inspo): Generate a song from one to four public audio references. Complete request and parameter reference.
- [Suno: lyrics](https://docs.api-stock.com/en/docs/models/music/suno/lyrics): Generate lyrics as structured text. Complete request and parameter reference.
- [Suno: mashup](https://docs.api-stock.com/en/docs/models/music/suno/mashup): Remix exactly two prior tracks. Complete request and parameter reference.
- [Suno: midi](https://docs.api-stock.com/en/docs/models/music/suno/midi): Generate MIDI data from a prior track. Complete request and parameter reference.
- [Suno: music-cover](https://docs.api-stock.com/en/docs/models/music/suno/music-cover): Automatically cover a previous generated track. Complete request and parameter reference.
- [Suno: music-video](https://docs.api-stock.com/en/docs/models/music/suno/music-video): Create a visualized MP4 from a prior track. Complete request and parameter reference.
- [Suno: music](https://docs.api-stock.com/en/docs/models/music/suno/music): Generate a new song. Complete request and parameter reference.
- [Suno: remaster](https://docs.api-stock.com/en/docs/models/music/suno/remaster): Improve the mastering of a prior track. Complete request and parameter reference.
- [Suno: remove-section](https://docs.api-stock.com/en/docs/models/music/suno/remove-section): Remove a time range from a prior track. Complete request and parameter reference.
- [Suno: replace-section](https://docs.api-stock.com/en/docs/models/music/suno/replace-section): Replace a time range in a prior track. Complete request and parameter reference.
- [Suno: sample](https://docs.api-stock.com/en/docs/models/music/suno/sample): Generate a song from a sampled range of a prior track. Complete request and parameter reference.
- [Suno: sound](https://docs.api-stock.com/en/docs/models/music/suno/sound): Generate a sound effect. Complete request and parameter reference.
- [Suno: stems-all](https://docs.api-stock.com/en/docs/models/music/suno/stems-all): Split a track into all available stem categories. Complete request and parameter reference.
- [Suno: stems](https://docs.api-stock.com/en/docs/models/music/suno/stems): Split a track into vocals and instrumental. Complete request and parameter reference.
- [Suno: timestamped-lyrics](https://docs.api-stock.com/en/docs/models/music/suno/timestamped-lyrics): Retrieve word-level timing for a generated track. Complete request and parameter reference.
- [Suno: upload](https://docs.api-stock.com/en/docs/models/music/suno/upload): Import public audio for use by later actions. Complete request and parameter reference.
- [Suno: voice](https://docs.api-stock.com/en/docs/models/music/suno/voice): Create a reusable voice or persona. Complete request and parameter reference.
- [Suno: vox](https://docs.api-stock.com/en/docs/models/music/suno/vox): Extract vocal segments from a prior track. Complete request and parameter reference.
- [Suno: wav](https://docs.api-stock.com/en/docs/models/music/suno/wav): Export an existing track as WAV. Complete request and parameter reference.
- [Agnes Video 2.5](https://docs.api-stock.com/en/docs/models/video/agnes-video-2.5): Generate 1–12 second videos from text, up to 9 reference images and 3 audio references. Supports 720p, 1080p and 2K output in six aspect ratios.
- [FLUX 3 Video](https://docs.api-stock.com/en/docs/models/video/flux-3-video): Black Forest Labs' multimodal video model with native synchronized audio. Text-to-video, keyframes (1-10 images) and continuation of an existing clip, 5-20 seconds at 720p/1080p, with a low-cost draft mode.
- [Gemini Omni 1.1 Flash](https://docs.api-stock.com/en/docs/models/video/gemini-omni-1.1-flash): Generate 4–10 second video with sound from text, first/last frames and image references, or transform a 3–10 second source video. Output from 360p to upscaled 4K.
- [Grok Imagine 1.5 Video](https://docs.api-stock.com/en/docs/models/video/grok-imagine-1.5-video): Generate short video from text or animate a reference image.
- [Video models](https://docs.api-stock.com/en/docs/models/video): All active video models and their integration pages.
- [Kling 3.0 Motion Control](https://docs.api-stock.com/en/docs/models/video/kling-3.0-motion-control): Transfer motion from a reference video to a character image.
- [Kling 3.0](https://docs.api-stock.com/en/docs/models/video/kling-3.0): Generate video from text or frames with native audio, up to 15 seconds and 4K.
- [Kling 4.0](https://docs.api-stock.com/en/docs/models/video/kling-4.0): Generate 3–30 second videos with stereo audio, references, keyframes and video editing at 720p or 1080p.
- [MiniMax H3](https://docs.api-stock.com/en/docs/models/video/minimax-h3): Text, image and audio reference video generation at 480p, 768p or 1080p. 1–15 seconds (up to 10 at 1080p), up to 9 images and 3 audio references. First 5 images and all audio references are free; extra images are billed separately per request.
- [PixVerse V6](https://docs.api-stock.com/en/docs/models/video/pixverse-v6): Generate video from text or frames with motion, audio, and continuation controls.
- [Seedance 1.5 Pro](https://docs.api-stock.com/en/docs/models/video/seedance-1-5-pro): Generate cinematic video from text or first/last frame images with optional generated audio.
- [Seedance 2.0 Fast](https://docs.api-stock.com/en/docs/models/video/seedance-2.0-fast): Generate 4-15 second video faster from text, first/last frames, and multimodal image, video, or audio references at 480p or 720p.
- [Seedance 2.0 Mini](https://docs.api-stock.com/en/docs/models/video/seedance-2.0-mini): Generate lightweight 4-15 second video from text, first/last frames, and multimodal image, video, or audio references at 480p or 720p.
- [Seedance 2.0](https://docs.api-stock.com/en/docs/models/video/seedance-2.0): Generate 4-15 second video from text, first/last frames, and multimodal image, video, or audio references at up to 4K resolution.
- [Seedance 2.5 Spicy](https://docs.api-stock.com/en/docs/models/video/seedance-2.5-spicy): Generate 4-30 second videos with native audio and image, video or audio references at up to 1080p through APIPod’s relaxed-moderation Seedance 2.5 route.
- [Seedance 2.5](https://docs.api-stock.com/en/docs/models/video/seedance-2.5): Generate 4-30 second video from text, first/last frames, and multimodal image, video, or audio references at 480p, 720p, or 1080p.
- [Veo 3.1 Fast](https://docs.api-stock.com/en/docs/models/video/veo3.1-fast): Generate video quickly from text or reference images with resolution controls.
- [Veo 3.1 Lite](https://docs.api-stock.com/en/docs/models/video/veo3.1-lite): Cheapest Veo 3.1 tier for high-volume text-to-video. 8-second clips with audio at 720p, 1080p or 4k. Text prompt only — no reference images.
- [Veo 3.1 Quality](https://docs.api-stock.com/en/docs/models/video/veo3.1-quality): Quality-focused video generation from text or reference images.
- [Wan 2.7 Video](https://docs.api-stock.com/en/docs/models/video/wan2.7-video): Generate, edit, reference, or continue video through one flexible model.
- [Wan 3.0 Video Prime](https://docs.api-stock.com/en/docs/models/video/wan3.0-video-prime): Faster Wan 3.0 video generation from text, first and last frames, or multimodal image, video, audio, document and web references. 2–30 seconds at 480p, 720p or 1080p.
- [Wan 3.0 Pro](https://docs.api-stock.com/en/docs/models/video/wan3.0-video-pro): Wan 3.0 Pro video generation from text, first and last frames, or multimodal references. 2–30 seconds with native audio at 480p, 720p, 1080p, 2K or 4K.
- [Wan 3.0 Video](https://docs.api-stock.com/en/docs/models/video/wan3.0-video): Alibaba Wanxiang 3.0 all-in-one reference video model. Text, first frame, first + last frame, multi-modal reference (images, video, audio) and document or web page references, 2-30 seconds at 480p/720p/1080p.
- [Messages API](https://docs.api-stock.com/en/docs/protocols/anthropic): Use the Anthropic-compatible Messages request and response format.
- [Chat Completions API](https://docs.api-stock.com/en/docs/protocols/openai): One OpenAI-compatible integration for every active API Stock LLM.
- [Tasks and webhooks](https://docs.api-stock.com/en/docs/tasks): Poll asynchronous generations or receive their terminal result by webhook.