AI Model Marketplace: Text, Image, Video & Audio APIs

The HiAPI model marketplace brings together text LLMs, image, video, music, and speech models. Available models include one-key access, usage-based pricing, an online Playground, and request examples; upcoming models include capability and launch previews. Filter by provider or task type.

851 Background Remover API — image generation, usage-based pricing; see live pricing. Turn product, portrait and pet images into transparent PNGs. Explore five before-and-after examples, input parameters and an API quickstart.
Bria Eraser API — image generation, usage-based pricing; see live pricing. Bria Eraser API removes passers-by, clutter or blemishes you paint on a mask and fills in the background. Clean product shots and photos, then try it online.
Bria Product Shot API — image generation, usage-based pricing; see live pricing. Bria Product Shot API puts your product photo in a new scene from an English description or a reference image, with preset or original placement. Try it online.
Claude Opus 4.8 API — text generation, usage-based pricing; see live pricing. Claude Opus 4.8 supports text generation, streaming responses, and tool calling through an OpenAI-compatible API. This route may include additional upstream context. For the cleanest native API experience, choose the Claude Opus 4.8 AWS model.
Claude Opus 4.8 (AWS) API — text generation, usage-based pricing; see live pricing. Claude Opus 4.8 is designed for complex tasks and high-quality text generation. It supports text and image input, streaming responses, tool calling, and configurable reasoning effort. The model is available through an OpenAI-compatible API and is suitable for code generation, technical analysis, long-form processing, structured output, and automated API workflows.
Claude Opus 5.5 API — text generation, usage-based pricing; see live pricing. Claude Opus 5.5 is built for long-running agentic coding and knowledge work with always-on thinking and five effort levels.
Claude Opus 5.5 (AWS) API — text generation, usage-based pricing; see live pricing. Claude Opus 5.5 is built for long-running agentic coding and knowledge work with always-on thinking and five effort levels. Served via the AWS route.
Claude Sonnet 4.6 API — text generation, usage-based pricing; see live pricing. Claude Sonnet 4.6 supports text conversations, image understanding, adaptive thinking, streaming and tool calling.
Creatify Boreal API — video generation, usage-based pricing; see live pricing. Creatify Boreal API: turn one prompt into product, UGC and presenter videos with native speech and sound, guided by an optional image or audio. Try it online.
DeepSeek V4 Flash API — text generation, usage-based pricing; see live pricing. DeepSeek V4 Flash is an open-weight language model for high-throughput generation, reasoning, coding, and agent workflows, with a 1M-token context window, thinking and non-thinking modes, JSON output, and tool calling.
DeepSeek V4 Flash Vision Exp API — text generation, usage-based pricing; see live pricing. DeepSeek V4 Flash Vision Exp accepts text and image input for multimodal understanding and agent workflows. It supports the Responses API and remains compatible with Chat Completions.
DeepSeek V4 Pro API — text generation, usage-based pricing; see live pricing. DeepSeek V4 Pro (0813) targets complex reasoning, coding, and agent workflows. It natively supports the Responses API and remains compatible with Chat Completions.
DeepSeek V4.1 Flash API — text generation, usage-based pricing; see live pricing. DeepSeek V4.1 Flash GA supports Responses and Chat Completions with text and image understanding.
ElevenLabs Sound Effects v2 API — sound effects, usage-based pricing; see live pricing. ElevenLabs Sound Effects v2 turns a description into 0.5–22 second loopable effects for video, games, and UI. Try it online and see pricing and API examples.
ElevenLabs Text to Dialogue API — music generation, usage-based pricing; see live pricing. Create multi-speaker dialogue with ElevenLabs Text to Dialogue. Hear an audio drama, map voices to lines, review pricing, and copy API code.
Eleven Music v2 API — music generation, coming soon. ElevenLabs' next-generation music model for prompt-led songs, instrumentals, long-form composition, reference-guided sound, and section-level editing.
FASHN Try-On v1.6 API — image generation, usage-based pricing; see live pricing. Try FASHN Try-On v1.6: upload a person photo and a garment image to get a natural on-model result, with tops, bottoms, one-pieces and four real examples.
FIBO Edit 1.5 API — image generation, usage-based pricing; see live pricing. Try FIBO Edit 1.5 image editing: one-instruction edits, up to 4 reference images for compositing and try-ons, mask edits and API examples.
FIBO Gen 1.5 API — image generation, usage-based pricing; see live pricing. Try FIBO Gen 1.5 text-to-image for photoreal images with accurate in-image text, 9 aspect ratios, reproducible seeds and API examples.
FLUX.1 Fill Pro API — image generation, usage-based pricing; see live pricing. FLUX.1 Fill Pro API repaints only the masked area. Upload a source and a black-and-white mask for product retouching, background replacement and recoloring, and try it online.
FLUX.1 Kontext Max API — image generation, usage-based pricing; see live pricing. Generate images from text or edit one source image with FLUX.1 Kontext Max. Keep subjects, text and layout consistent; see real cases, pricing and API examples.
FLUX1.1 [pro] API — image generation, usage-based pricing; see live pricing. Generate polished photography, architecture, food, nature, and commercial visuals with custom sizing and prompt upsampling controls.
FLUX.2 [pro] Image to Image API — image generation, usage-based pricing; see live pricing. Edit and compose images with FLUX.2 [pro] Image to Image using up to eight references, auto ratio, 1K/2K output, a matched watercolor example, and API quickstart code.
FLUX.2 [klein] 4B Image to Image API — image generation, usage-based pricing; see live pricing. A compact low-cost editing route for commercial refinements, background changes, recoloring, and rapid reference-based iteration.
FLUX.2 [klein] 4B Text to Image API — image generation, usage-based pricing; see live pricing. Try FLUX.2 [klein] 4B Text to Image for low-cost drafts and commercial visuals with eleven ratios, five megapixel tiers, seed control, and API code.
FLUX.2 [klein] 9B Image to Image API — image generation, usage-based pricing; see live pricing. Edit with FLUX.2 [klein] 9B Image to Image using one reference, real cleanup and text-replacement examples, five ratios, four to eight inference steps, and API code.
FLUX.2 [klein] 9B Text to Image API — image generation, usage-based pricing; see live pricing. Try FLUX.2 [klein] 9B Text to Image with real event, product, magazine, and neon examples, five aspect ratios, four to eight inference steps, and API code.
FLUX.2 [pro] Text to Image API — image generation, usage-based pricing; see live pricing. Black Forest Labs FLUX.2 Pro: high-fidelity text-to-image with strong prompt adherence and crisp in-image text.
FLUX 3 Image API — image generation, usage-based pricing; see live pricing. FLUX 3 Image API turns prompts and references into detailed visuals for products, spaces and creative work. Try online and view images, pricing and guides.
FLUX 3 Max Image to Video API — video generation, usage-based pricing; see live pricing. Turn a first frame, with an optional last frame, into a 5–20 second FLUX 3 Max clip at 720p or 1080p with optional synchronized audio. See inputs, outputs, per-second pricing and API code.
FLUX 3 Max Keyframes to Video API — video generation, usage-based pricing; see live pricing. Place up to 10 keyframes on a 24fps timeline and generate 5–20 second FLUX 3 Max clips at 720p or 1080p. See keyframe examples, per-second pricing and POST /v1/tasks code.
FLUX 3 Max Text to Video API — video generation, usage-based pricing; see live pricing. Generate 5–20 second FLUX 3 Max clips from a prompt at 720p or 1080p in eight aspect ratios, with optional synchronized audio. See examples, per-second pricing and POST /v1/tasks code.
flux-3-video API — video generation, usage-based pricing; see live pricing. Black Forest Labs FLUX.3 Video generates up to 20-second clips from text, images, or a source video, with 720p/1080p output, synchronized audio, multi-keyframe storyboards, and low-cost Draft previews.
FLUX.1 [schnell] API — image generation, usage-based pricing; see live pricing. A fast, low-cost 1-4 step model for drafts, batch generation, and rapid prompt exploration.
Nano Banana 2.1 API — image generation, usage-based pricing; see live pricing. Create fashion portraits and interiors with Nano Banana 2.1. Try online, view examples and edit reference photos through the HiAPI API.
Gemini Omni 1.1 Flash API — video generation, usage-based pricing; see live pricing. Gemini Omni 1.1 Flash API creates videos with ambient sound for product films and social posts. Try it online and explore examples and API guidance.
GLM-5.3 API — text generation, usage-based pricing; see live pricing. Zhipu GLM-5.3 text model, available through an OpenAI-compatible Chat Completions endpoint.
Google Virtual Try-On API — image generation, usage-based pricing; see live pricing. Google Virtual Try-On API: put a garment image on a person photo for a natural on-body result, one per request, for product pages and styling. Try it online.
GPT-5.6 Luna API — text generation, usage-based pricing; see live pricing. GPT-5.6 Luna targets cost-sensitive, high-throughput workloads such as bulk classification, extraction, rewriting, and lightweight coding. HiAPI currently exposes text, multi-turn, and function tool calling through the streaming Responses API.
GPT-5.6 Sol API — text generation, usage-based pricing; see live pricing. GPT-5.6 Sol is the flagship reasoning model in OpenAI's GPT-5.6 family for complex coding, professional analysis, and demanding agent workflows. HiAPI currently exposes text, multi-turn, and function tool calling through the streaming Responses API.
GPT-5.6 Terra API — text generation, usage-based pricing; see live pricing. GPT-5.6 Terra balances intelligence, speed, and cost for everyday coding, document work, and general agent workflows. HiAPI currently exposes text, multi-turn, and function tool calling through the streaming Responses API.
GPT-6 Astra API — text generation, usage-based pricing; see live pricing. GPT-6 Astra offers streaming text, five reasoning levels, function calls and JSON output through the Responses API.
GPT-6 Luna API — text generation, usage-based pricing; see live pricing. Use GPT-6 Luna API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Responses examples.
gpt-6-sol API — text generation, usage-based pricing; see live pricing. Use gpt-6-sol API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Chat Completions examples.
GPT-6.1 Sol API — text generation, usage-based pricing; see live pricing. Use GPT-6.1 Sol API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Responses examples.
GPT-6.1 Terra API — text generation, usage-based pricing; see live pricing. Use GPT-6.1 Terra API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Responses examples.
GPT Image 2 API — image generation, usage-based pricing; see live pricing. GPT Image 2 API turns text or reference images into posters and product visuals, with background and style edits. Try it online or integrate it into your app.
gpt-image-2.5-flare API — image generation, usage-based pricing; see live pricing. Explore GPT Image 2.5 Flare for fast creative work, with photography, ads, comics, pixel art and recurring-character examples. Generate images online or integrate with HiAPI.
gpt-image-2.5-sunburst API — image generation, usage-based pricing; see live pricing. Explore GPT Image 2.5 Sunburst for detailed creation, multi-reference outfits, text localization, object removal and campaign revisions through HiAPI.
GPT Image 2.6 API — image generation, coming soon. GPT Image 2.6 is an image model in OpenAI's GPT Image family. Find markup editing details, HiAPI API access preparation, general image prompt templates and launch email notifications.
Grok 4.6 API — text generation, usage-based pricing; see live pricing. Grok 4.6 is an xAI text reasoning model available through Chat Completions with streaming, JSON objects, tool calling, and four reasoning effort levels.
Grok 4.7 API — text generation, usage-based pricing; see live pricing. Grok 4.7 is xAI's text model for coding, agentic tasks, and knowledge work. Use HiAPI Chat Completions for streaming, JSON objects, tools, and four reasoning efforts.
Grok Imagine 1.5 Image to Video API — video generation, usage-based pricing; see live pricing. Try Grok Imagine 1.5 Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Grok Imagine 1.5 Lite Image to Video API — video generation, usage-based pricing; see live pricing. Grok Imagine 1.5 Lite API animates one image into a 1–15 s clip with built-in sound, keeping its style. Try it online and view examples and docs.
Grok Imagine 1.5 Lite Text to Video API — video generation, usage-based pricing; see live pricing. Grok Imagine 1.5 Lite API turns a prompt into 1–15 s clips with built-in sound for ads, dialogue and openers. Try it online and view examples and docs.
Grok Image 2.0 Image to Image API — image generation, usage-based pricing; see live pricing. Edit one public reference image for recoloring, restyling, scene replacement, and detail refinement while following its framing.
Grok Image 2.0 Text to Image API — image generation, usage-based pricing; see live pricing. Generate product, editorial, landscape, and character visuals in low or medium quality at 1K/2K across square to ultrawide formats.
Grok Imagine Image to Image API — image generation, usage-based pricing; see live pricing. Edit with Grok Imagine Image to Image using up to three references, a matched cabin-to-night example, fourteen ratios, flat 1k/2k pricing, and API code.
Grok Imagine Image to Video API — video generation, usage-based pricing; see live pricing. Try Grok Imagine Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Grok Imagine Quality Image to Image API — image generation, usage-based pricing; see live pricing. Use Grok Imagine Quality Image to Image with up to three references, a matched night-scene edit, fourteen ratios, 1k/2k quality pricing, and API code.
Grok Imagine Quality Text to Image API — image generation, usage-based pricing; see live pricing. Create hero-grade cinematic images with Grok Imagine Quality Text to Image, thirteen ratios, 1k/2k tiers, API examples, and quickstart code.
Grok Imagine Text to Image API — image generation, usage-based pricing; see live pricing. Generate cinematic landscapes and night scenes with Grok Imagine Text to Image, thirteen aspect ratios, flat 1k/2k pricing, API examples, and quickstart code.
Grok Imagine Text to Video API — video generation, usage-based pricing; see live pricing. Try Grok Imagine text-to-video online, watch public API results, compare 480p and 720p pricing, and integrate POST /v1/tasks.
Hailuo 2.3 Fast Image to Video API — video generation, usage-based pricing; see live pricing. Try Hailuo 2.3 Fast Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Hailuo 2.3 Image to Video API — video generation, usage-based pricing; see live pricing. Try Hailuo 2.3 Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Hailuo 2.3 Text to Video API — video generation, usage-based pricing; see live pricing. Try Hailuo 2.3 text-to-video online, watch motion and physics results, compare fixed 6- and 10-second pricing, and call POST /v1/tasks.
HappyHorse 1.0 API — video generation, usage-based pricing; see live pricing. Generate 3-15 second text-to-video clips at 720p or 1080p across five common aspect ratios.
HappyHorse 1.1 Image to Video API — video generation, usage-based pricing; see live pricing. Try HappyHorse 1.1 Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
HappyHorse 1.1 Reference to Video API — video generation, usage-based pricing; see live pricing. Try HappyHorse 1.1 Reference to Video reference-to-video online. Use reference images to guide subjects, style, and scenes, then review pricing, prompts, and POST /v1/tasks API code.
HappyHorse 1.1 Text to Video API — video generation, usage-based pricing; see live pricing. Generate 3-15 second 720p/1080p clips across nine aspect ratios for social, cinematic, and campaign video.
HeyGen Avatar IV API — video generation, usage-based pricing; see live pricing. HeyGen Avatar IV API: turn one portrait photo into a lip-synced talking video from a script or your own audio for explainers and short videos. Try it online.
HeyGen Avatar V API — video generation, usage-based pricing; see live pricing. HeyGen Avatar V digital human video: drive a preset avatar with text or audio, with lip-sync, backgrounds, transparent WebM, and captions.
Ideogram 3.0 Character API — image generation, usage-based pricing; see live pricing. Upload one character reference and place the same character in new scenes. Try Ideogram 3.0 Character on HiAPI with examples, three per-image tiers and async API samples.
Ideogram 3.0 Character Edit API — image generation, usage-based pricing; see live pricing. Use a source image, a mask and one character reference to inpaint the same character into an existing scene. Try it on HiAPI with before/after examples, billing notes and API samples.
Ideogram V4 API — image generation, usage-based pricing; see live pricing. Try Ideogram V4 for accurate in-image text, logos, posters, and signage with TURBO, BALANCED, and QUALITY tiers plus API examples.
Ideogram 4.5 API — image generation, usage-based pricing; see live pricing. Try Ideogram 4.5 text-to-image for posters, logo wordmarks and accurate in-image typography: low, medium and high quality, six sizes, prompt expansion and seed control, with real examples and API code.
Ideogram 4.5 Edit API — image generation, usage-based pricing; see live pricing. Edit images with Ideogram 4.5 Edit: prompt edits, up to four reference images, mask inpainting and Precise Edit that restores unedited pixels, with real examples and API code.
Imagen 4 API — image generation, usage-based pricing; see live pricing. Imagen 4 API turns text into product, lifestyle and campaign images in six aspect ratios. Try it online and review examples, live pricing and API examples.
Imagen 4 Fast API — image generation, usage-based pricing; see live pricing. Imagen 4 Fast generates images quickly from text for direction exploration and batch drafts, in six aspect ratios. Try it online and review examples and API examples.
Imagen 4 Ultra API — image generation, usage-based pricing; see live pricing. Imagen 4 Ultra generates finished, detail-rich images from text for product macros, portraits and close-ups, in six aspect ratios. Try it online and review examples and API examples.
Kandinsky 6.0 Pro Image to Video API — video generation, usage-based pricing; see live pricing. Animate a first frame into a 5-second 480p clip with synchronized audio and automatic aspect matching. Billed per video.
Kandinsky 6.0 Pro Text to Video API — video generation, usage-based pricing; see live pricing. Turn a prompt into a 5-second 480p clip with synchronized audio in five aspect ratios. Billed per video.
Kimi K3 API — text generation, usage-based pricing; see live pricing. Kimi K3 is a reasoning model from Moonshot AI. Use Chat Completions for text conversations with three reasoning effort levels and streaming output.
Kimi K3.1 Pro API — text generation, usage-based pricing; see live pricing. Use Kimi K3.1 Pro API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Chat Completions examples.
Kimi K3.1 Pro Highspeed API — text generation, usage-based pricing; see live pricing. Use Kimi K3.1 Pro Highspeed API for text generation: Q&A, coding, documents and agent workflows. Try it online and view pricing and Chat Completions examples.
Kling 2.5 Turbo Image-to-Video API — video generation, usage-based pricing; see live pricing. Animate a first frame into a 5- or 10-second video, with optional last-frame control.
Kling 2.5 Turbo Text-to-Video API — video generation, usage-based pricing; see live pricing. Turn text ideas into moving shots in 5 or 10 seconds, with an included audio track.
Kling 3.0 Image-to-Video API — video generation, usage-based pricing; see live pricing. Try Kling 3.0 Image-to-Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Kling 3.0 Motion Control API — video generation, usage-based pricing; see live pricing. Kling 3.0 Motion Control API: transfer a reference video's motion and audio onto one character image for AI dance videos and talking avatars. Try it online.
Kling 3.0 Omni Image-to-Video API — video generation, usage-based pricing; see live pricing. Animate a first frame, or a first and last frame, into a 3–15 second video at 720p to 4K, with native audio and smart multi-shot; the frame follows the first image.
Kling 3.0 Omni Reference-to-Video API — video generation, usage-based pricing; see live pricing. Generate 3–15 second videos from 1–7 reference images, plus an optional reference clip, so the same person, pet or object appears in a new scene, at 720p to 4K.
Kling 3.0 Omni Text-to-Video API — video generation, usage-based pricing; see live pricing. Generate 3–15 second videos from text at 720p to 4K, with native audio, smart multi-shot and @subject references for characters or products.
Kling 3.0 Omni Transformation API — video generation, usage-based pricing; see live pricing. Upload a video and use a prompt to restyle it, change the setting or swap the subject while keeping the original motion and camera movement, at 720p to 4K.
Kling 3.0 Text-to-Video API — video generation, usage-based pricing; see live pricing. Create 3-15 second videos at 720p, 1080p, or 4K with square, landscape, vertical, and optional sound output.
Kling 3.0 Turbo Image to Video API — video generation, usage-based pricing; see live pricing. Try Kling 3.0 Turbo Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Kling 3.0 Turbo Text to Video API — video generation, usage-based pricing; see live pricing. Try Kling 3.0 Turbo text-to-video in the HiAPI Playground. Compare 720p results, copy prompts, review 3–15 second parameters and pricing, then call POST /v1/tasks.
Kling 4.0 Image-to-Video API — video generation, usage-based pricing; see live pricing. Kling 4.0 image-to-video API animates one first-frame image into a clip up to 30 seconds with synchronized audio. Keep the source framing and try it online.
Kling 4.0 Text-to-Video API — video generation, usage-based pricing; see live pricing. Kling 4.0 text-to-video API turns a prompt into clips up to 30 seconds with synchronized audio, 720p or 1080p and four framings. Watch verified examples and try it online.
Krea 2 Medium Turbo API — image generation, usage-based pricing; see live pricing. Try Krea 2 Medium Turbo for fast text-to-image generation with 8 aspect ratios including 2.35:1, four creativity levels, reproducible seeds and API examples.
Krea 3 API — image generation, usage-based pricing; see live pricing. Try Krea 3 text-to-image: prompt reasoning, berry and jam variants, six sizes up to 1024 × 1024, negative prompt (berry) and seed, with examples and API code.
LTX 2.5 Fast Image to Video API — video generation, usage-based pricing; see live pricing. Animate a first frame, optionally toward a last frame, into a 2-20 second 720p or 1080p video with native audio.
LTX 2.5 Fast Text to Video API — video generation, usage-based pricing; see live pricing. Turn a prompt into a 2-20 second 720p or 1080p video, landscape or vertical, with native audio.
Lyria 3 Pro API — music generation, usage-based pricing; see live pricing. Try Google Lyria 3 Pro for AI music generation. Hear a playable sample, review prompt and optional image guidance, pricing, and API code.
Lyria 3.5 API — music generation, usage-based pricing; see live pricing. Lyria 3.5 turns prompts or lyrics into complete songs for songwriting, video soundtracks, and music ideas. Try it online and view pricing and API examples.
MAI-Image-2.6 API — image generation, coming soon. MAI-Image-2.6 is Microsoft’s next-generation text-to-image and image editing model—built for higher visual quality, controllable edits, multi-reference workflows, and web grounding across ads, e-commerce product shots, and design.
MiniMax H3 API — video generation, usage-based pricing; see live pricing. MiniMax H3 combines native 2K text-to-video, first and last frame control, and multimodal reference video under one model ID. Compare the workflows, check live pricing, and validate a result in Playground before integrating it.
MiniMax H3 Max Image-to-Video API — video generation, usage-based pricing; see live pricing. Use a first frame, last frame or both to guide a clip’s opening and ending, then describe motion and sound.
MiniMax H3 Max Text-to-Video API — video generation, usage-based pricing; see live pricing. Direct scenes, action and sound with text, choosing framing for landscape, portrait or square clips.
MiniMax Music 1.5 API — music generation, usage-based pricing; see live pricing. Generate complete Chinese or English songs with MiniMax Music 1.5. Hear sample tracks, structured lyrics, audio settings, pricing, and API code.
MiniMax Music 2.6 API — music generation, usage-based pricing; see live pricing. Generate full songs with MiniMax Music 2.6 using custom lyrics, automatic lyrics, or instrumental mode. Hear sample tracks and copy API code.
MiniMax Music 3 API — music generation, usage-based pricing; see live pricing. Generate songs with MiniMax Music 3 using a music prompt and lyrics. Review duration-based pricing, parameters, workflow, and API code.
Mirelo SFX 2.0 API — sound effects, usage-based pricing; see live pricing. Mirelo SFX 2.0 turns text into 1–30 second WAV sound effects for video foley, games, and short-form content. Try it online and view pricing and API examples.
Mureka 9.5 Instrumental API — music generation, usage-based pricing; see live pricing. Mureka 9.5 turns a text description of genre, mood, and instruments into instrumental music. Try it online in Playground, then copy the API example.
Mureka 9.5 Lyrics to Song API — music generation, usage-based pricing; see live pricing. Mureka 9.5 turns lyrics into a finished vocal song with style direction and female or male vocals. Try it online in Playground, then copy the API example.
Muse Image Image-to-Image API — image generation, usage-based pricing; see live pricing. Muse Image API edits subjects, colors and layouts from references for covers and posters. Try online and see image comparisons, pricing and API guides.
Muse Image Text-to-Image API — image generation, usage-based pricing; see live pricing. Muse Image API creates illustrations and layouts for book covers, posters and content. Try online and explore images, live pricing and API guides.
Nano Banana API — image generation, usage-based pricing; see live pricing. A general-purpose image generator for illustration, photography, product concepts, and social visuals.
Nano Banana 2 API — image generation, usage-based pricing; see live pricing. Create or remix images with optional references, broad aspect ratios, and higher-resolution output.
Nano Banana 2 Lite API — image generation, usage-based pricing; see live pricing. A fixed-1K entry route for high-volume drafts, fast iteration, and optional multi-reference remixing.
Nano Banana Pro API — image generation, usage-based pricing; see live pricing. Generate high-detail commercial images or remix optional references with broad ratios and up to 4K output.
OmniHuman 1.5 API — video generation, usage-based pricing; see live pricing. OmniHuman 1.5 API: turn one portrait and an audio clip into a lip-synced talking video with natural gestures for short videos and lessons. Try it online.
PixVerse V6 Image to Video API — video generation, usage-based pricing; see live pricing. Animate an image into a 1–15 second PixVerse V6 video at 360p–1080p that keeps the source's shape, with optional synchronized audio and style presets. See examples, per-second pricing and API code.
PixVerse V6 Text to Video API — video generation, usage-based pricing; see live pricing. Generate 1–15 second PixVerse V6 videos from text at 360p–1080p in eight aspect ratios, with optional synchronized audio and style presets. See examples, per-second pricing and API code.
Qwen-Audio 3.0 TTS Flash API — music generation, usage-based pricing; see live pricing. Try Qwen-Audio 3.0 TTS Flash for low latency text-to-speech. Hear a multilingual sample, compare voices and controls, and copy API code.
Qwen-Audio 3.0 TTS Plus API — music generation, usage-based pricing; see live pricing. Try Qwen-Audio 3.0 TTS Plus for high quality text-to-speech. Hear a multilingual sample, compare voices and controls, and copy API code.
Qwen Image 2.0 API — image generation, usage-based pricing; see live pricing. A cost-efficient Chinese-friendly model with negative prompts, prompt extension, optional seed, and five 2K pixel-size presets.
Qwen Image 2.0 Pro API — image generation, usage-based pricing; see live pricing. Try Qwen Image 2.0 Pro with real Chinese typography, portrait, product, and concept examples, five 2K-class sizes, prompt extension, and API code.
Qwen Image 2.1 Pro API — image generation, usage-based pricing; see live pricing. Try Qwen Image 2.1 Pro with four cases — sketch to 3D toy, two-reference scene composition, word-exact Chinese poster text, and a product-shot restyle — plus up to 10 references, five 2K-class ratios, and API code.
Qwen Image 2.1 Turbo API — image generation, usage-based pricing; see live pricing. Try Qwen Image 2.1 Turbo with four cases — sticker art, a flat-lay illustration with copy space, cloud-city concept art, and photo-to-watercolor restyling — plus up to 10 references, five 2K-class ratios, and fast flat-price generation.
Qwen Image 3.0 Image to Image API — image generation, usage-based pricing; see live pricing. Use Qwen Image 3.0 Image to Image with up to three references, a product recolor example, eight ratios, 1K/2K output, and API code.
Qwen Image 3.0 Pro Image to Image API — image generation, usage-based pricing; see live pricing. Edit images with Qwen Image 3.0 Pro using up to three references, exact cover-text replacement, 1K/2K pricing, eight ratios, and API quickstart code.
Qwen Image 3.0 Pro API — image generation, usage-based pricing; see live pricing. Use the Pro route for denser typography, architecture, science editorials, luxury products, and final campaign layouts.
Qwen Image 3.0 API — image generation, usage-based pricing; see live pricing. Create typography-led posters, editorial scenes, and product visuals with Chinese and English text, prompt extension, and 1K/2K output.
Ray 3.2 Image to Video API — video generation, usage-based pricing; see live pricing. Turn a first frame, with an optional last frame, into a 5-second Ray 3.2 clip at 540p, 720p or 1080p. See input and output examples, per-clip pricing and POST /v1/tasks code.
Ray 3.2 Text to Video API — video generation, usage-based pricing; see live pricing. Generate 5- or 10-second Ray 3.2 videos from a prompt at 540p, 720p or 1080p in six aspect ratios. Watch examples, copy prompts, check per-clip pricing and call POST /v1/tasks.
Recraft Creative Upscale API — image generation, usage-based pricing; see live pricing. Recraft Creative Upscale API enlarges an image and redraws texture and detail, for refreshing old assets and enlarging illustrations. Try it online on HiAPI.
Recraft Crisp Upscale API — image generation, usage-based pricing; see live pricing. Upscale images 2× with the Recraft Crisp Upscale API: one image URL in, a sharper image at double the width and height out, content unchanged. See before/after examples, flat per-image pricing and quickstart code.
Recraft Remove Background API — image generation, usage-based pricing; see live pricing. Remove backgrounds with the Recraft API: one image URL in, transparent PNG out with hair and fur-level edges preserved. See a cutout example, flat per-image pricing, and quickstart code.
Recraft V4.1 Flash API — image generation, usage-based pricing; see live pricing. Try Recraft V4.1 Flash text-to-image for fast photos, illustrations and posters, with 6 size presets, custom palettes and API examples.
Recraft V4.1 API — image generation, usage-based pricing; see live pricing. Try Recraft V4.1 text-to-image for detailed photos, illustrations and posters, with 6 size presets, custom palettes and API examples.
Runway Gen-4.5 Image-to-Video API — video generation, usage-based pricing; see live pricing. Animate a first frame into 720p video with multiple aspect ratios and 5, 8 or 10 second durations, billed per second.
Runway Gen-4.5 Text-to-Video API — video generation, usage-based pricing; see live pricing. Generate 720p landscape or portrait video from text. 16:9 supports 5/8/10 seconds; 9:16 supports 5/10 seconds, billed per second.
Seedance 2.0 API — video generation, usage-based pricing; see live pricing. A multimodal video route supporting text-only generation, endpoint frames, image/video/audio references, 4-15 seconds, and up to 4K output.
Seedance 2.0 Fast API — video generation, usage-based pricing; see live pricing. A faster multimodal Seedance route with text, endpoint frames, optional references, generated audio, and 480p/720p output.
Seedance 2.0 Mini API — video generation, usage-based pricing; see live pricing. A lower-cost multimodal route for 4-15 second drafts with endpoint frames, optional references, generated audio, and 480p/720p output.
Seedance 2.5 Image to Video API — video generation, usage-based pricing; see live pricing. Try Seedance 2.5 image-to-video with first-frame and first/last-frame control. Compare 720p results, copy prompts, review 4–30 second pricing, and call POST /v1/tasks.
Seedance 2.5 Reference to Video API — video generation, usage-based pricing; see live pricing. Try Seedance 2.5 reference-to-video with video, image, and audio references. Learn @video1 mappings, review 4–30 second pricing, and call POST /v1/tasks.
Seedance 2.5 Text to Video API — video generation, usage-based pricing; see live pricing. Try Seedance 2.5 text-to-video online, review an API result, compare 720p and 1080p pricing, and integrate POST /v1/tasks.
Seedream 4.5 Image to Image API — image generation, usage-based pricing; see live pricing. ByteDance Seedream 4.5 image editing: unified generation-editing architecture with up to 14 reference images for edits and composites, consistent subjects, 2K/4K output.
Seedream 4.5 Text to Image API — image generation, usage-based pricing; see live pricing. Try Seedream 4.5 Text to Image with real landscape, food, sci-fi, and Chinese-aesthetic examples, eight ratios, 2K/4K output, and API code.
Seedream 5.0 Flash API — image generation, usage-based pricing; see live pricing. Try Seedream 5.0 Flash API online for image generation and editing, with up to 10 references, custom sizes, examples and integration guides.
Seedream 5.0 Lite Image to Image API — image generation, usage-based pricing; see live pricing. Edit with Seedream 5.0 Lite Image to Image using up to 14 references, real recolor, text replacement, and composite examples, 2K or 4K output, and API code.
Seedream 5.0 Lite Text to Image API — image generation, usage-based pricing; see live pricing. Try Seedream 5.0 Lite Text to Image with real poster, infographic, banner, and photography examples, eight aspect ratios, 2K or 4K output, and API code.
Seedream 5.0 Pro Image to Image API — image generation, usage-based pricing; see live pricing. Edit with Seedream 5.0 Pro Image to Image using one to ten references, real recolor, weather, and multi-image examples, 1K or 2K pricing, and API code.
Seedream 5.0 Pro Text to Image API — image generation, usage-based pricing; see live pricing. Try Seedream 5.0 Pro Text to Image with real product, portrait, poster, and cinematic examples, 1K or 2K pricing, eight aspect ratios, and API code.
Veo 3.1 Fast Image to Video API — video generation, usage-based pricing; see live pricing. Try Veo 3.1 Fast Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Veo 3.1 Fast Text to Video API — video generation, usage-based pricing; see live pricing. A faster Veo route for 4, 6, or 8 second text-to-video with 720p-4K output, seeds, negative prompts, and generated audio.
Veo 3.1 Image to Video API — video generation, usage-based pricing; see live pricing. Try Veo 3.1 image-to-video online with one source image, 4/6/8-second output, 720p to 4K resolution, native audio, pricing, prompts, and API code.
veo-3.1-lite/image-to-video API — video generation, usage-based pricing; see live pricing. Veo 3.1 Lite image-to-video with native audio, 720p or 1080p output, and 4, 6, or 8 second clips.
veo-3.1-lite/text-to-video API — video generation, usage-based pricing; see live pricing. Veo 3.1 Lite text-to-video with native audio, 720p or 1080p output, and 4, 6, or 8 second clips.
Veo 3.1 Text to Video API — video generation, usage-based pricing; see live pricing. Premium 4, 6, or 8 second text-to-video with 720p-4K output, negative prompts, seeds, and synchronized generated audio.
Vidu Q3 Ad Reference-to-Video API — video generation, usage-based pricing; see live pricing. Reference-to-video built for product ads: turn a product shot into a 3-15 second ad clip at 720P or 1080P with camera work, shot cutting and sound generated for you, billed per second.
Vidu Q3 Mix Reference-to-Video API — video generation, usage-based pricing; see live pricing. Lock the look of a character, product or scene with 1-7 reference images and generate 1-16 second video at 720P or 1080P across 10 frame sizes, billed per second.
Vidu Q4 Preview Image-to-Video API — video generation, usage-based pricing; see live pricing. Animate one first-frame image into a 3-16 second video up to 4K, with native audio on by default and the frame following the image; billed per second.
Vidu Q4 Preview Reference-to-Video API — video generation, usage-based pricing; see live pricing. 1-15 reference images and up to 3 voice clips place a fixed cast, setting and voice in a new 3-16 second shot up to 4K, billed per second.
Wan 2.6 Flash Image to Video API — video generation, usage-based pricing; see live pricing. Upload one image, describe the motion and get a 5, 10 or 15 second 720p or 1080p video, with optional synchronized audio.
Wan 2.7 Image Standard API — image generation, usage-based pricing; see live pricing. Wan 2.7 Image Standard turns prompts and up to nine references into posters, product shots, and everyday visuals at 1K/2K. Try the API and Playground online.
Wan 2.7 Image Text to Image API — image generation, usage-based pricing; see live pricing. Try Wan 2.7 Image Text to Image with Chinese prompts, 1K/2K/4K output, extreme wide and tall ratios, optional thinking mode, and API code.
Wan 2.7 Image to Video API — video generation, usage-based pricing; see live pricing. Try Wan 2.7 Image to Video online. Animate a source image, review supported durations and resolutions, copy prompts, pricing, and POST /v1/tasks API code.
Wan 2.7 Text to Video API — video generation, usage-based pricing; see live pricing. Try Wan 2.7 text-to-video online, review a cinematic preview, compare 720P and 1080P per-second pricing, and integrate POST /v1/tasks.
Wan 3.0 Video API — video generation, usage-based pricing; see live pricing. An all-purpose 2-30 second video route supporting text, first/last frames, reference media, files or webpages, 480P-1080P output, and optional synchronized audio.
Wan 3.0 Prime API — video generation, usage-based pricing; see live pricing. The fast Wan 3.0 route for 2-30 second video from text, first/last frames, reference images or audio, files or webpages, with 480P-1080P output and optional synchronized audio.
Z-Image API — image generation, usage-based pricing; see live pricing. Try Z-Image for low-cost Chinese-friendly portraits, signage, city scenes, and food photography with five ratios, examples, and API code.