Proprietary EndpointNew
Fast multimodal coding and agent model with 1M context, adjustable reasoning depth, image and video input, function calling, and built-in web search.
Browse the full catalog of models across text, image, audio, video, 3D, and more.
Model catalog
Browse text, image, video, audio, 3D, search, and agent endpoints with pay-as-you-go pricing. The interactive catalog loads current availability from EmpirioLabs, and these model docs are crawlable without client JavaScript.
xAI image-to-video with prompt-guided motion, native audio, 480p or 720p output, and up to 15 second clips.
Multimodal video generation for cinematic clips from text, image, audio, or video inputs.
Unified image generation and editing for high-resolution creative, brand, and product visuals.
Cost-effective vision-language model for text, image, video, coding, tools, and 1M-context workflows.
Flagship long-context model for coding, productivity, long-running agents, deep thinking, and tool use.
Multimodal reasoning for coding, agents, long-context analysis, and text, image, and video input.
Moonshot multimodal reasoning with strong coding support, 256K context, and image and video input.
Long-context reasoning with tool calling, structured output, cache support, and 128K output.
Image-to-3D generation that turns a reference image into a textured GLB asset.
Fast multimodal coding and agent model with 1M context, adjustable reasoning depth, image and video input, function calling, and built-in web search.
Alibaba CloudAudio generation from a written description, with narration, dialogue in up to three cloned voices, sound effects, ambience, and music in one file.
DeepSeekPost-trained 1017 release with stronger coding and agent results, faster task completion, shorter outputs, image input, and a 1M context window.
Alibaba CloudImage generation and editing with Pro and Turbo variants, up to ten reference images, transparent PNG output, and custom sizes up to 2560x2560.
Alibaba CloudReal-time speech synthesis with 19 voices, delivery direction in plain language, inline emotion and sound tags, and audio streamed over SSE or WebSocket.
EmpirioLabsAnswers yes/no, choice, score and tool questions about text, JSON, images, video and audio in up to 1M tokens, and can tell when the input lacks the answer.
Z.aiCoding and agentic model with a 1M token context, 128K output, always-on reasoning at low, high, or max effort, native web search, and tool calling.
Z.aiNatively multimodal flash model with a 1M token context, image and video input, always-on reasoning, native web search, and tool calling.
Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, native web search, and tool calling.
Moonshot AIKimi K3 is Moonshot's flagship reasoning model with a 1M token context, always-on thinking, native web search, and text, image, and video inputs.
Meta AIMeta's updated frontier reasoning model with a 1,048,576-token context, image, video, audio, and PDF understanding, web search, and tool calling.
Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs.
Apache-licensed 4B FLUX.2 Klein image generation and editing model with text-to-image, reference-image editing, and creative workflow support.
TencentOpen-source text-to-image model on a multimodal Mixture-of-Experts architecture with photorealistic detail and strong multilingual text rendering.
DeepSeekAutoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.
Alibaba CloudUnified image generation and editing model with class-leading complex Chinese/English text rendering, realistic textures, and multi-image fusion.
Alibaba CloudQwen image generation and editing with Base and Pro variants, multilingual typography, multi-image references, and controllable 1K or 2K output.
ByteDanceUnified multimodal image model that reasons through prompts before rendering, producing high-resolution and consistent edits and brand visuals.
Kling AIText-to-video and image-to-video with synchronized native audio, at 720p or 1080p for 3 to 15 seconds, with aspect ratio and prompt control.
Alibaba CloudVideo model offering Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit modes with high-fidelity, motion-smooth output.
8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.
Kling AIVideo model in Standard or Pro modes with Text-to-Video, Image-to-Video, Reference-to-Video, editing, native sound, and multi-scene transitions.
Kling AIKling 3.0 model that transfers motion from a reference video onto a character from a reference image, with Standard 720p and Pro 1080p tiers.
OpenMOSSOpen-source 32B MoE foundation model that generates synchronized video and audio in one inference step with precise dual-tower lip-sync.
Open-source music generation model for text-to-song and lyric-guided audio, with fast 8-step XL Turbo inference for controllable song iteration.
Realtime voice model that takes plain-English delivery direction, holds one voice identity across 200+ languages, and streams with word timestamps.
Sub-130ms TTFB voice synthesis with 271+ voices across 15 languages, expressive prosody, and real-time SSE streaming for low-latency voice agents.
Broadcast-quality voice synthesis with rich expressive prosody, 271+ voices across 15 languages, and real-time SSE streaming with per-word timestamps.
Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.
Latency-first realtime voice synthesis holding one voice identity across 200+ languages, tuned for high-volume streaming workloads.
DeepgramSpeech-to-text transcription using the Nova-3 model with multi-language support and advanced customizable settings for production workloads.
OpenAIWhisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.
Controlled Whisper Large v3 Turbo transcription with multilingual ASR, translation, VAD, timestamps, subtitles, hotwords, and decoder controls.
StepFunStepFun streaming speech recognition model for Chinese and English audio transcription.
StepFunContext-aware transcription for proper nouns, technical terms, dialects, and difficult audio including whispers, fast speech, and singing.
StepFunLive transcription over a socket, returning partial results as the speaker talks, with voice activity detection marking each sentence.
ExaQuick LLM-style answer to a natural-language question, grounded in fresh Exa web search results with inline citations and source links.
ExaWeb search engine for finding pages, retrieving similar pages, crawling, and dedicated code search across the open web for AI agents.
LinkupIterative AI search that keeps querying when initial results are insufficient, returning more comprehensive answers than Standard mode.
LinkupAI-powered web search with detailed overviews and answers, faster than Deep Search.
PerplexityInstitutional-grade research agent that runs many rounds of web search and page reading, with maximum depth and extensive source coverage.
PerplexityResearch model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.
TRELLIS.2 image-to-3D model that turns a reference image into a textured GLB asset with resolution, seed, mesh, texture, and export controls.
DeemosRodin Gen-2 engine that turns a text prompt or up to five reference images into production 3D assets with PBR materials and quad or raw meshes.
Hitem3DProduction-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats.
Alibaba CloudMultilingual text embedding with selectable output dimensions (64–2048). Up to 8,192 tokens per input.
Alibaba CloudSpeed-optimised multimodal embedding, same shape as Vision-Plus, 3× cheaper image/video tokens.
Alibaba CloudMultimodal embedding producing independent vectors for text, image, and video inputs.
ByteDanceMultimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.
Alibaba CloudSemantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.
GPTZeroDeep-learning detector that flags portions of text likely generated by AI versus human, classifying content as entirely human, AI, or mixed.
ManusAutonomous AI agent that turns a high-level prompt into subtasks, calls tools and APIs, and delivers end-to-end results without manual orchestration.
LightOnDocument OCR that reads PDFs and images into structured Markdown, page by page, with tables, math, charts, image regions, and layout.
Check out our pricing or reach out if you want your own model deployed on our stack.
