> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/documentation/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Documentation

## Docs

- [Welcome](https://docs.empiriolabs.ai/welcome.md): Documentation for the EmpirioLabs AI model platform
- [Getting Started](https://docs.empiriolabs.ai/getting-started.md): Make your first successful request to the EmpirioLabs AI API
- [Authentication](https://docs.empiriolabs.ai/authentication.md): Secure every request with a bearer token using your EmpirioLabs API key
- [Concepts](https://docs.empiriolabs.ai/concepts.md): Understand the main resources and building blocks of the EmpirioLabs AI platform
- [Models and Pricing](https://docs.empiriolabs.ai/models-pricing.md): Discover model availability, modalities, pricing, and supported parameters
- [Billing and Credits](https://docs.empiriolabs.ai/billing-credits.md): Prepaid credits, payment methods, auto top-up, and receipts
- [Subscription Plans](https://docs.empiriolabs.ai/plans.md): Lite, Pro and Max weekly allowances on top of pay as you go
- [Limits and API Keys](https://docs.empiriolabs.ai/rate-limits-api-keys.md): Production limits, API keys, GPU Cloud, hosted agents, playground saved chats, and increase requests
- [Errors and Status Codes](https://docs.empiriolabs.ai/errors.md): How the API reports errors, what each HTTP status means, and when to retry
- [Account Usage API](https://docs.empiriolabs.ai/account-usage-api.md): Query balance, request history, usage counters, costs, and saved Playground chats
- [Generation Templates](https://docs.empiriolabs.ai/generation-templates.md): One-field effects and Compose recipes for AI video. Apply curated effects to normal generations, or plan and render a full short-form production.
- [Realtime Voice API](https://docs.empiriolabs.ai/realtime.md): Full-duplex speech-to-speech over WebSocket. Stream microphone audio to the model and receive its spoken reply on the same connection, interrupt it mid-response, and let server-side voice activity detection manage turns.
- [Decisions API](https://docs.empiriolabs.ai/decisions.md): Calibrated probabilities for yes/no, choice, score, and tool questions about text, images, audio, and video
- [GPU Cloud](https://docs.empiriolabs.ai/gpu-cloud.md): Deploy managed GPU instances, run model or Docker workloads, and connect through the EmpirioLabs API.
- [Hosted Agents](https://docs.empiriolabs.ai/hosted-agents.md): Deploy a private OpenClaw or Hermes agent runtime that uses EmpirioLabs models.
- [OpenAI, Anthropic, and Gemini Compatibility](https://docs.empiriolabs.ai/compatibility.md): Use familiar request shapes while routing through EmpirioLabs AI
- [Integrations](https://docs.empiriolabs.ai/integrations.md): Connect EmpirioLabs to coding agents, IDEs, CLIs, chat frontends, and OpenAI-compatible tools
- [MCP Server](https://docs.empiriolabs.ai/mcp.md): Use every EmpirioLabs model and platform feature from Claude, ChatGPT, Cursor, and any MCP client
- [Authors and Models](https://docs.empiriolabs.ai/providers.md): 38 authors and 207 models on EmpirioLabs, callable through one OpenAI-compatible API.
- [ACE-Step](https://docs.empiriolabs.ai/providers/ace-step.md): 1 ACE-Step model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [ACE-Step 1.5 XL](https://docs.empiriolabs.ai/models/ace-step-1-5-xl.md): Open-source music generation model for text-to-song and lyric-guided audio, with fast 8-step XL Turbo inference for controllable song iteration.
- [Alibaba Cloud](https://docs.empiriolabs.ai/providers/alibaba.md): 49 Alibaba Cloud models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Qwen3.8 Max 0902](https://docs.empiriolabs.ai/models/qwen3-8-max-0902.md): Upgraded Qwen3.8 Max snapshot with stronger coding, steadier multi-tool agent runs, and sharper chart and document vision across a 1M-token context.
- [Qwen3.8 Max](https://docs.empiriolabs.ai/models/qwen3-8-max.md): Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.
- [Qwen3.7 Max](https://docs.empiriolabs.ai/models/qwen3-7-max.md): Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context.
- [Qwen3.8 27B](https://docs.empiriolabs.ai/models/qwen3-8-27b.md): Multimodal reasoner with 256K context, image and video input, function tools, structured JSON, and thinking on by default.
- [Qwen3.6 27B](https://docs.empiriolabs.ai/models/qwen3-6-27b.md): Qwen3.6 27B improves agentic coding, STEM reasoning, spatial vision, OCR, and text, image, and video understanding on 256K context.
- [Qwen3.6 35B A3B](https://docs.empiriolabs.ai/models/qwen3-6-35b-a3b.md): Qwen3.6 35B A3B is a 256-expert mixture-of-experts reasoning model with 128K context, function tools, and strict structured JSON output.
- [Qwen3.5 4B](https://docs.empiriolabs.ai/models/qwen3-5-4b.md): Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.
- [Qwen3.5 122B-A10B](https://docs.empiriolabs.ai/models/qwen3-5-122b-a10b.md): Qwen3.5 122B-A10B is a multimodal reasoning model with 256K context, efficient sparse MoE inference, and text, image, and video input.
- [Qwen3.5 35B-A3B](https://docs.empiriolabs.ai/models/qwen3-5-35b-a3b.md): Qwen3.5 35B-A3B is an efficient native vision-language model with sparse MoE routing, deep thinking, and text, image, and video input.
- [Qwen3.5 27B](https://docs.empiriolabs.ai/models/qwen3-5-27b.md): Qwen3.5 27B is a dense multimodal reasoning model with fast responses, 256K context, and text, image, and video understanding.
- [Qwen3.5 9B](https://docs.empiriolabs.ai/models/qwen3-5-9b.md): Qwen3.5 9B is a compact multimodal reasoning model with 256K context, image and video input, function tools, and structured output.
- [Qwen3.5 397B-A17B](https://docs.empiriolabs.ai/models/qwen3-5-397b-a17b.md): Qwen3.5 397B-A17B is a flagship multimodal reasoning model for language, code, agents, GUI tasks, and image and video understanding.
- [Qwen3.8 Flash](https://docs.empiriolabs.ai/models/qwen3-8-flash.md): Fast Qwen3.8 vision-language model for coding, agents, and visual understanding, with image and video input, five built-in tools, and a 1M token context.
- [Qwen3.7 Flash](https://docs.empiriolabs.ai/models/qwen3-7-flash.md): Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context.
- [Qwen3.6 Flash](https://docs.empiriolabs.ai/models/qwen3-6-flash.md): Fast Qwen3.6 vision-language model for agentic coding, math reasoning, spatial understanding, OCR, and text, image, and video input.
- [Qwen3.5 Flash](https://docs.empiriolabs.ai/models/qwen3-5-flash.md): Vision-language model with hybrid linear-attention plus sparse MoE, 1M context, and fast multimodal text/image/video inference.
- [Qwen3.7 Plus](https://docs.empiriolabs.ai/models/qwen3-7-plus.md): Cost-effective Qwen3.7 vision-language model for text, image, video, coding, tool use, GUI understanding, and 1M-context workflows.
- [Qwen3.6 Plus](https://docs.empiriolabs.ai/models/qwen3-6-plus.md): Vision-language model with major upgrades over 3.5: agentic and front-end coding, multimodal recognition, OCR, and object localization.
- [Qwen3.5 Plus](https://docs.empiriolabs.ai/models/qwen3-5-plus.md): Multimodal model with hybrid architecture for efficient deep thinking and visual understanding across text, image, and video on a 1M context.
- [Qwen3.8 Omni Flash Realtime](https://docs.empiriolabs.ai/models/qwen3-8-omni-flash-realtime.md): Speech and live video frames in, speech out over one socket, with 56 voices, tool calling during the conversation, and separate text and audio token rates.
- [Qwen3.5 Omni Flash Realtime](https://docs.empiriolabs.ai/models/qwen3-5-omni-flash-realtime.md): Speech in, speech out, over one socket, with separate text and audio token rates and per-turn billing.
- [Qwen3.5 Omni Plus Realtime](https://docs.empiriolabs.ai/models/qwen3-5-omni-plus-realtime.md): Speech in, speech out, over one socket, on the larger Omni tier, with separate text and audio token rates and per-turn billing.
- [Qwen3.8 Omni Flash](https://docs.empiriolabs.ai/models/qwen3-8-omni-flash.md): Omni-modal reasoner that reads text, images, audio, and video and answers in text, with a 1M token context, thinking, and native web search.
- [Qwen3.5 Omni Flash](https://docs.empiriolabs.ai/models/qwen3-5-omni-flash.md): Cost-efficient omni-modal model handling text, image, audio, and video, with up to 3 hours of audio and 1 hour of video across 90+ languages.
- [Qwen3.5 Omni Plus](https://docs.empiriolabs.ai/models/qwen3-5-omni-plus.md): Flagship omni-modal model for text, image, audio, and video. 3h audio, 1h video, 90+ input and 30+ output languages, 55 voice timbres.
- [Qwen3.8 LiveTranslate Flash Realtime](https://docs.empiriolabs.ai/models/qwen3-8-livetranslate-flash-realtime.md): Simultaneous spoken translation over a WebSocket. Set the target language, then speak; the model replies in that language with text and audio.
- [Qwen3 Rerank](https://docs.empiriolabs.ai/models/qwen3-rerank.md): Semantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.
- [Qwen Audio 3.1 ASR Message](https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr-message.md): Transcription tuned for voice messages and voice input over a socket, returning each utterance as one complete transcript when the speaker pauses.
- [Qwen Audio 3.1 ASR](https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr.md): Speech-to-text for short clips and long recordings, with sentence segments, word timestamps, and multilingual and Chinese dialect recognition.
- [Qwen Audio 3.1 ASR Stream](https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr-stream.md): Live transcription over a socket, streaming partial words while the speaker talks and a settled sentence at each pause, priced per token.
- [Qwen Audio 3.1 Realtime Plus](https://docs.empiriolabs.ai/models/qwen-audio-3-1-realtime-plus.md): Duplex speech conversation over one socket, with 27 voices, native web search, tool calling, and separate text and audio token rates.
- [Qwen Audio 3.0 TTS](https://docs.empiriolabs.ai/models/qwen-audio-3-0-tts.md): Tiered speech synthesis with over 1,000 voices, 16 languages, 20 Chinese dialects, natural-language delivery direction, and inline emotion tags.
- [Wan 3.0](https://docs.empiriolabs.ai/models/wan-3-0.md): All-in-one video generation up to 30 seconds with native audio, omni-modal references (images, video, audio, files, web links), and a fast Prime tier.
- [Wan 2.7](https://docs.empiriolabs.ai/models/wan-2-7.md): Multimodal video model supporting T2V, I2V, video editing, and reference-to-video, with high-fidelity output from text, image, or video inputs.
- [Wan 2.6](https://docs.empiriolabs.ai/models/wan-2-6.md): Multimodal video generation model for cinematic, multi-shot stories with native audio-visual sync (lip-sync, dialogue, music, SFX).
- [Wan 2.5](https://docs.empiriolabs.ai/models/wan-2-5.md): Alibaba's Wan 2.5 video model with text-to-video and image-to-video, native audio, optional custom audio tracks, and 480p to 1080p output.
- [Wan 2.2](https://docs.empiriolabs.ai/models/wan-2-2.md): Alibaba's Wan 2.2 video family with standard and flash tiers, first and last frame interpolation, and 480p to 1080p output at low cost.
- [Wan 2.1](https://docs.empiriolabs.ai/models/wan-2-1.md): Alibaba's Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.
- [Wan2.7 Image](https://docs.empiriolabs.ai/models/wan2-7-image.md): Image generation and editing companion model: text-to-image, bounding-box edits, and cohesive image sets, with up to 4K output on Pro.
- [Wan2.5 Image](https://docs.empiriolabs.ai/models/wan2-5-image.md): Alibaba's Wan 2.5 image model with text-to-image and multi-reference editing of up to 3 images at about 1.7 megapixels.
- [Wan2.2 Image](https://docs.empiriolabs.ai/models/wan2-2-image.md): Alibaba's Wan 2.2 text-to-image model with plus and flash tiers and up to 1440x1440 output at low per-image pricing.
- [Wan2.1 Image](https://docs.empiriolabs.ai/models/wan2-1-image.md): Alibaba's Wan 2.1 text-to-image model with turbo and plus tiers and up to 1440x1440 output at low per-image pricing.
- [Qwen Image 3.0](https://docs.empiriolabs.ai/models/qwen-image-3-0.md): Qwen image generation and editing with Base and Pro variants, multilingual typography, multi-image references, and controllable 1K or 2K output.
- [Qwen Image 2.0](https://docs.empiriolabs.ai/models/qwen-image-2-0.md): Unified image generation and editing model with class-leading complex Chinese/English text rendering, realistic textures, and multi-image fusion.
- [HappyHorse 1.1](https://docs.empiriolabs.ai/models/happyhorse-1-1.md): Text, image, and reference-to-video in one model. Cinematic motion, character consistency across up to 9 references, and synchronized native audio.
- [HappyHorse 1.0](https://docs.empiriolabs.ai/models/happyhorse-1-0.md): Video model offering Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit modes with high-fidelity, motion-smooth output.
- [Tongyi Embedding Vision Flash](https://docs.empiriolabs.ai/models/tongyi-embedding-vision-flash.md): Speed-optimised multimodal embedding, same shape as Vision-Plus, 3× cheaper image/video tokens.
- [Tongyi Embedding Vision Plus](https://docs.empiriolabs.ai/models/tongyi-embedding-vision-plus.md): Multimodal embedding producing independent vectors for text, image, and video inputs.
- [Text Embedding v4](https://docs.empiriolabs.ai/models/text-embedding-v4.md): Multilingual text embedding with selectable output dimensions (64–2048). Up to 8,192 tokens per input.
- [Amazon](https://docs.empiriolabs.ai/providers/amazon.md): 5 Amazon models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Nova Lite 2](https://docs.empiriolabs.ai/models/nova-lite-2.md): Fast, cost-effective multimodal reasoning model for text, images, documents, and video on a 1M context (long docs and ~90 min clips).
- [Nova Lite 1.0](https://docs.empiriolabs.ai/models/nova-lite-1-0.md): Low-cost multimodal foundation model for text, images, and video on a 300K context (up to ~30 min video), tuned for speed and affordability.
- [Nova Micro 1.0](https://docs.empiriolabs.ai/models/nova-micro-1-0.md): Text-only foundation model tuned for ultra-low latency and cost on 128K context. Strong for summarization, translation, and chat with 44% cache discount.
- [Nova Pro 1.0](https://docs.empiriolabs.ai/models/nova-pro-1-0.md): Multimodal foundation model balancing accuracy, speed, and cost for text, images, and video on 300K context (up to ~30 min video).
- [Amazon Nova Reel 1.1](https://docs.empiriolabs.ai/models/amazon-nova-reel-1-1.md): Video generation model producing up to 2-minute multi-shot videos from text and optional image prompts with improved quality and consistency.
- [Black Forest Labs](https://docs.empiriolabs.ai/providers/black-forest-labs.md): 1 Black Forest Labs model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [FLUX.2 Klein 4B](https://docs.empiriolabs.ai/models/flux-2-klein-4b.md): Apache-licensed 4B FLUX.2 Klein image generation and editing model with text-to-image, reference-image editing, and creative workflow support.
- [ByteDance](https://docs.empiriolabs.ai/providers/bytedance.md): 16 ByteDance models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Seedream 5.0 Flash](https://docs.empiriolabs.ai/models/seedream-5-0-flash.md): Fast Seedream image model that splits one image into editable layers, edits by coordinate or sketch marker, and fuses up to 10 references.
- [Seedream 5.0 Pro](https://docs.empiriolabs.ai/models/seedream-5-0-pro.md): Premium Seedream image model that splits one image into editable layers, edits by coordinate or sketch marker, and fuses up to 10 references.
- [Seedream 5.0 Lite](https://docs.empiriolabs.ai/models/seedream-5-0-lite.md): Unified multimodal image model that reasons through prompts before rendering, producing high-resolution and consistent edits and brand visuals.
- [Seedream 4.5](https://docs.empiriolabs.ai/models/seedream-4-5.md): High-fidelity image generation and editing with up to 14 reference images, strong text rendering, and 2K or 4K output at one flat price.
- [Seedream 4.0](https://docs.empiriolabs.ai/models/seedream-4-0.md): Unified image generation and editing with up to 14 reference images, batch sets of up to 15, and 1K to 4K output at one flat per-image price.
- [Seedance 2.5](https://docs.empiriolabs.ai/models/seedance-2-5.md): Long-form video model for coherent clips up to 30 seconds, with up to 50 reference images, videos, and audio clips, native audio, editing, and extension.
- [Seedance 2.0 Mini](https://docs.empiriolabs.ai/models/seedance-2-0-mini.md): The fastest, most affordable Seedance 2.0 tier for short cinematic clips with native audio, camera control, and image or video inputs at 480p and 720p.
- [Seedance 2.0 Fast](https://docs.empiriolabs.ai/models/seedance-2-0-fast.md): Speed-optimized 2.0 video variant for cinematic clips with native audio sync, camera control, and stable motion at lower cost per render.
- [Seedance 2.0 Pro](https://docs.empiriolabs.ai/models/seedance-2-0-pro.md): Multimodal video model for cinematic output from text, image, audio, or video inputs, with stable motion and consistent characters.
- [Seedance 1.5 Pro](https://docs.empiriolabs.ai/models/seedance-1-5-pro.md): Joint audio and video generation with millisecond lip sync, dialogue in six languages, cinematic camera moves, and up to 1080p output.
- [Seed 2.1 Turbo](https://docs.empiriolabs.ai/models/seed-2-1-turbo.md): Next-generation coding and agent model with engineering-grade code delivery, long-horizon autonomy, and 256K multimodal understanding.
- [Seed 2.0 Lite](https://docs.empiriolabs.ai/models/seed-2-0-lite.md): Balanced general-purpose model for high-frequency enterprise workloads: information processing, content, search, and data analysis.
- [Seed 2.0 Mini](https://docs.empiriolabs.ai/models/seed-2-0-mini.md): Latency-focused multimodal model with 256K context, four reasoning effort modes, and image/video understanding for high-concurrency use.
- [Seed 2.0 Pro](https://docs.empiriolabs.ai/models/seed-2-0-pro.md): Flagship general model with 256K context for complex reasoning, multimodal understanding, structured generation, and tool-augmented execution.
- [Seed 2.0 Code](https://docs.empiriolabs.ai/models/seed-2-0-code.md): Coding-tuned 256K-context model with strong front-end results and multilingual programming support for AI coding tools and agents.
- [Skylark Embedding Vision](https://docs.empiriolabs.ai/models/skylark-embedding-vision.md): Multimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.
- [Deemos](https://docs.empiriolabs.ai/providers/deemos.md): 1 Deemos model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Hyper3D Gen2](https://docs.empiriolabs.ai/models/hyper3d-gen2.md): Rodin 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.
- [Deepgram](https://docs.empiriolabs.ai/providers/deepgram.md): 2 Deepgram models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Deepgram Nova 3](https://docs.empiriolabs.ai/models/deepgram-nova-3.md): Speech-to-text transcription using the Nova-3 model with multi-language support and advanced customizable settings for production workloads.
- [Deepgram Nova-3 Stream](https://docs.empiriolabs.ai/models/deepgram-nova-3-stream.md): Live transcription over a socket, returning interim results while the speaker is still talking and a settled transcript once each phrase ends.
- [DeepSeek](https://docs.empiriolabs.ai/providers/deepseek.md): 5 DeepSeek models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [DeepSeek V4.1 Flash](https://docs.empiriolabs.ai/models/deepseek-v4-1-flash.md): Lightweight flagship of DeepSeek's new architecture with native image understanding, hybrid thinking, 1M context, and up to 384K output tokens.
- [DeepSeek V4 Flash 0731](https://docs.empiriolabs.ai/models/deepseek-v4-flash-0731.md): Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.
- [DeepSeek V4 Pro 0813](https://docs.empiriolabs.ai/models/deepseek-v4-pro-0813.md): Official 0813 Pro release with major gains across coding, repository work, tool use, and agent tasks, plus hybrid thinking and a 1M context window.
- [DeepSeek V4 Pro](https://docs.empiriolabs.ai/models/deepseek-v4-pro.md): Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.
- [Janus-Pro DeepSeek](https://docs.empiriolabs.ai/models/janus-pro-deepseek.md): Autoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.
- [EmpirioLabs](https://docs.empiriolabs.ai/providers/empiriolabs.md): 1 EmpirioLabs model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Aplomb 1](https://docs.empiriolabs.ai/models/aplomb-1.md): Answers 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.
- [Exa](https://docs.empiriolabs.ai/providers/exa.md): 2 Exa models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Exa Answer](https://docs.empiriolabs.ai/models/exa-answer.md): Quick LLM-style answer to a natural-language question, grounded in fresh Exa web search results with inline citations and source links.
- [Exa Search](https://docs.empiriolabs.ai/models/exa-search.md): Web search engine for finding pages, retrieving similar pages, crawling, and dedicated code search across the open web for AI agents.
- [Google](https://docs.empiriolabs.ai/providers/google.md): 9 Google models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Gemini 3.8 Flash TTS](https://docs.empiriolabs.ai/models/gemini-3-8-flash-tts.md): Expressive speech with inline vocal tags, style direction, and two-speaker dialogue, across 130 languages and a library of more than 2,000 voices.
- [Gemini 3.8 Flash-Lite TTS](https://docs.empiriolabs.ai/models/gemini-3-8-flash-lite-tts.md): Cost-efficient speech for voice agents and dubbing, with streaming, vocal tags, and two-speaker dialogue across 101 languages and 2,000+ voices.
- [Gemini 3.1 Flash TTS](https://docs.empiriolabs.ai/models/gemini-3-1-flash-tts.md): Highly controllable TTS with new Audio Tags for precise style, tone, pace, and delivery across narration, assistants, and voice apps.
- [Gemini 2.5 Flash TTS](https://docs.empiriolabs.ai/models/gemini-2-5-flash-tts.md): Low-latency text-to-speech with single- and multi-speaker voices and controllable style, accent, and expressive tone for production apps.
- [Gemini 2.5 Pro TTS](https://docs.empiriolabs.ai/models/gemini-2-5-pro-tts.md): High-quality TTS preview for podcasts, audiobooks, and customer support, with expressive multi-speaker voices across 23+ languages.
- [Gemini 3.8 Live](https://docs.empiriolabs.ai/models/gemini-3-8-live.md): Low-latency voice conversation over one socket, with 30 voices, live video input, tool calling, and replies you can interrupt as you speak.
- [Gemini 3.8 Live Extended Thinking](https://docs.empiriolabs.ai/models/gemini-3-8-live-extended-thinking.md): Voice conversation that keeps talking while it reasons in the background, with 30 voices, live video input, tool calling, and adjustable reasoning effort.
- [Gemma 4 26B-A4B](https://docs.empiriolabs.ai/models/gemma-4-26b-a4b.md): Gemma 4 26B A4B is a Google open multimodal model with 256K context, text, image, and video input, tools, and structured output.
- [Gemma 3 27B](https://docs.empiriolabs.ai/models/gemma-3-27b.md): Open-source vision-language model with 128K context, 140+ languages, improved math/reasoning, structured outputs, and function calling.
- [GPTZero](https://docs.empiriolabs.ai/providers/gptzero.md): 1 GPTZero model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [GPTZero](https://docs.empiriolabs.ai/models/gptzero.md): Deep-learning detector that flags portions of text likely generated by AI versus human, classifying content as entirely human, AI, or mixed.
- [Hitem3D](https://docs.empiriolabs.ai/providers/hitem3d.md): 1 Hitem3D model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Hitem3D 2.0](https://docs.empiriolabs.ai/models/hitem3d-2-0.md): Production-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats.
- [Inworld](https://docs.empiriolabs.ai/providers/inworld.md): 4 Inworld models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [TTS 2 Flash](https://docs.empiriolabs.ai/models/tts-2-flash.md): Latency-first realtime voice synthesis holding one voice identity across 200+ languages, tuned for high-volume streaming workloads.
- [TTS 2](https://docs.empiriolabs.ai/models/tts-2.md): Realtime voice model that takes plain-English delivery direction, holds one voice identity across 200+ languages, and streams with word timestamps.
- [TTS 1.5 Mini](https://docs.empiriolabs.ai/models/tts-1-5-mini.md): Sub-130ms TTFB voice synthesis with 271+ voices across 15 languages, expressive prosody, and real-time SSE streaming for low-latency voice agents.
- [TTS 1.5 Max](https://docs.empiriolabs.ai/models/tts-1-5-max.md): Broadcast-quality voice synthesis with rich expressive prosody, 271+ voices across 15 languages, and real-time SSE streaming with per-word timestamps.
- [Kling AI](https://docs.empiriolabs.ai/providers/kling.md): 4 Kling AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Kling 3.0 Turbo](https://docs.empiriolabs.ai/models/kling-3-0-turbo.md): Text-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.
- [Kling O3](https://docs.empiriolabs.ai/models/kling-o3.md): Video model in Standard or Pro modes with Text-to-Video, Image-to-Video, Reference-to-Video, editing, native sound, and multi-scene transitions.
- [Kling V3](https://docs.empiriolabs.ai/models/kling-v3.md): Kuaishou's Kling 3.0 video generator with text-to-video, first and last frame image-to-video, native audio, and 720p, 1080p, or 4K output.
- [Kling v3 Motion Control](https://docs.empiriolabs.ai/models/kling-v3-motion-control.md): Kling 3.0 model that transfers motion from a reference video onto a character from a reference image, with Standard 720p and Pro 1080p tiers.
- [Linkup](https://docs.empiriolabs.ai/providers/linkup.md): 2 Linkup models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Linkup Deep Search](https://docs.empiriolabs.ai/models/linkup-deep-search.md): Iterative AI search that keeps querying when initial results are insufficient, returning more comprehensive answers than Standard mode.
- [Linkup Standard](https://docs.empiriolabs.ai/models/linkup-standard.md): AI-powered web search with detailed overviews and answers, faster than Deep Search. Ranks #1 on OpenAI SimpleQA benchmark.
- [Manus](https://docs.empiriolabs.ai/providers/manus.md): 1 Manus model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Manus](https://docs.empiriolabs.ai/models/manus.md): Autonomous AI agent that turns a high-level prompt into subtasks, calls tools and APIs, and delivers end-to-end results without manual orchestration.
- [Meta AI](https://docs.empiriolabs.ai/providers/meta.md): 4 Meta AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Muse Spark 1.3](https://docs.empiriolabs.ai/models/muse-spark-1-3.md): Meta's long-horizon agentic reasoning model with a 1,048,576-token context, image, video, and PDF understanding, web search, and tool calling.
- [Muse Spark 1.2](https://docs.empiriolabs.ai/models/muse-spark-1-2.md): Meta's updated frontier reasoning model with a 1,048,576-token context, image, video, audio, and PDF understanding, web search, and tool calling.
- [Muse Spark 1.1](https://docs.empiriolabs.ai/models/muse-spark-1-1.md): Meta frontier reasoning model with a 1,048,576-token context plus image, video, audio, and PDF understanding, web search, and tool calling.
- [Muse Glimmer 30B](https://docs.empiriolabs.ai/models/muse-glimmer-30b.md): Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.
- [Microsoft](https://docs.empiriolabs.ai/providers/microsoft.md): 1 Microsoft model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [TRELLIS.2 4B](https://docs.empiriolabs.ai/models/trellis-2-4b.md): TRELLIS.2 image-to-3D model that turns a reference image into a textured GLB asset with resolution, seed, mesh, texture, and export controls.
- [MiniMax](https://docs.empiriolabs.ai/providers/minimax.md): 5 MiniMax models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [MiniMax Music 3](https://docs.empiriolabs.ai/models/minimax-music-3.md): Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.
- [MiniMax H3](https://docs.empiriolabs.ai/models/minimax-h3.md): Generates 4 to 15 second clips at up to 2K with native stereo audio, following text, image, video, and audio references in one request.
- [MiniMax M3](https://docs.empiriolabs.ai/models/minimax-m3.md): MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input.
- [MiniMax M2.7 Highspeed](https://docs.empiriolabs.ai/models/minimax-m2-7-highspeed.md): High-speed M2.7 variant tuned for fast inference with strong general-purpose performance with strong agentic capabilities.
- [MiniMax M2.7](https://docs.empiriolabs.ai/models/minimax-m2-7.md): MiniMax M2.7 is a general-purpose reasoning chat model with interleaved thinking, function calling, and prompt caching.
- [Mistral AI](https://docs.empiriolabs.ai/providers/mistral.md): 2 Mistral AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Mistral Small 4](https://docs.empiriolabs.ai/models/mistral-small-4.md): Hybrid model unifying Instruct, Reasoning (Magistral), and Devstral families: 40% lower completion time and 3x throughput vs Small 3.
- [Mistral Small 3.1](https://docs.empiriolabs.ai/models/mistral-small-3-1.md): 24B-parameter multimodal model with 128K context for image analysis, programming, math, and multilingual tasks, tuned for efficient local inference.
- [Moonshot AI](https://docs.empiriolabs.ai/providers/moonshot.md): 4 Moonshot AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Kimi K3](https://docs.empiriolabs.ai/models/kimi-k3.md): Kimi K3 is Moonshot's flagship reasoning model with a 1M token context, always-on thinking, native web search, and text, image, and video inputs.
- [Kimi K2.6](https://docs.empiriolabs.ai/models/kimi-k2-6.md): Kimi K2.6 is a Moonshot multimodal reasoning model with 256K context, strong coding, and text, image, and video inputs.
- [Kimi K2.7 Code](https://docs.empiriolabs.ai/models/kimi-k2-7-code.md): Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs.
- [Kimi K2.7 Code Highspeed](https://docs.empiriolabs.ai/models/kimi-k2-7-code-highspeed.md): Kimi K2.7 Code Highspeed is the faster-serving tier of Moonshot's agentic coding model, with 256K context, always-on reasoning, and image and video input.
- [OpenAI](https://docs.empiriolabs.ai/providers/openai.md): 3 OpenAI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [GPT Image 2](https://docs.empiriolabs.ai/models/gpt-image-2.md): OpenAI's flagship image model with strong prompt fidelity, crisp text rendering, and instruction-based editing across up to 16 reference images.
- [Whisper Large v3 Turbo](https://docs.empiriolabs.ai/models/whisper-large-v3-turbo.md): Controlled self-hosted Whisper Large v3 Turbo transcription with multilingual ASR, translation, VAD, timestamps, subtitles, hotwords, and decoder controls…
- [OpenAI Whisper 1](https://docs.empiriolabs.ai/models/openai-whisper-1.md): Whisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.
- [OpenMOSS](https://docs.empiriolabs.ai/providers/openmoss.md): 1 OpenMOSS model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [MOSS Video and Audio](https://docs.empiriolabs.ai/models/moss-video-and-audio.md): Open-source 32B MoE foundation model that generates synchronized video and audio in one inference step with precise dual-tower lip-sync.
- [Perplexity](https://docs.empiriolabs.ai/providers/perplexity.md): 7 Perplexity models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Perplexity Advanced Deep Research](https://docs.empiriolabs.ai/models/perplexity-advanced-deep-research.md): Institutional-grade research agent that runs many rounds of web search and page reading, with maximum depth and extensive source coverage.
- [Perplexity Deep Research](https://docs.empiriolabs.ai/models/perplexity-deep-research.md): Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.
- [Perplexity Pro Search](https://docs.empiriolabs.ai/models/perplexity-pro-search.md): Sonar Pro as an agentic researcher: chains web searches, fetches full pages, and streams live reasoning, adapting strategy for complex queries.
- [Perplexity Search](https://docs.empiriolabs.ai/models/perplexity-search.md): Real-time web search with filtering by domain, language, date, and more. Returns search results, not LLM responses; no file uploads.
- [Perplexity Sonar](https://docs.empiriolabs.ai/models/perplexity-sonar.md): Real-time web-connected search with accurate citations and customizable sources for up-to-date AI search integration in production apps.
- [Perplexity Sonar Pro](https://docs.empiriolabs.ai/models/perplexity-sonar-pro.md): Search-grounded model with double the citations and a larger context window, tuned for complex queries needing in-depth, nuanced answers.
- [Perplexity Sonar Reasoning Pro](https://docs.empiriolabs.ai/models/perplexity-sonar-reasoning-pro.md): Reasoning model that researches over several rounds of web search, chaining evidence across many sources before it answers, with inline citations.
- [PixVerse](https://docs.empiriolabs.ai/providers/pixverse.md): 7 PixVerse models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Pixverse C1](https://docs.empiriolabs.ai/models/pixverse-c1.md): Cinema-grade video model for action and effects work, from text, images, first and last frames, or references, with native synchronized audio.
- [Pixverse v6](https://docs.empiriolabs.ai/models/pixverse-v6.md): Generates video from text, images, first and last frames, or up to seven references, with native audio, multi-shot cuts, and clip extension.
- [Pixverse v5.6](https://docs.empiriolabs.ai/models/pixverse-v5-6.md): Generates videos from text or 1-2 frame image prompts up to 1080p, multiple aspect ratios, 5-10s durations, with optional synchronized audio.
- [Pixverse v5](https://docs.empiriolabs.ai/models/pixverse-v5.md): Cinematic video generation in Text-to-Video, Image-to-Video, and Transition modes with high detail, fluid motion, and lifelike animations.
- [Pixverse Lip Sync](https://docs.empiriolabs.ai/models/pixverse-lipsync.md): Aligns mouth movement in an existing video to an uploaded audio track or to text spoken by one of fourteen built-in voices.
- [Pixverse Avatar](https://docs.empiriolabs.ai/models/pixverse-avatar.md): Turns a single portrait into a talking avatar video, driven by an uploaded audio track or by text spoken with a built-in voice.
- [Pixverse Edit](https://docs.empiriolabs.ai/models/pixverse-edit.md): Six video transformations in one model: prompt editing, restyling, subject swap, motion transfer, upscaling, and generated sound effects.
- [Sakana AI](https://docs.empiriolabs.ai/providers/sakana.md): 4 Sakana AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Fugu Ultra v2.0](https://docs.empiriolabs.ai/models/fugu-ultra-v2-0.md): Flagship multi-agent conductor for the hardest reasoning, coding, and research work, with 1M context, image input, and web search.
- [Fugu Ultra v1.1](https://docs.empiriolabs.ai/models/fugu-ultra-v1-1.md): Updated multi-agent conductor for hard reasoning, coding, and research, with distinct max effort, 1M context, image input, and web search.
- [Fugu Ultra v1.0](https://docs.empiriolabs.ai/models/fugu-ultra-v1-0.md): Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.
- [Fugu Max](https://docs.empiriolabs.ai/models/fugu-max.md): Cost-efficient multi-agent conductor that assembles a right-sized expert team per task, with 1M context, image input, and web search.
- [Sonilo](https://docs.empiriolabs.ai/providers/sonilo.md): 7 Sonilo models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Sonilo Sound Effects 1.0](https://docs.empiriolabs.ai/models/sonilo-sound-effects-1-0.md): Frame-accurate sound effects placed on the action in a video, or generated from a text description, with per-segment direction.
- [Sonilo v1.1](https://docs.empiriolabs.ai/models/sonilo-v1-1.md): Frame-synced soundtracks generated straight from video, or music from a text prompt, with per-segment direction and stem separation.
- [Sonilo Video to Video](https://docs.empiriolabs.ai/models/sonilo-video-to-video.md): Returns your own video with a generated soundtrack, frame-synced effects, or both mixed in, keeping the original picture untouched.
- [Sonilo Video Translation](https://docs.empiriolabs.ai/models/sonilo-video-translation.md): Dubs a video into 24 languages with lip-sync matched voices, returning one finished video per language plus optional subtitle tracks.
- [Sonilo Audio Ducking](https://docs.empiriolabs.ai/models/sonilo-audio-ducking.md): Mixes narration over a music bed, dipping the music under the voice automatically so dialogue stays clear without manual automation.
- [Sonilo Proofread](https://docs.empiriolabs.ai/models/sonilo-proofread.md): Transcribes a video and translates the script into 24 languages, returning editable subtitle tracks you can correct before dubbing.
- [Sonilo Video Analysis](https://docs.empiriolabs.ai/models/sonilo-video-analysis.md): Reads a video and writes a timed creative brief, with a prompt per scene for music and sound design, ready to drive a later generation.
- [Soul AI Lab](https://docs.empiriolabs.ai/providers/soul-ai-lab.md): 1 Soul AI Lab model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [SoulX Podcast](https://docs.empiriolabs.ai/models/soulx-podcast.md): Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control (laughter, sighs) and zero-shot voice cloning.
- [Stability AI](https://docs.empiriolabs.ai/providers/stability.md): 2 Stability AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Stable Audio 2.5](https://docs.empiriolabs.ai/models/stable-audio-2-5.md): Up-to-3-minute audio from text with text-to-audio, audio-to-audio, and audio inpainting for music production, sound design, and remixing.
- [Stable Audio 2.0](https://docs.empiriolabs.ai/models/stable-audio-2-0.md): Generates audio up to 3 minutes from text prompts, supporting text-to-audio and audio-to-audio with adjustable duration, steps, and CFG scale.
- [StepFun](https://docs.empiriolabs.ai/providers/stepfun.md): 17 StepFun models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Step 5 Preview](https://docs.empiriolabs.ai/models/step-5-preview.md): Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.
- [Step 3.7 Flash](https://docs.empiriolabs.ai/models/step-3-7-flash.md): StepFun multimodal reasoning model with image and video input, tool calling, adjustable reasoning effort, and 256K context.
- [Step 3.5 Flash 2603](https://docs.empiriolabs.ai/models/step-3-5-flash-2603.md): Agent-optimized Step 3.5 Flash variant with low and high reasoning effort modes.
- [Step 3.5 Flash](https://docs.empiriolabs.ai/models/step-3-5-flash.md): StepFun text reasoning model for agents, coding, tool calling, and long-context analysis.
- [StepAudio 3 Chat](https://docs.empiriolabs.ai/models/stepaudio-3-chat.md): Audio and text conversation model that reasons before answering, with function calling and JSON output.
- [StepAudio 2.5 Chat](https://docs.empiriolabs.ai/models/stepaudio-2-5-chat.md): StepFun audio and text conversation model with text output and paralinguistic understanding.
- [StepAudio 3 TTS](https://docs.empiriolabs.ai/models/stepaudio-3-tts.md): Human-level speech synthesis across six languages, with 12 system voices, natural-language delivery direction, and streaming playback.
- [StepAudio 2.5 TTS](https://docs.empiriolabs.ai/models/stepaudio-2-5-tts.md): Contextual StepFun text-to-speech model with natural-language voice direction and expressive delivery.
- [StepAudio 3 Gen](https://docs.empiriolabs.ai/models/stepaudio-3-gen.md): Generates dialogue, sound effects, ambience, and background music together in one clip from a written scene.
- [StepAudio 3 Music](https://docs.empiriolabs.ai/models/stepaudio-3-music.md): Writes complete songs from a style description, with vocals, arrangement, and mixing, or instrumentals and covers.
- [StepAudio 3 ASR Max](https://docs.empiriolabs.ai/models/stepaudio-3-asr-max.md): Context-aware transcription for proper nouns, technical terms, dialects, and difficult audio including whispers, fast speech, and singing.
- [StepAudio 2.5 ASR Stream](https://docs.empiriolabs.ai/models/stepaudio-2-5-asr-stream.md): Live transcription over a socket, returning partial results as the speaker talks, with voice activity detection marking each sentence.
- [StepAudio 2.5 ASR](https://docs.empiriolabs.ai/models/stepaudio-2-5-asr.md): StepFun streaming speech recognition model for Chinese and English audio transcription.
- [StepAudio 3 Realtime](https://docs.empiriolabs.ai/models/stepaudio-3-realtime.md): Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.
- [StepAudio 2.5 Realtime](https://docs.empiriolabs.ai/models/stepaudio-2-5-realtime.md): Speech in, speech out, over one socket, with paralinguistic understanding of tone and pacing.
- [Step Image Edit 2](https://docs.empiriolabs.ai/models/step-image-edit-2.md): StepFun image generation and image editing model for text-to-image and single-image edits.
- [Step TTS 2](https://docs.empiriolabs.ai/models/step-tts-2.md): StepFun text-to-speech model with official voices, custom cloned voices, and voice tag controls.
- [Tavily](https://docs.empiriolabs.ai/providers/tavily.md): 2 Tavily models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Tavily Research](https://docs.empiriolabs.ai/models/tavily-research.md): Multi-search research assistant that explores a topic, analyzes sources, and produces a detailed research report with citations.
- [Tavily Search](https://docs.empiriolabs.ai/models/tavily-search.md): Web search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.
- [Tencent](https://docs.empiriolabs.ai/providers/tencent.md): 2 Tencent models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Hunyuan Video 1.5](https://docs.empiriolabs.ai/models/hunyuan-video-1-5.md): 8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.
- [Hunyuan Image 3](https://docs.empiriolabs.ai/models/hunyuan-image-3.md): Open-source text-to-image model on a multimodal Mixture-of-Experts architecture with photorealistic detail and strong multilingual text rendering.
- [VITA-Group / EPFL](https://docs.empiriolabs.ai/providers/vita-epfl.md): 1 VITA-Group / EPFL model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [SVI 2.0 Pro](https://docs.empiriolabs.ai/models/svi-2-0-pro.md): Stable Video Infinity 2.0 Pro on WAN 2.2: extends still images into theoretically infinite-length video while keeping consistent character IDs.
- [WinFunc](https://docs.empiriolabs.ai/providers/winfunc.md): 1 WinFunc model on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [DeepReasoning](https://docs.empiriolabs.ai/models/deepreasoning.md): Pairs DeepSeek R1 chain-of-thought reasoning with Anthropic Claude creative and code generation behind a unified, data-controlled interface.
- [xAI](https://docs.empiriolabs.ai/providers/xai.md): 2 xAI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [Grok Imagine Image 2.0](https://docs.empiriolabs.ai/models/grok-imagine-image-2-0.md): Text-to-image plus multi-reference editing with up to five source images, automatic or pinned quality tiers, and 1K or 2K output resolution.
- [Grok Imagine Video 1.5](https://docs.empiriolabs.ai/models/grok-imagine-video-1-5.md): Text-to-video, image-to-video, and reference-to-video generation with up to seven reference images for consistent characters, up to 15 seconds at 1080p.
- [Xiaomi](https://docs.empiriolabs.ai/providers/xiaomi.md): 5 Xiaomi models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [MiMo V2.6 Pro](https://docs.empiriolabs.ai/models/mimo-v2-6-pro.md): Trillion-parameter flagship for agentic work, with native image, video, and audio understanding and reasoning across a 1M context.
- [MiMo V2.6 Pro UltraSpeed](https://docs.empiriolabs.ai/models/mimo-v2-6-pro-ultraspeed.md): High-throughput build of the trillion-parameter flagship, matching its full-modality reasoning while generating output substantially faster.
- [MiMo V2.5 Pro](https://docs.empiriolabs.ai/models/mimo-v2-5-pro.md): Top-tier model for agentic workflows, complex software engineering, and long-horizon tasks, sustaining work across 1000+ tool calls on 1M context.
- [MiMo V2.6 Flash](https://docs.empiriolabs.ai/models/mimo-v2-6-flash.md): Low-cost full-modality reasoner with native image, video, and audio understanding on a 1M context, built for high-frequency production workloads.
- [MiMo V2.5](https://docs.empiriolabs.ai/models/mimo-v2-5.md): Multimodal model with native visual and audio understanding on a 1M context, designed to reason and act across modalities in agentic workflows.
- [Z.ai](https://docs.empiriolabs.ai/providers/zhipu.md): 8 Z.ai models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.
- [GLM 5.3](https://docs.empiriolabs.ai/models/glm-5-3.md): Coding 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.
- [GLM 5.2](https://docs.empiriolabs.ai/models/glm-5-2.md): Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, native web search, and tool calling.
- [GLM 5.1](https://docs.empiriolabs.ai/models/glm-5-1.md): Long-context Zhipu AI reasoning model with 202K context, 128K output, tool calling, structured output, and cache support.
- [GLM 5.3 Flash](https://docs.empiriolabs.ai/models/glm-5-3-flash.md): Natively multimodal flash model with a 1M token context, image and video input, always-on reasoning, native web search, and tool calling.
- [GLM 4.7 Flash](https://docs.empiriolabs.ai/models/glm-4-7-flash.md): Free lightweight GLM-4.7 text model for coding, reasoning, long-context writing, and general chat.
- [GLM 4.6V Flash](https://docs.empiriolabs.ai/models/glm-4-6v-flash.md): Free multimodal GLM-4.6V model for image, video, file, and text understanding with native function calling.
- [GLM 4.5 Flash](https://docs.empiriolabs.ai/models/glm-4-5-flash.md): Free lightweight GLM-4.5 text model for reasoning, coding, long-form chat, and general language tasks.
- [GLM TTS](https://docs.empiriolabs.ai/models/glm-tts.md): LLM-based text-to-speech with zero-shot voice cloning from 3-10s of audio and emotion-expressive, controllable output via multi-reward RL.
- [API Reference](https://docs.empiriolabs.ai/api-reference-overview.md): Complete REST surface: chat, responses, embeddings, reranks, decisions, images, video, 3D, audio, transcription, search, detection, batch, jobs
- [AI Agent Access](https://docs.empiriolabs.ai/ai-agent-access.md): Pre-built context bundles for AI coding assistants
- [Support](https://docs.empiriolabs.ai/support.md): Get help with onboarding, integrations, and production issues
- [Changelog](https://docs.empiriolabs.ai/documentation/changelog.md): Product updates and platform release notes