Models (2)·续2
Compare
<h3>gemini-omni-flash</h3>GoogleText-to-Video Preview high-performance multimodal video generation and editing model with conversational controls and generated audio.
Compare
<h3>nano-banana</h3>GoogleText-to-Image Google's fast image generation model producing high-quality images from text prompts.
Compare
<h3>nano-banana-2</h3>GoogleText-to-Image Google's second-generation image generation model with improved quality and speed.
Compare
<h3>nano-banana-2-lite</h3>GoogleText-to-Image Google's fastest Gemini image generation model for rapid image creation and iteration.
Compare
<h3>nano-banana-2.1</h3>GoogleText-to-Image Google's Nano Banana 2.1 image generation and editing model, optimized for a balance of quality and performance.
Compare
<h3>nano-banana-pro</h3>GoogleText-to-Image Google's higher-quality image generation model with improved detail and prompt adherence.
Compare
<h3>veo-3.1</h3>GoogleText-to-Video Google's latest video generation model with improved quality, motion, and audio generation.
Compare
<h3>veo-3.1-fast</h3>GoogleText-to-Video A faster version of Veo 3.1 optimized for lower latency while maintaining high-quality video and audio output.
Compare
<h3>tts-1.5-max</h3>InworldText-to-Speech Highest-quality text-to-speech with under 200ms latency, emotion control, and 15-language support.
Compare
<h3>tts-1.5-mini</h3>InworldText-to-Speech Ultra-fast, cost-efficient text-to-speech with approximately 120ms latency and 15-language support.
Compare
<h3>tts-2</h3>InworldText-to-Speech Inworld's most powerful and expressive text-to-speech model. Builds on TTS 1.5 with rich expressive speech, real-time latency, natural language steering (e.g. [whisper], [say excitedly]), and stronger multilingual support across 15 production languages plus 90+ experimental languages.
Compare
k<h3>krea-2-large</h3>kreaText-to-Image More than 2x the size of Medium, with softer post-training. Outputs are rawer, more textured, and more flexible — at its best, Large produces results Medium can't match. Strongest on photorealism, raw looks (motion blur, grain, low dynamic range), and expressive and artistic styles.
Compare
k<h3>krea-2-medium</h3>kreaText-to-Image Smaller, faster, more cost-efficient. Extensive post-training makes outputs especially stable and consistent across generations. Strongest on illustration, anime, painting, and other expressive or artistic styles.
Compare
k<h3>krea-2-medium-turbo</h3>kreaText-to-Image The fastest Krea 2 model, built for low-cost iteration on expressive illustrations, style-driven concepts, and rapid visual exploration. Keeps the Krea 2 style system and expressive visual range but uses a distilled sampling schedule so you can move through ideas much faster. Especially useful for expressive illustration, graphic styles, typography experiments, and quick campaign or concept directions.
Compare
k<h3>krea-3</h3>kreaImage-to-Image Krea 3 is Krea's image generation and editing model, in beta. It edits one or more reference images from a text instruction, or generates an image from the prompt alone. References are passed as HTTP(S) URLs in image_urls (up to 8). Outputs go up to 2K, with optional thinking_mode, aspect_ratio, seed and regional_edit controls.
Compare
l<h3>ltx-2-5-fast</h3>lightricksText-to-Video Lightricks LTX-2.5 Fast is a fast video generation model for text-to-video and image-to-video workflows, with synchronized audio, configurable duration, resolution, and frame rate.
Compare
<h3>muse-spark-1.1</h3>MetaText Generation Muse Spark 1.1 is Meta's agentic and coding model for multi-step tool loops, software engineering assistants, and long-context reasoning.
Compare
<h3>muse-spark-1.2</h3>MetaText Generation Muse Spark 1.2 is Meta's agentic and coding model for multi-step tool loops, software engineering assistants, and long-context reasoning.
Compare
<h3>muse-spark-1.3</h3>MetaText Generation Muse Spark 1.3 is Meta's latest agentic and coding model, tuned for multi-step tool loops, browser tasks, software engineering, and long-horizon reasoning.
Compare
<h3>muse-spark-open</h3>MetaText Generation Meta's most capable open-weight model, built for agentic coding. Show it a screenshot, chart, or photo alongside your request and it reasons over both to write working code, call tools, and carry multi-step tasks across a 1M-token context.
Compare
<h3>muse-wonder-1.0</h3>MetaText Generation Muse Wonder 1.0 is Meta's agentic and coding model for complex software engineering, multi-step tool loops, and long-context reasoning.
Compare
<h3>h3</h3>MiniMaxText-to-Video A multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation with 768P and 2K output.
Compare
<h3>h3-max</h3>MiniMaxText-to-Video A fast multimodal video generation model supporting text-to-video and image-to-video generation at 480P and 768P.
Compare
<h3>hailuo-2.3</h3>MiniMaxText-to-Video A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across text-to-video and image-to-video workflows.
Compare
<h3>hailuo-2.3-fast</h3>MiniMaxText-to-Video A lower-latency version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization while enabling faster iteration.
Compare
<h3>m2.7</h3>MiniMaxText Generation MiniMax's M2.7 language model with multilingual capabilities.
Compare
<h3>m3</h3>MiniMaxText Generation MiniMax's M3 language model with frontier coding and agentic capabilities, a 1M token context window, and multilingual support.
Compare
<h3>music-2.6</h3>MiniMaxMusic Generation MiniMax's music generation model that creates full-length songs with vocals from text prompts and lyrics, or instrumental tracks. Supports BPM/key control and auto-generated lyrics.
Compare
<h3>speech-2.8-hd</h3>MiniMaxText-to-Speech MiniMax Speech 2.8 HD focuses on studio-grade audio generation with emotion control, multilingual support (40+ languages), and voice cloning.
Compare
<h3>speech-2.8-turbo</h3>MiniMaxText-to-Speech MiniMax Speech 2.8 Turbo turns text into natural, expressive speech with voice cloning, emotion control, and 40+ language support at faster speeds.
Compare
<h3>kimi-k3</h3>Moonshot AIText Generation Kimi K3 is Moonshot's flagship 2.8 trillion-parameter model, built on Kimi Delta Attention (a hybrid linear attention mechanism) with Attention Residuals. It offers native visual understanding, always-on reasoning, and a 1M-token context window for long-horizon coding, knowledge work, and deep reasoning tasks.
Compare
<h3>gpt-4.1</h3>OpenAIText Generation OpenAI's flagship GPT model for complex tasks with a million-token context window.
Compare
<h3>gpt-4.1-mini</h3>OpenAIText Generation Fast, affordable version of GPT-4.1 with a million-token context window.
Compare
<h3>gpt-4.1-nano</h3>OpenAIText Generation GPT-4.1 Nano is OpenAI’s smallest and cheapest GPT-4.1 variant, optimized for high-throughput, low-latency tasks.
Compare
<h3>gpt-4o</h3>OpenAIText Generation GPT-4o is OpenAI’s multimodal flagship, accepting text and images and responding quickly across a wide range of tasks.
Compare
<h3>gpt-4o-mini</h3>OpenAIText Generation GPT-4o Mini is the lightweight, low-cost variant of GPT-4o, well suited to high-volume tasks with multimodal inputs.
Compare
<h3>gpt-4o-transcribe</h3>OpenAIAutomatic Speech Recognition A speech-to-text model that uses GPT-4o to transcribe audio with improved word error rate and better language recognition compared to original Whisper models.
Compare
<h3>gpt-5</h3>OpenAIText Generation OpenAI's model excelling at coding, writing, and reasoning.
Compare
<h3>gpt-5-mini</h3>OpenAIText Generation GPT-5 Mini is the lightweight, low-cost variant of GPT-5, well suited to high-volume coding and reasoning tasks.
Compare
<h3>gpt-5-nano</h3>OpenAIText Generation GPT-5 Nano is OpenAI’s smallest GPT-5 variant, optimized for low latency and cheap, high-throughput tasks.
Compare
<h3>gpt-5.1</h3>OpenAIText Generation GPT-5.1 is OpenAI’s incremental improvement over GPT-5, with stronger coding, reasoning, and writing.
Compare
<h3>gpt-5.4</h3>OpenAIText Generation GPT-5.4 is OpenAI's flagship model with strong coding, reasoning, and multimodal capabilities.
Compare
<h3>gpt-5.4-mini</h3>OpenAIText Generation GPT-5.4 mini is a smaller, faster, and more cost-efficient version of GPT-5.4 for lightweight tasks.
Compare
<h3>gpt-5.4-nano</h3>OpenAIText Generation GPT-5.4 nano is OpenAI's smallest and fastest model, optimized for edge and low-latency use cases.
我的书签
添加书签
移除书签
