Explore AI Models

[Core Function] GPT Image 2 is a state-of-the-art text-to-image generation model. [Strengths] It excels at generating highly detailed, photorealistic images from text descriptions, with native support for ultra-high resolutions including 2K and 4K (up to 3840x2160). [Best For] Highly recommended for: cinematic landscapes, detailed character portraits, high-end commercial concept art, and any scenario requiring maximum resolution and visual fidelity. [Limitations] Do NOT use this model if you need a transparent background (e.g., for icons or UI assets), as it does not support the `background: transparent` parameter. [Routing] Use this model by default for all high-quality image generation requests. If the user explicitly asks for an image with a transparent background, route to GPT Image 1.5 instead.

[Core Function] Seedance 2.0 T2V is ByteDance Dreamina Seedance 2.0 text-to-video. [Strengths] Supports 480p/720p/1080p/4k, 24 fps, 4-15s MP4 output. Text-only input — do not pass images, video, or audio. [Routing] Use for high-fidelity text-to-video when quality or 4k output is requested.

[Core Function] Qwen Image 3.0 Pro is Alibaba's latest text-to-image model with strong prompt following and photorealism. [Strengths] It supports free-form output size (width*height), optional negative prompts, intelligent prompt rewrite, batch generation of 1-6 images, and long structured prompts for complex layouts. [Best For] Highly recommended for: photorealistic stills, marketing posters with readable text, detailed scene compositions, multi-panel layouts, product hero shots, and multi-variant creative exploration (n up to 6). [Limitations] Do NOT use this if the user needs native 4K output, thinking-mode reasoning, or image editing with reference images (use Qwen Image 3.0 Pro Edit for edits). Keep total pixels within 512*512 to 2048*2048. Very long prompts combined with a long negative_prompt may exceed the model input capacity (about 4.5k tokens total). [Routing] Prefer this over Qwen Image 2.0 Pro for new Qwen Image text-to-image work. If the user provides reference image(s) to edit, route to Qwen Image 3.0 Pro Edit instead.

[Core Function] Kling V3 T2I is the flagship text-to-image model (POST /images/generations, model_name=kling-v3). [Strengths] High aesthetic quality, prompt adherence, 1K/2K. [Best For] Concept art and photorealistic generation without a reference image. [Limitations] No reference image; for I2I use kling-v3-i2i; for multi-image/series use kling-v3-omni-image. [Routing] Default for Kling text-to-image.

[Core Function] Kling V3 T2V is the next-generation text-to-video base model. [Strengths] It natively supports generating ultra-long 15-second videos, 4K resolution, and synchronized native audio directly from text. [Best For] Highly recommended for: high-end cinematic creation, 4K video generation, and creating long-form scenes with integrated sound. [Limitations] Do NOT use this model if you need complex multi-shot narratives or deep physics reasoning; use V3 Omni or Video O1 respectively. [Routing] Use this model by default for high-quality text-to-video tasks that require up to 15 seconds, 4K resolution, or native audio without reference images.

[Core Function] Qwen-Audio 3.0 TTS Plus is Alibaba's high-quality Qwen-Audio text-to-speech model on the same SpeechSynthesizer endpoint family as CosyVoice. [Strengths] Natural speech synthesis with voice, format, sample-rate, prosody, SSML, instruction, language_hint, and AIGC watermark controls; system voices include longanlingxin and longanlufeng (see the Qwen-Audio-TTS voice list). [Best For] Premium narration, brand voiceovers, multilingual product audio, and quality-sensitive batch TTS when Qwen-Audio voices are preferred. [Limitations] Do NOT mix Flash-only voices (e.g. longanhuan_v3.6) with Plus. [Routing] Choose Plus when speech quality is the priority. Choose qwen-audio-3.0-tts-flash when lower latency matters more.

[Core Function] Grok Imagine Image (Quality) is xAI's high-fidelity text-to-image generation model. [Strengths] It excels at producing richly detailed, high-quality images from a text prompt, with flexible aspect ratios and an optional 2K resolution. [Best For] Highly recommended for: detailed concept art, marketing visuals, and any scenario where image quality is prioritized over generation speed. [Limitations] Do NOT use this model when latency is critical, as generation is slower than the standard model. [Routing] Use this model by default when the user emphasizes quality or detail. For faster, lighter generation use Grok Imagine Image (standard).

[Core Function] Grok Imagine Video is xAI's text-to-video generation model. [Strengths] It excels at generating short, dynamic video clips directly from a text prompt, with controllable duration, aspect ratio, and resolution. [Best For] Highly recommended for: short social clips, animated concepts, and dynamic scene generation from a description. [Limitations] Do NOT use this model when you have a starting image or reference subjects, or when you need resolutions above 720p or clips longer than 15 seconds; it is limited to 480p/720p and 15s. [Routing] Use this model when the user wants a video from text only. If a starting image is provided, route to the Image-to-Video model; for reference-driven character video, use Reference-to-Video.

[Core Function] Nano Banana 2.1 Edit is Google's fast image-editing and video-to-image model, exposed as google/nano-banana-2.1-edit. [Strengths] It edits up to 14 reference images, or one HTTPS video plus up to 10 images, at 1K, 2K, or 4K, with improved character and multi-reference consistency. thinkingLevel defaults to medium. Optional systemInstruction is omitted when blank. enableWebSearch turns on Google Search grounding (web and image search) only when true. [Best For] Prompted restyling, multi-image product and character edits, and turning a video into a still. [Limitations] Do NOT use this model for text-only generation, 512-pixel output, or audio generation. At least one of image or video is required. seed, temperature, topP, topK, and logprobs are rejected. [Routing] Use this endpoint when the user provides images or a video and wants Nano Banana 2.1. Use google/nano-banana-2-edit for the previous Gemini 3.1 Flash Image editor, including 512 output. Use google/nano-banana-2.1 when there is no visual input. Use google/nano-banana-pro-edit for the highest-fidelity still edits that do not need video input.

[Core Function] Nano Banana 2.1 is Google's fast text-to-image model on Gemini 3.6 Flash, exposed as google/nano-banana-2.1. [Strengths] It keeps Flash-level speed at 1K, 2K, and 4K, with stronger visual quality, text rendering, and real-world knowledge than Nano Banana 2. thinkingLevel trades latency for quality and defaults to medium. Optional systemInstruction is omitted when blank. enableWebSearch turns on Google Search grounding (web and image search) only when true. [Best For] High-volume image production, posters and diagrams with readable text, localized text, and rapid iteration on new text-to-image work. [Limitations] Do NOT use this model for image or video editing, 512-pixel output, audio input, or reference images. This endpoint accepts a prompt only. seed, temperature, topP, topK, and logprobs are rejected. [Routing] Use google/nano-banana-2.1 for new text-to-image work. Use google/nano-banana-2 when the caller needs the 512 resolution of Gemini 3.1 Flash Image. Use google/nano-banana-2.1-edit when the user supplies images or a video. Use google/nano-banana-pro when the user wants the highest-end professional stills.

[Core Function] MiniMax H3 Max V2V generates video guided by one or more reference videos plus a text prompt. [Strengths] It accepts up to 3 reference videos with optional reference images and audios, 5-15 second duration, 480P or 768P output, optional aspect ratio defaulting to 16:9, and optional prompt_expansion_mode (disabled, balanced, or quality). [Best For] Highly recommended for: motion remix, style transfer from video clips, keeping subject motion while changing the scene description, and multi-clip reference guidance. [Limitations] Do NOT use this model for text-only generation, first or last frame transitions, or if you need 2K or a 4 second clip. prompt, duration, resolution, and reference_videos are required. Do NOT send first_frame_image or last_frame_image on this endpoint. [Routing] Choose MiniMax H3 Max V2V when the user provides reference videos. For reference stills only, use MiniMax H3 Max I2V. For start or end frames, use MiniMax H3 Max FL2V. For text only, use MiniMax H3 Max T2V. For 2K or 4 second clips, use MiniMax H3 V2V.

[Core Function] MiniMax H3 Max I2V generates video from reference images plus a text prompt. [Strengths] It accepts up to 9 reference images and optional reference audios, with 5-15 second duration, 480P or 768P output, optional aspect ratio defaulting to 16:9, and optional prompt_expansion_mode (disabled, balanced, or quality). [Best For] Highly recommended for: character or style consistency from stills, product look references, multi-image subject guidance, and prompt-driven scenes featuring a referenced subject. [Limitations] Do NOT use this model for first or last frame transitions, when the primary input is a reference video, or if you need 2K or a 4 second clip. prompt, duration, resolution, and reference_images are required. Do NOT send first_frame_image, last_frame_image, or reference_videos on this endpoint. [Routing] Choose MiniMax H3 Max I2V when the user provides reference stills. For start or end frames, use MiniMax H3 Max FL2V. For reference videos, use MiniMax H3 Max V2V. For text only, use MiniMax H3 Max T2V. For 2K or 4 second clips, use MiniMax H3 I2V.

[Core Function] MiniMax H3 Max FL2V generates video guided by a first frame, a last frame, or both. [Strengths] It supports first-only, last-only, and first-plus-last conditioning with 5-15 second duration and 480P or 768P output. Output framing follows the input frame imagery. Optional prompt_expansion_mode is disabled, balanced (default), or quality. [Best For] Highly recommended for: start-frame animation, end-frame targeting, before-and-after transitions, and storyboard frame bridging. [Limitations] Do NOT use this model for pure text-to-video, reference-image subject remix, or reference-video remix, or if you need 2K or a 4 second clip. Provide prompt, duration, resolution, and at least one of first_frame_image or last_frame_image. Do NOT send ratio, reference_images, reference_videos, or reference_audios on this endpoint. [Routing] Choose MiniMax H3 Max FL2V when the user supplies a start and/or end frame. For reference images without frame roles, use MiniMax H3 Max I2V. For reference videos, use MiniMax H3 Max V2V. For text only, use MiniMax H3 Max T2V. For 2K or 4 second clips, use MiniMax H3 FL2V.

[Core Function] MiniMax H3 Max T2V creates video from a text prompt only. [Strengths] It supports 5-15 second clips, 480P or 768P output, concrete aspect ratios from cinematic ultrawide to vertical, and optional prompt_expansion_mode (disabled, balanced, or quality). [Best For] Highly recommended for: prompt-only storyboards, character-driven shorts, cinematic B-roll from text, and drafts without image inputs. [Limitations] Do NOT use this model if you need to condition on images, first or last frames, or reference videos, or if you need 2K or a 4 second clip. prompt, duration, resolution, and ratio are required; ratio must be one of the documented aspect ratios. [Routing] Choose MiniMax H3 Max T2V for text-only MiniMax H3 Max video. If the user provides a start or end frame, use MiniMax H3 Max FL2V. If they provide reference images, use MiniMax H3 Max I2V. If they provide reference videos, use MiniMax H3 Max V2V. For 2K or 4 second clips, use MiniMax H3 T2V.

[Core Function] Seedance 2.5 R2V is ByteDance Dreamina Seedance 2.5 reference-to-video generation from up to 30 reference images. [Strengths] It supports optional reference audio, fixed or adaptive aspect ratio, 480p/720p/1080p, 4-30 second duration, and mp4 or mov output. [Best For] Highly recommended for: multi-image character consistency and image-led storytelling on Seedance 2.5. [Limitations] Do NOT send first_frame_image, last_frame_image, or video_urls. Do NOT use audio_urls alone. Do NOT use this model when the user requires 4k output. [Routing] Prefer this model when the user provides reference images without a driving video. Use Seedance 2.5 I2V for first-frame or first-and-last-frame animation, Seedance 2.5 T2V for text-only requests, and Seedance 2.5 V2V when reference video is required.

[Core Function] GPT Image 2.5 Flare Edit is a speed-oriented image editing model. [Strengths] Supports up to 16 input images, optional mask-based local edits, resolution tiers up to 4K, and transparent backgrounds. [Best For] Product image changes, masked object replacements, and edits guided by multiple reference images. [Limitations] Do NOT use this for editing more than 16 input images or selecting arbitrary pixel dimensions. Exact input fidelity control is not exposed. [Routing] Choose this variant when speed is the priority; use GPT Image 2.5 Sunburst Edit when image quality is the priority.