类型(5)
提供商(16)
能力(12)
Coming soon: the fast Kling 4.0 model. 3-20s at 720p, text-to-video, image-to-video, Omni Reference.
查看详情
Kling 4.0 Flash
Kling
Coming soon: the fast Kling 4.0 model. 3-20s at 720p, text-to-video, image-to-video, Omni Reference.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
查看详情
FLUX 3 Video
Black Forest Labs
Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
- 文本生成视频
- 图像生成视频
- 视频生成视频
Bounding-box layouts and edits, up to 10 references, 15 aspect ratios plus auto, 768sq to 4K.
试用此模型FLUX 3 Image
Black Forest Labs
Bounding-box layouts and edits, up to 10 references, 15 aspect ratios plus auto, 768sq to 4K.
- 文本生成图像
- 图像生成图像
5.6B open weights, text-to-image, editing, up to 4 references, 7 aspect ratios to 4 MP, 16 steps.
试用此模型FLUX 3 Image Klein
Black Forest Labs
5.6B open weights, text-to-image, editing, up to 4 references, 7 aspect ratios to 4 MP, 16 steps.
- 文本生成图像
- 图像生成图像
Undistilled 5.6B FLUX 3 Klein, 50 steps, CFG guidance, negative prompt, 4 refs, 7 ratios to 4 MP.
试用此模型FLUX 3 Image Klein Base
Black Forest Labs
Undistilled 5.6B FLUX 3 Klein, 50 steps, CFG guidance, negative prompt, 4 refs, 7 ratios to 4 MP.
- 文本生成图像
- 图像生成图像
T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p.
试用此模型
Grok Imagine 1.5 Video
xAI
T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound.
试用此模型Grok Imagine 1.5 Lite Video
xAI
Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound.
- 文本生成视频
- 图像生成视频
Add 2–10 seconds to any 2–15 second clip from its URL, 1.0 model, up to 720p.
试用此模型Grok Imagine 1.0 Video Extend
xAI
Add 2–10 seconds to any 2–15 second clip from its URL, 1.0 model, up to 720p.
- 视频生成视频
Prompt-driven edit of any clip by URL, 1.0 model, same length and ratio, up to 720p.
试用此模型Grok Imagine 1.0 Video Edit
xAI
Prompt-driven edit of any clip by URL, 1.0 model, same length and ratio, up to 720p.
- 视频生成视频
xAI TTS: preset voices, 20 languages, speed control, mp3, wav, or pcm.
试用此模型Grok Text to Speech
xAI
xAI TTS: preset voices, 20 languages, speed control, mp3, wav, or pcm.
- 文本转语音
xAI transcription: word timestamps, language detection, speaker diarization.
试用此模型Grok Speech to Text
xAI
xAI transcription: word timestamps, language detection, speaker diarization.
- 语音转文本
3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
试用此模型Kling 4.0
Kling
3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
试用此模型
Gemini 4 Argon
#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
- 文本转文本
Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
试用此模型
Vidu Q4
Vidu
Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
- 图像生成视频
- 参考生成视频
#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
试用此模型
Eleven v4
ElevenLabs
#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
- 文本转语音
#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
试用此模型Eleven v4 Turbo
ElevenLabs
#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
- 文本转语音
Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
试用此模型ElevenLabs
ElevenLabs
Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
- 文本转语音
- 音效
- 语音转文本
Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
试用此模型
SeeDance 2.0
ByteDance
Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
- 视频编辑
Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
试用此模型SeeDance 2.0 Mini
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
- 视频编辑
Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
试用此模型SeeDance 2.0 Fast
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
- 视频编辑
1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
试用此模型
Claude Haiku 5.5
Anthropic
1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
- 文本转文本
Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
试用此模型Nano Banana 2.1
Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
- 文本生成图像
- 图像生成图像
Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
试用此模型Gemini 3.8 Flash TTS
Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
- 文本转语音
The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
试用此模型Gemini 3.8 Flash Lite TTS
The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
- 文本转语音
Near-Astra coding and computer use at a fifth of Astra's price, 75.2% DeepSWE, 1M context, cached input at half GPT 6 Sol's rate.
试用此模型
GPT 6.1 Sol
OpenAI
Near-Astra coding and computer use at a fifth of Astra's price, 75.2% DeepSWE, 1M context, cached input at half GPT 6 Sol's rate.
- 文本转文本
1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
试用此模型Claude Sonnet 5.5
Anthropic
1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
- 文本转文本
1M context, image input, 56.4% Agents' Last Exam at 60% less per task than Opus 5, half the price of GPT 5.6 Sol.
试用此模型GPT 6 Sol
OpenAI
1M context, image input, 56.4% Agents' Last Exam at 60% less per task than Opus 5, half the price of GPT 5.6 Sol.
- 文本转文本
OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
试用此模型GPT 6 Luna
OpenAI
OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
- 文本转文本
1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
试用此模型
DeepSeek V4.1 Flash
DeepSeek
1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
- 文本转文本
1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
试用此模型DeepSeek V4 Pro
DeepSeek
1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
- 文本转文本
Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
试用此模型DeepSeek V4 Flash
DeepSeek
Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
- 文本转文本
500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
试用此模型Grok 4.7
xAI
500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
- 文本转文本
Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
试用此模型GPT Image 2.5
OpenAI
Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
- 文本生成图像
- 图像生成图像
1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
试用此模型GPT 6 Astra
OpenAI
1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
- 文本转文本
1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
试用此模型Gemini 3.5 Flash
1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
- 文本转文本
1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
试用此模型Gemini 3.8 Flash
1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
- 文本转文本
1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
试用此模型Claude Fable 5.1
Anthropic
1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
- 文本转文本
500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
试用此模型Grok 4.5
xAI
500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
- 文本转文本
1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
试用此模型Grok 4.3
xAI
1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
- 文本转文本
256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
试用此模型Grok Build 0.1
xAI
256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
- 文本转文本
1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
试用此模型Grok 4.20 Reasoning
xAI
1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
- 文本转文本
1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
试用此模型Grok 4.20 Non-Reasoning
xAI
1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
- 文本转文本
Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
试用此模型Grok 4.20 Multi-Agent
xAI
Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
- 文本转文本
Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
试用此模型Gemini Omni Flash 1.1
Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频编辑
Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
试用此模型
Wan 3.0 Prime
Alibaba
Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
试用此模型Gemini 3.1 Flash TTS
Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
- 文本转语音
High-quality narration with 30 voices, dialogue mode, and 70+ languages.
试用此模型Gemini 2.5 Pro TTS
High-quality narration with 30 voices, dialogue mode, and 70+ languages.
- 文本转语音
Fastest, lowest cost per second, with 30 voices and dialogue mode.
试用此模型Gemini 2.5 Flash TTS
Fastest, lowest cost per second, with 30 voices and dialogue mode.
- 文本转语音
2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
试用此模型Wan 3.0
Alibaba
2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
- 文本生成视频
- 图像生成视频
- 参考生成视频
500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
试用此模型Grok 4.6
xAI
500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
- 文本转文本
1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
试用此模型Gemini 3.7 Flash
1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
- 文本转文本
Quality-focused xAI text-to-image and reference editing with up to 5 input images.
试用此模型Grok Imagine 2.0 Image
xAI
Quality-focused xAI text-to-image and reference editing with up to 5 input images.
- 文本生成图像
- 图像生成图像
1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
试用此模型Gemini 3.6 Flash
1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
- 文本转文本
4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
试用此模型SeeDance 2.5
ByteDance
4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
- 视频编辑
2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
试用此模型
MiniMax Hailuo H3
MiniMax
2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
- 文本生成视频
- 图像生成视频
- 参考生成视频
1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
试用此模型Claude Opus 5
Anthropic
1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
- 文本转文本
2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
试用此模型
Kimi K3
Moonshot AI
2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
- 文本转文本
1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
试用此模型GPT 5.6 Sol
OpenAI
1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
- 文本转文本
1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
试用此模型GPT 5.6 Terra
OpenAI
1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
- 文本转文本
Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
试用此模型GPT 5.6 Luna
OpenAI
Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
- 文本转文本
Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
试用此模型SeeDream 5.0 Pro
ByteDance
Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
- 文本生成图像
- 图像生成图像
1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
试用此模型Claude Fable 5
Anthropic
1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
- 文本转文本
200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
试用此模型Claude Sonnet 4.5
Anthropic
200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
- 文本转文本
200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
试用此模型Claude Opus 4.5
Anthropic
200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
- 文本转文本
200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
试用此模型Claude Haiku 4.5
Anthropic
200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
- 文本转文本
Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
试用此模型Claude Sonnet 5
Anthropic
Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
- 文本转文本
Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
试用此模型Nano Banana 2 Lite
Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
- 文本生成图像
- 图像生成图像
Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
试用此模型
HappyHorse 1.1
Alibaba
Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
- 文本生成视频
- 图像生成视频
- 参考生成视频
T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
试用此模型Kling 3.0 Turbo
Kling
T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
- 文本生成视频
- 图像生成视频
1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
试用此模型Claude Opus 4.8
Anthropic
1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
- 文本转文本
Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
试用此模型
Composer 2.5
Cursor
Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
- 文本转文本
Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
试用此模型Composer 2.5 Fast
Cursor
Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
- 文本转文本
T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
试用此模型HappyHorse 1.0
Alibaba
T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
- 文本生成视频
- 图像生成视频
- 参考生成视频
1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
试用此模型GPT 5.5
OpenAI
1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
- 文本转文本
T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
试用此模型GPT Image 2
OpenAI
T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
- 文本生成图像
- 图像生成图像
1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
试用此模型Claude Opus 4.7
Anthropic
1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
- 文本转文本
T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
试用此模型Wan 2.7 Image
Alibaba
T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
- 文本生成图像
- 图像生成图像
T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
试用此模型Wan 2.7 Image Pro
Alibaba
T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
- 文本生成图像
- 图像生成图像
T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
试用此模型Wan 2.7
Alibaba
T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
试用此模型Wan 2.7 Video Edit
Alibaba
Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
- 视频编辑
400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
试用此模型GPT 5.4 Mini
OpenAI
400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
- 文本转文本
400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
试用此模型GPT 5.4 Nano
OpenAI
400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
- 文本转文本
Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
试用此模型GPT 5.4
OpenAI
Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
- 文本转文本
1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
试用此模型Claude Sonnet 4.6
Anthropic
1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
- 文本转文本
Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
试用此模型HappyHorse 1.0 Video Edit
Alibaba
Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
- 视频编辑
1M context, 128k output, effort controls, top Arena Document and Search rank.
试用此模型Claude Opus 4.6
Anthropic
1M context, 128k output, effort controls, top Arena Document and Search rank.
- 文本转文本
Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
试用此模型Kling 3.0
Kling
Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
试用此模型Kling 3.0 Motion Control
Kling
Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
- 图像生成视频
- 参考生成视频
- 视频生成视频
T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
试用此模型Kling 3.0 Omni Image
Kling
T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
- 文本生成图像
- 图像生成图像
Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
试用此模型Kling 3.0 Omni
Kling
Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
Edit videos with reference (style guide) or transform mode, plus image and video elements.
试用此模型Kling 3.0 Omni 编辑
Kling
Edit videos with reference (style guide) or transform mode, plus image and video elements.
- 视频编辑
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
试用此模型SeeDream 5.0 Lite
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- 文本生成图像
- 图像生成图像
T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
试用此模型Z-Image Turbo
Alibaba
T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
- 文本生成图像
T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
试用此模型Wan 2.6
Alibaba
T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
试用此模型Wan 2.6 Flash
Alibaba
Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
- 文本生成视频
- 图像生成视频
- 参考生成视频
T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
试用此模型Wan 2.6 Image
Alibaba
T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
- 文本生成图像
- 图像生成图像
Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
试用此模型Kling 2.6 动作控制
Kling
Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
- 图像生成视频
- 参考生成视频
- 视频生成视频
T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
试用此模型Kling 2.6
Kling
T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
- 文本生成视频
- 图像生成视频
Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
试用此模型Flux.2 Pro
Black Forest Labs
Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- 文本生成图像
- 图像生成图像
9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
试用此模型Flux.2 Klein 9B
Black Forest Labs
9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
- 文本生成图像
- 图像生成图像
4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
试用此模型Flux.2 Klein 4B
Black Forest Labs
4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
- 文本生成图像
- 图像生成图像
T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
试用此模型
Qwen Image 2.0
Alibaba
T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
- 文本生成图像
- 图像生成图像
Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
试用此模型Qwen Image 2.0 Pro
Alibaba
Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
- 文本生成图像
- 图像生成图像
Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
试用此模型Kling O1
Kling
Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
试用此模型Kling O1 Image
Kling
Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
- 文本生成图像
- 图像生成图像
Reasoning video editing with reference or transform mode, up to 4 reference images.
试用此模型Kling O1 编辑
Kling
Reasoning video editing with reference or transform mode, up to 4 reference images.
- 视频编辑
Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
试用此模型Nano Banana Pro
Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
- 文本生成图像
- 图像生成图像
T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
试用此模型Kling 2.5 Turbo
Kling
T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
- 文本生成视频
- 图像生成视频
Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
试用此模型MiniMax Hailuo 2.3
MiniMax
Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
- 图像生成视频
Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
试用此模型MiniMax Hailuo 2.3 Fast
MiniMax
Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
- 图像生成视频
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
试用此模型SeeDream 4.5
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- 文本生成图像
- 图像生成图像
4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
试用此模型Veo 3.1
4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
- 文本生成视频
- 图像生成视频
- 参考生成视频
- 视频生成视频
Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
试用此模型Nano Banana 2
Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
- 文本生成图像
- 图像生成图像
T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
试用此模型Wan 2.5 Image
Alibaba
T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
- 文本生成图像
- 图像生成图像
T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
试用此模型Wan 2.5
Alibaba
T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
- 文本生成视频
- 图像生成视频
T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
试用此模型Qwen Image
Alibaba
T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
- 文本生成图像
- 图像生成图像
Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
试用此模型Qwen Image Max
Alibaba
Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
- 文本生成图像
- 图像生成图像
Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
试用此模型Qwen Image Plus
Alibaba
Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
- 文本生成图像
- 图像生成图像
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
试用此模型SeeDream 4.0
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- 文本生成图像
- 图像生成图像
T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
试用此模型SeeDance 1.5 Pro
ByteDance
T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
- 文本生成视频
- 图像生成视频
Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
试用此模型MiniMax Hailuo 2.0
MiniMax
Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
- 图像生成视频
Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
试用此模型Wan 2.2 Image
Alibaba
Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
- 文本生成图像
Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
试用此模型Wan 2.2 Image Flash
Alibaba
Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
- 文本生成图像
Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
试用此模型Wan 2.2
Alibaba
Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
- 文本生成视频
- 图像生成视频
Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
试用此模型Wan 2.2 Fast
Alibaba
Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
- 文本生成视频
- 图像生成视频
Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
试用此模型Nano Banana
Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
- 文本生成图像
- 图像生成图像
Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
试用此模型
Topaz Video Upscale
Topaz Labs
Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
- 视频生成视频
AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
试用此模型Topaz Image Upscale
Topaz Labs
AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
- 图像生成图像
T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
试用此模型Kling 2.1 Master
Kling
T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
- 文本生成视频
- 图像生成视频
Extend a finished Fast video by 6 or 10 seconds, preset or custom mode.
试用此模型Grok Imagine 1.5 Fast Video Extend
xAI
Extend a finished Fast video by 6 or 10 seconds, preset or custom mode.
- 视频生成视频
Upscale a finished Grok Imagine video to HD from its task ID.
试用此模型Grok Imagine Upscale
xAI
Upscale a finished Grok Imagine video to HD from its task ID.
- 视频生成视频
I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
试用此模型Kling 2.1
Kling
I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
- 图像生成视频
First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
试用此模型SeeDance 1.0 Pro
ByteDance
First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
- 图像生成视频
Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
试用此模型SeeDance 1.0 Pro Fast
ByteDance
Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
- 文本生成视频
- 图像生成视频
Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
试用此模型Flux.2 Flex
Black Forest Labs
Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
- 文本生成图像
- 图像生成图像
Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
试用此模型Flux.2 Max
Black Forest Labs
Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- 文本生成图像
- 图像生成图像
T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
试用此模型Grok Imagine 1.5 Fast Video
xAI
T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
- 文本生成视频
- 图像生成视频
- 参考生成视频
Fast xAI text-to-image and reference editing with up to 5 images.
试用此模型Grok Imagine 1.0 Image
xAI
Fast xAI text-to-image and reference editing with up to 5 images.
- 文本生成图像
- 图像生成图像
Browse model families
按任务分类的 API
All models A–Z
Every model and variant on the platform, including the specialised routes that sit inside a family page.