KI-Modellverzeichnis — Video-, Bild- und Audiogenerierung
Entdecken und testen Sie 131 Modelle von 16 Anbietern. Öffnen Sie eine Karte, um das Modell im Playground zu testen.
Preise pro Variante für jedes Untermodell finden Sie auf der Preisseite.
Typ(5)
Anbieter(16)
Fähigkeiten(12)
Coming soon: the fast Kling 4.0 model. 3-20s at 720p, text-to-video, image-to-video, Omni Reference.
Details ansehen
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.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
Details ansehen
FLUX 3 Video
Black Forest Labs
Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
- Text zu Video
- Bild zu Video
- Video zu Video
Bounding-box layouts and edits, up to 10 references, 15 aspect ratios plus auto, 768sq to 4K.
Dieses Modell ausprobierenFLUX 3 Image
Black Forest Labs
Bounding-box layouts and edits, up to 10 references, 15 aspect ratios plus auto, 768sq to 4K.
- Text zu Bild
- Bild zu Bild
5.6B open weights, text-to-image, editing, up to 4 references, 7 aspect ratios to 4 MP, 16 steps.
Dieses Modell ausprobierenFLUX 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.
- Text zu Bild
- Bild zu Bild
Undistilled 5.6B FLUX 3 Klein, 50 steps, CFG guidance, negative prompt, 4 refs, 7 ratios to 4 MP.
Dieses Modell ausprobierenFLUX 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.
- Text zu Bild
- Bild zu Bild
T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p.
Dieses Modell ausprobieren
Grok Imagine 1.5 Video
xAI
T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound.
Dieses Modell ausprobierenGrok Imagine 1.5 Lite Video
xAI
Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound.
- Text zu Video
- Bild zu Video
Add 2–10 seconds to any 2–15 second clip from its URL, 1.0 model, up to 720p.
Dieses Modell ausprobierenGrok 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.
- Video zu Video
Prompt-driven edit of any clip by URL, 1.0 model, same length and ratio, up to 720p.
Dieses Modell ausprobierenGrok Imagine 1.0 Video Edit
xAI
Prompt-driven edit of any clip by URL, 1.0 model, same length and ratio, up to 720p.
- Video zu Video
xAI TTS: preset voices, 20 languages, speed control, mp3, wav, or pcm.
Dieses Modell ausprobierenGrok Text to Speech
xAI
xAI TTS: preset voices, 20 languages, speed control, mp3, wav, or pcm.
- Text zu Sprache
xAI transcription: word timestamps, language detection, speaker diarization.
Dieses Modell ausprobierenGrok Speech to Text
xAI
xAI transcription: word timestamps, language detection, speaker diarization.
- Sprache zu Text
3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
Dieses Modell ausprobierenKling 4.0
Kling
3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
Dieses Modell ausprobieren
Gemini 4 Argon
#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
- Text zu Text
Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
Dieses Modell ausprobieren
Vidu Q4
Vidu
Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
- Bild zu Video
- Referenz zu Video
#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
Dieses Modell ausprobieren
Eleven v4
ElevenLabs
#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
- Text zu Sprache
#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
Dieses Modell ausprobierenEleven v4 Turbo
ElevenLabs
#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
- Text zu Sprache
Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
Dieses Modell ausprobierenElevenLabs
ElevenLabs
Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
- Text zu Sprache
- Soundeffekte
- Sprache zu Text
Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
Dieses Modell ausprobieren
SeeDance 2.0
ByteDance
Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
- Video bearbeiten
Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
Dieses Modell ausprobierenSeeDance 2.0 Mini
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
- Video bearbeiten
Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
Dieses Modell ausprobierenSeeDance 2.0 Fast
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
- Video bearbeiten
Generate music, extend songs, add vocals, isolate stems, and write lyrics.
Dieses Modell ausprobieren
Suno
Suno
Generate music, extend songs, add vocals, isolate stems, and write lyrics.
- Musik
- Soundeffekte
1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
Dieses Modell ausprobieren
Claude Haiku 5.5
Anthropic
1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
- Text zu Text
Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
Dieses Modell ausprobierenNano Banana 2.1
Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
- Text zu Bild
- Bild zu Bild
Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
Dieses Modell ausprobierenGemini 3.8 Flash TTS
Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
- Text zu Sprache
The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
Dieses Modell ausprobierenGemini 3.8 Flash Lite TTS
The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
- Text zu Sprache
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.
Dieses Modell ausprobieren
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.
- Text zu Text
1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
Dieses Modell ausprobierenClaude Sonnet 5.5
Anthropic
1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
- Text zu Text
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.
Dieses Modell ausprobierenGPT 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.
- Text zu Text
OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
Dieses Modell ausprobierenGPT 6 Luna
OpenAI
OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
- Text zu Text
1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
Dieses Modell ausprobieren
DeepSeek V4.1 Flash
DeepSeek
1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
- Text zu Text
1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
Dieses Modell ausprobierenDeepSeek V4 Pro
DeepSeek
1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
- Text zu Text
Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
Dieses Modell ausprobierenDeepSeek V4 Flash
DeepSeek
Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
- Text zu Text
1M context, 128k output, 66.4% Terminal-Bench 4.0.
Dieses Modell ausprobierenClaude Opus 5.5
Anthropic
1M context, 128k output, 66.4% Terminal-Bench 4.0.
- Text zu Text
500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
Dieses Modell ausprobierenGrok 4.7
xAI
500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
- Text zu Text
Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
Dieses Modell ausprobierenGPT Image 2.5
OpenAI
Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
- Text zu Bild
- Bild zu Bild
1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
Dieses Modell ausprobierenGPT 6 Astra
OpenAI
1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
- Text zu Text
1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
Dieses Modell ausprobierenGemini 3.5 Flash
1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
- Text zu Text
1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
Dieses Modell ausprobierenGemini 3.8 Flash
1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
- Text zu Text
1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
Dieses Modell ausprobierenClaude Fable 5.1
Anthropic
1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
- Text zu Text
500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
Dieses Modell ausprobierenGrok 4.5
xAI
500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
- Text zu Text
1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
Dieses Modell ausprobierenGrok 4.3
xAI
1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
- Text zu Text
256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
Dieses Modell ausprobierenGrok Build 0.1
xAI
256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
- Text zu Text
1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
Dieses Modell ausprobierenGrok 4.20 Reasoning
xAI
1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
- Text zu Text
1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
Dieses Modell ausprobierenGrok 4.20 Non-Reasoning
xAI
1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
- Text zu Text
Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
Dieses Modell ausprobierenGrok 4.20 Multi-Agent
xAI
Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
- Text zu Text
Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
Dieses Modell ausprobierenGemini Omni Flash 1.1
Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video bearbeiten
Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
Dieses Modell ausprobieren
Wan 3.0 Prime
Alibaba
Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
Dieses Modell ausprobierenGemini 3.1 Flash TTS
Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
- Text zu Sprache
High-quality narration with 30 voices, dialogue mode, and 70+ languages.
Dieses Modell ausprobierenGemini 2.5 Pro TTS
High-quality narration with 30 voices, dialogue mode, and 70+ languages.
- Text zu Sprache
Fastest, lowest cost per second, with 30 voices and dialogue mode.
Dieses Modell ausprobierenGemini 2.5 Flash TTS
Fastest, lowest cost per second, with 30 voices and dialogue mode.
- Text zu Sprache
2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
Dieses Modell ausprobierenWan 3.0
Alibaba
2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
- Text zu Video
- Bild zu Video
- Referenz zu Video
500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
Dieses Modell ausprobierenGrok 4.6
xAI
500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
- Text zu Text
1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
Dieses Modell ausprobierenGemini 3.7 Flash
1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
- Text zu Text
Quality-focused xAI text-to-image and reference editing with up to 5 input images.
Dieses Modell ausprobierenGrok Imagine 2.0 Image
xAI
Quality-focused xAI text-to-image and reference editing with up to 5 input images.
- Text zu Bild
- Bild zu Bild
1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
Dieses Modell ausprobierenGemini 3.6 Flash
1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
- Text zu Text
4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
Dieses Modell ausprobierenSeeDance 2.5
ByteDance
4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
- Video bearbeiten
2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
Dieses Modell ausprobieren
MiniMax Hailuo H3
MiniMax
2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
- Text zu Video
- Bild zu Video
- Referenz zu Video
1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
Dieses Modell ausprobierenClaude Opus 5
Anthropic
1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
- Text zu Text
2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
Dieses Modell ausprobieren
Kimi K3
Moonshot AI
2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
- Text zu Text
1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
Dieses Modell ausprobierenGPT 5.6 Sol
OpenAI
1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
- Text zu Text
1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
Dieses Modell ausprobierenGPT 5.6 Terra
OpenAI
1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
- Text zu Text
Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
Dieses Modell ausprobierenGPT 5.6 Luna
OpenAI
Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
- Text zu Text
Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
Dieses Modell ausprobierenSeeDream 5.0 Pro
ByteDance
Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
- Text zu Bild
- Bild zu Bild
1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
Dieses Modell ausprobierenClaude Fable 5
Anthropic
1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
- Text zu Text
200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
Dieses Modell ausprobierenClaude Sonnet 4.5
Anthropic
200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
- Text zu Text
200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
Dieses Modell ausprobierenClaude Opus 4.5
Anthropic
200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
- Text zu Text
200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
Dieses Modell ausprobierenClaude Haiku 4.5
Anthropic
200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
- Text zu Text
Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
Dieses Modell ausprobierenClaude Sonnet 5
Anthropic
Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
- Text zu Text
Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
Dieses Modell ausprobierenNano Banana 2 Lite
Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
- Text zu Bild
- Bild zu Bild
Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
Dieses Modell ausprobieren
HappyHorse 1.1
Alibaba
Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
- Text zu Video
- Bild zu Video
- Referenz zu Video
T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
Dieses Modell ausprobierenKling 3.0 Turbo
Kling
T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
- Text zu Video
- Bild zu Video
1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
Dieses Modell ausprobierenClaude Opus 4.8
Anthropic
1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
- Text zu Text
Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
Dieses Modell ausprobieren
Composer 2.5
Cursor
Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
- Text zu Text
Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
Dieses Modell ausprobierenComposer 2.5 Fast
Cursor
Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
- Text zu Text
T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
Dieses Modell ausprobierenHappyHorse 1.0
Alibaba
T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
- Text zu Video
- Bild zu Video
- Referenz zu Video
1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
Dieses Modell ausprobierenGPT 5.5
OpenAI
1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
- Text zu Text
T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
Dieses Modell ausprobierenGPT Image 2
OpenAI
T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
- Text zu Bild
- Bild zu Bild
1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
Dieses Modell ausprobierenClaude Opus 4.7
Anthropic
1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
- Text zu Text
T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
Dieses Modell ausprobierenWan 2.7 Image
Alibaba
T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
- Text zu Bild
- Bild zu Bild
T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
Dieses Modell ausprobierenWan 2.7 Image Pro
Alibaba
T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
- Text zu Bild
- Bild zu Bild
T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
Dieses Modell ausprobierenWan 2.7
Alibaba
T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
Dieses Modell ausprobierenWan 2.7 Video Edit
Alibaba
Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
- Video bearbeiten
400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
Dieses Modell ausprobierenGPT 5.4 Mini
OpenAI
400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
- Text zu Text
400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
Dieses Modell ausprobierenGPT 5.4 Nano
OpenAI
400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
- Text zu Text
Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
Dieses Modell ausprobierenGPT 5.4
OpenAI
Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
- Text zu Text
1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
Dieses Modell ausprobierenClaude Sonnet 4.6
Anthropic
1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
- Text zu Text
Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
Dieses Modell ausprobierenHappyHorse 1.0 Video Edit
Alibaba
Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
- Video bearbeiten
1M context, 128k output, effort controls, top Arena Document and Search rank.
Dieses Modell ausprobierenClaude Opus 4.6
Anthropic
1M context, 128k output, effort controls, top Arena Document and Search rank.
- Text zu Text
Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
Dieses Modell ausprobierenKling 3.0
Kling
Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
Dieses Modell ausprobierenKling 3.0 Motion Control
Kling
Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
- Bild zu Video
- Referenz zu Video
- Video zu Video
T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
Dieses Modell ausprobierenKling 3.0 Omni Image
Kling
T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
- Text zu Bild
- Bild zu Bild
Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
Dieses Modell ausprobierenKling 3.0 Omni
Kling
Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
Edit videos with reference (style guide) or transform mode, plus image and video elements.
Dieses Modell ausprobierenKling 3.0 Omni Edit
Kling
Edit videos with reference (style guide) or transform mode, plus image and video elements.
- Video bearbeiten
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Dieses Modell ausprobierenSeeDream 5.0 Lite
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Text zu Bild
- Bild zu Bild
T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
Dieses Modell ausprobierenZ-Image Turbo
Alibaba
T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
- Text zu Bild
T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
Dieses Modell ausprobierenWan 2.6
Alibaba
T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
Dieses Modell ausprobierenWan 2.6 Flash
Alibaba
Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
- Text zu Video
- Bild zu Video
- Referenz zu Video
T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
Dieses Modell ausprobierenWan 2.6 Image
Alibaba
T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
- Text zu Bild
- Bild zu Bild
Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
Dieses Modell ausprobierenKling 2.6 Bewegungssteuerung
Kling
Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
- Bild zu Video
- Referenz zu Video
- Video zu Video
T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
Dieses Modell ausprobierenKling 2.6
Kling
T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
- Text zu Video
- Bild zu Video
Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
Dieses Modell ausprobierenFlux.2 Pro
Black Forest Labs
Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- Text zu Bild
- Bild zu Bild
9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
Dieses Modell ausprobierenFlux.2 Klein 9B
Black Forest Labs
9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
- Text zu Bild
- Bild zu Bild
4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
Dieses Modell ausprobierenFlux.2 Klein 4B
Black Forest Labs
4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
- Text zu Bild
- Bild zu Bild
T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
Dieses Modell ausprobieren
Qwen Image 2.0
Alibaba
T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
- Text zu Bild
- Bild zu Bild
Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
Dieses Modell ausprobierenQwen Image 2.0 Pro
Alibaba
Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
- Text zu Bild
- Bild zu Bild
Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
Dieses Modell ausprobierenKling O1
Kling
Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
Dieses Modell ausprobierenKling O1 Image
Kling
Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
- Text zu Bild
- Bild zu Bild
Reasoning video editing with reference or transform mode, up to 4 reference images.
Dieses Modell ausprobierenKling O1 Edit
Kling
Reasoning video editing with reference or transform mode, up to 4 reference images.
- Video bearbeiten
Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
Dieses Modell ausprobierenNano Banana Pro
Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
- Text zu Bild
- Bild zu Bild
T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
Dieses Modell ausprobierenKling 2.5 Turbo
Kling
T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
- Text zu Video
- Bild zu Video
Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
Dieses Modell ausprobierenMiniMax Hailuo 2.3
MiniMax
Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
- Bild zu Video
Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
Dieses Modell ausprobierenMiniMax Hailuo 2.3 Fast
MiniMax
Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
- Bild zu Video
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Dieses Modell ausprobierenSeeDream 4.5
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Text zu Bild
- Bild zu Bild
4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
Dieses Modell ausprobierenVeo 3.1
4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
- Text zu Video
- Bild zu Video
- Referenz zu Video
- Video zu Video
Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
Dieses Modell ausprobierenNano Banana 2
Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
- Text zu Bild
- Bild zu Bild
T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
Dieses Modell ausprobierenWan 2.5 Image
Alibaba
T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
- Text zu Bild
- Bild zu Bild
T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
Dieses Modell ausprobierenWan 2.5
Alibaba
T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
- Text zu Video
- Bild zu Video
T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
Dieses Modell ausprobierenQwen Image
Alibaba
T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
- Text zu Bild
- Bild zu Bild
Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
Dieses Modell ausprobierenQwen Image Max
Alibaba
Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
- Text zu Bild
- Bild zu Bild
Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
Dieses Modell ausprobierenQwen Image Plus
Alibaba
Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
- Text zu Bild
- Bild zu Bild
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Dieses Modell ausprobierenSeeDream 4.0
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Text zu Bild
- Bild zu Bild
T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
Dieses Modell ausprobierenSeeDance 1.5 Pro
ByteDance
T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
- Text zu Video
- Bild zu Video
Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
Dieses Modell ausprobierenMiniMax Hailuo 2.0
MiniMax
Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
- Bild zu Video
Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
Dieses Modell ausprobierenWan 2.2 Image
Alibaba
Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
- Text zu Bild
Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
Dieses Modell ausprobierenWan 2.2 Image Flash
Alibaba
Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
- Text zu Bild
Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
Dieses Modell ausprobierenWan 2.2
Alibaba
Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
- Text zu Video
- Bild zu Video
Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
Dieses Modell ausprobierenWan 2.2 Fast
Alibaba
Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
- Text zu Video
- Bild zu Video
Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
Dieses Modell ausprobierenNano Banana
Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
- Text zu Bild
- Bild zu Bild
Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
Dieses Modell ausprobieren
Topaz Video Upscale
Topaz Labs
Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
- Video zu Video
AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
Dieses Modell ausprobierenTopaz Image Upscale
Topaz Labs
AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
- Bild zu Bild
T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
Dieses Modell ausprobierenKling 2.1 Master
Kling
T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
- Text zu Video
- Bild zu Video
Extend a finished Fast video by 6 or 10 seconds, preset or custom mode.
Dieses Modell ausprobierenGrok Imagine 1.5 Fast Video Extend
xAI
Extend a finished Fast video by 6 or 10 seconds, preset or custom mode.
- Video zu Video
Upscale a finished Grok Imagine video to HD from its task ID.
Dieses Modell ausprobierenGrok Imagine Upscale
xAI
Upscale a finished Grok Imagine video to HD from its task ID.
- Video zu Video
I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
Dieses Modell ausprobierenKling 2.1
Kling
I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
- Bild zu Video
T2V or I2V at 480p/720p, 5 or 10 second clips.
Dieses Modell ausprobierenSeeDance 1.0
ByteDance
T2V or I2V at 480p/720p, 5 or 10 second clips.
- Text zu Video
- Bild zu Video
First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
Dieses Modell ausprobierenSeeDance 1.0 Pro
ByteDance
First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
- Bild zu Video
Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
Dieses Modell ausprobierenSeeDance 1.0 Pro Fast
ByteDance
Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
- Text zu Video
- Bild zu Video
Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
Dieses Modell ausprobierenFlux.2 Flex
Black Forest Labs
Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
- Text zu Bild
- Bild zu Bild
Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
Dieses Modell ausprobierenFlux.2 Max
Black Forest Labs
Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- Text zu Bild
- Bild zu Bild
T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
Dieses Modell ausprobierenGrok Imagine 1.5 Fast Video
xAI
T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
- Text zu Video
- Bild zu Video
- Referenz zu Video
Fast xAI text-to-image and reference editing with up to 5 images.
Dieses Modell ausprobierenGrok Imagine 1.0 Image
xAI
Fast xAI text-to-image and reference editing with up to 5 images.
- Text zu Bild
- Bild zu Bild
Browse model families
APIs nach Aufgabe
All models A–Z
Every model and variant on the platform, including the specialised routes that sit inside a family page.