AI Model APIs — Video, Image & Audio Generation

Browse and try 115 models from 16 providers. Open any card to try that model in the playground.

Per-variant pricing for every sub-model is on the pricing page.

Type(5)

Provider(16)

Capabilities(12)

Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.

View details

FLUX 3 Video

Black Forest Labs

Text to Video
Image to Video
Video to Video

Flare for speed, Sunburst for detail: 1K/2K/4K, 15 aspect ratios, 16 reference images.

Try this model

GPT Image 2.6

OpenAI

Text to Image
Image to Image

GPT Image 2.6 pricing

Any length from 3 to 15s, character references with voice presets, and video editing up to 15s.

Try this model

Gemini Omni Flash 1.2

Google

Text to Video
Image to Video
Reference to Video
Video Edit

Gemini Omni Flash 1.2 pricing

The faster H3: 768p, 4-15s, start/end frames, up to 9 reference images and 3 reference videos, native audio.

Try this model

MiniMax H3 Highspeed

MiniMax

Text to Video
Image to Video
Reference to Video

MiniMax H3 Highspeed pricing

The fast Kling 4.0 model. 3-20s at 720p with stereo audio, from text, a start frame, or up to 10 reference images.

Try this model

Kling 4.0 Flash

Kling

Text to Video
Image to Video
Reference to Video
Video to Video

Kling 4.0 Flash pricing

H3 inputs at about half the price: 480p or 768p, 4-15s, start/end frames, up to 9 reference images and 3 reference videos.

Try this model

MiniMax H3 Lite

MiniMax

Text to Video
Image to Video
Reference to Video

MiniMax H3 Lite pricing

About 30 s a job: 480p or 768p, 4-15s, start/end frames, up to 9 reference images with no per-image charge, 3 reference videos and 3 audio clips.

Try this model

MiniMax H3 Fast

MiniMax

Text to Video
Image to Video
Reference to Video

MiniMax H3 Fast pricing

480p or 768p, 5-15s, start/end frames, up to 9 reference images, 3 reference videos and 3 audio clips, seed and prompt expansion.

Try this model

MiniMax H3 Max

MiniMax

Text to Video
Image to Video
Reference to Video

MiniMax H3 Max pricing

Distilled H3 Max: text or start/end frames only, 480p or 768p, 5-15s, six aspect ratios, seed and prompt expansion.

Try this model

MiniMax H3 Max Turbo

MiniMax

Text to Video
Image to Video

MiniMax H3 Max Turbo pricing

Astra-level computer use at a tenth of Astra's token price, 60.0% Agents' Last Exam, 74.2% OSWorld 2.1, 1M context.

Try this model

GPT 6.1 Terra

OpenAI

Text to Text

GPT 6.1 Terra pricing

Generate music, extend songs, add vocals, isolate stems, and write lyrics.

Try this model

Suno

Music
Sound Effects

Suno pricing

65.7% Terminal-Bench 4.0, 55 on the Intelligence Index, 2.8T MoE, 1M context, 131k default output. Highspeed serving 2-3x faster.

Try this model

Kimi K3.1 Pro

Moonshot AI

Text to Text

Kimi K3.1 Pro pricing

Bounding-box layouts and edits, up to 10 references, 15 aspect ratios plus auto, 768sq to 4K.

Try this model

FLUX 3 Image

Black Forest Labs

Text to Image
Image to Image

FLUX 3 Image pricing

5.6B open weights, text-to-image, editing, up to 4 references, 7 aspect ratios to 4 MP, 16 steps.

Try this model

FLUX 3 Image Klein

Black Forest Labs

Text to Image
Image to Image

FLUX 3 Image Klein pricing

Undistilled 5.6B FLUX 3 Klein, 50 steps, CFG guidance, negative prompt, 4 refs, 7 ratios to 4 MP.

Try this model

FLUX 3 Image Klein Base

Black Forest Labs

Text to Image
Image to Image

FLUX 3 Image Klein Base pricing

T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p.

Try this model

Grok Imagine 1.5 Video

xAI

Text to Video
Image to Video
Reference to Video

Grok Imagine 1.5 Video pricing

Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound.

Try this model

Grok Imagine 1.5 Lite Video

xAI

Text to Video
Image to Video

Grok Imagine 1.5 Lite Video pricing

Add 2–10 seconds to any 2–15 second clip from its URL, 1.0 model, up to 720p.

Try this model

Grok Imagine 1.0 Video Extend

xAI

Video to Video

Grok Imagine 1.0 Video Extend pricing

Prompt-driven edit of any clip by URL, 1.0 model, same length and ratio, up to 720p.

Try this model

Grok Imagine 1.0 Video Edit

xAI

Video to Video

Grok Imagine 1.0 Video Edit pricing

xAI TTS: preset voices, 20 languages, speed control, mp3, wav, or pcm.

Try this model

Grok Text to Speech

xAI

Text to Speech

Grok Text to Speech pricing

xAI transcription: word timestamps, language detection, speaker diarization.

Try this model

Grok Speech to Text

xAI

Speech to Text

Grok Speech to Text pricing

3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot.

Try this model

Kling 4.0

Kling

Text to Video
Image to Video
Reference to Video
Video to Video

Kling 4.0 pricing

#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.

Try this model

Gemini 4 Argon

Google

Text to Text

Gemini 4 Argon pricing

Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.

Try this model

Vidu Q4

Vidu

Image to Video
Reference to Video

Vidu Q4 pricing

#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.

Try this model

Eleven v4

ElevenLabs

Text to Speech

#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.

Try this model

Eleven v4 Turbo

ElevenLabs

Text to Speech

Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.

Try this model

ElevenLabs

Text to Speech
Sound Effects
Speech to Text

ElevenLabs pricing

Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.

Try this model

SeeDance 2.0

ByteDance

Text to Video
Image to Video
Reference to Video
Video to Video
Video Edit

SeeDance 2.0 pricing

Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.

Try this model

SeeDance 2.0 Mini

ByteDance

Text to Video
Image to Video
Reference to Video
Video to Video
Video Edit

SeeDance 2.0 Mini pricing

Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.

Try this model

SeeDance 2.0 Fast

ByteDance

Text to Video
Image to Video
Reference to Video
Video to Video
Video Edit

SeeDance 2.0 Fast pricing

1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.

Try this model

Claude Haiku 5.5

Anthropic

Text to Text

Claude Haiku 5.5 pricing

Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.

Try this model

Nano Banana 2.1

Google

Text to Image
Image to Image

Nano Banana 2.1 pricing

Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.

Try this model

Gemini 3.8 Flash TTS

Google

Text to Speech

Gemini 3.8 Flash TTS pricing

The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.

Try this model

Gemini 3.8 Flash Lite TTS

Google

Text to Speech

Gemini 3.8 Flash Lite TTS pricing

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.

Try this model

GPT 6.1 Sol

OpenAI

Text to Text

GPT 6.1 Sol pricing

1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.

Try this model

Claude Sonnet 5.5

Anthropic

Text to Text

Claude Sonnet 5.5 pricing

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.

Try this model

GPT 6 Sol

OpenAI

Text to Text

GPT 6 Sol pricing

OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.

View details

GPT 6 Luna

OpenAI

Text to Text

1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.

Try this model

DeepSeek V4.1 Flash

DeepSeek

Text to Text

DeepSeek V4.1 Flash pricing

1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.

Try this model

DeepSeek V4 Pro

DeepSeek

Text to Text

DeepSeek V4 Pro pricing

Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.

Try this model

DeepSeek V4 Flash

DeepSeek

Text to Text

DeepSeek V4 Flash pricing

1M context, 128k output, 66.4% Terminal-Bench 4.0.

Try this model

Claude Opus 5.5

Anthropic

Text to Text

Claude Opus 5.5 pricing

500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.

Try this model

Grok 4.7

xAI

Text to Text

Grok 4.7 pricing

Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.

Try this model

GPT Image 2.5

OpenAI

Text to Image
Image to Image

GPT Image 2.5 pricing

1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.

Try this model

GPT 6 Astra

OpenAI

Text to Text

GPT 6 Astra pricing

1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.

Try this model

Gemini 3.5 Flash

Google

Text to Text

Gemini 3.5 Flash pricing

1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.

Try this model

Gemini 3.8 Flash

Google

Text to Text

Gemini 3.8 Flash pricing

1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.

Try this model

Claude Fable 5.1

Anthropic

Text to Text

Claude Fable 5.1 pricing

500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.

Try this model

Grok 4.5

xAI

Text to Text

Grok 4.5 pricing

1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.

Try this model

Grok 4.3

xAI

Text to Text

Grok 4.3 pricing

256k context, image input, agentic coding with function calling and MCP, 0.53s first token.

Try this model

Grok Build 0.1

xAI

Text to Text

Grok Build 0.1 pricing

Reasoning, Non-Reasoning or Multi-Agent on one page, 1M context, image input.

Try this model

Grok 4.20

xAI

Text to Text

Grok 4.20 pricing

Text, image, and character references with voice presets; 4-10s videos plus conversational editing.

Try this model

Gemini Omni Flash 1.1

Google

Text to Video
Image to Video
Reference to Video
Video Edit

Gemini Omni Flash 1.1 pricing

Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.

Try this model

Wan 3.0 Prime

Alibaba

Text to Video
Image to Video
Reference to Video

Wan 3.0 Prime pricing

Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.

Try this model

Gemini 3.1 Flash TTS

Google

Text to Speech

Gemini 3.1 Flash TTS pricing

High-quality narration with 30 voices, dialogue mode, and 70+ languages.

Try this model

Gemini 2.5 Pro TTS

Google

Text to Speech

Gemini 2.5 Pro TTS pricing

Fastest, lowest cost per second, with 30 voices and dialogue mode.

Try this model

Gemini 2.5 Flash TTS

Google

Text to Speech

Gemini 2.5 Flash TTS pricing

2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.

Try this model

Wan 3.0

Alibaba

Text to Video
Image to Video
Reference to Video

Wan 3.0 pricing

500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.

Try this model

Grok 4.6

xAI

Text to Text

Grok 4.6 pricing

1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.

Try this model

Gemini 3.7 Flash

Google

Text to Text

Gemini 3.7 Flash pricing

Quality-focused xAI text-to-image and reference editing with up to 5 input images.

Try this model

Grok Imagine 2.0 Image

xAI

Text to Image
Image to Image

Grok Imagine 2.0 Image pricing

1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.

Try this model

Gemini 3.6 Flash

Google

Text to Text

Gemini 3.6 Flash pricing

4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.

Try this model

SeeDance 2.5

ByteDance

Text to Video
Image to Video
Reference to Video
Video to Video
Video Edit

SeeDance 2.5 pricing

2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, up to 9 reference images and 3 reference videos.

Try this model

MiniMax Hailuo H3

MiniMax

Text to Video
Image to Video
Reference to Video

MiniMax Hailuo H3 pricing

1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.

Try this model

Claude Opus 5

Anthropic

Text to Text

Claude Opus 5 pricing

2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.

Try this model

Kimi K3

Moonshot AI

Text to Text

Kimi K3 pricing

1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.

Try this model

GPT 5.6 Sol

OpenAI

Text to Text

GPT 5.6 Sol pricing

1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.

Try this model

GPT 5.6 Terra

OpenAI

Text to Text

GPT 5.6 Terra pricing

Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.

View details

GPT 5.6 Luna

OpenAI

Text to Text

Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.

Try this model

SeeDream 5.0 Pro

ByteDance

Text to Image
Image to Image

SeeDream 5.0 Pro pricing

1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.

Try this model

Claude Fable 5

Anthropic

Text to Text

Claude Fable 5 pricing

200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.

View details

Claude Sonnet 4.5

Anthropic

Text to Text

200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.

View details

Claude Opus 4.5

Anthropic

Text to Text

200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.

Try this model

Claude Haiku 4.5

Anthropic

Text to Text

Claude Haiku 4.5 pricing

Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.

Try this model

Claude Sonnet 5

Anthropic

Text to Text

Claude Sonnet 5 pricing

Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.

Try this model

Nano Banana 2 Lite

Google

Text to Image
Image to Image

Nano Banana 2 Lite pricing

Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.

Try this model

HappyHorse 1.1

Alibaba

Text to Video
Image to Video
Reference to Video

HappyHorse 1.1 pricing

T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.

Try this model

Kling 3.0 Turbo

Kling

Text to Video
Image to Video

Kling 3.0 Turbo pricing

1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.

Try this model

Claude Opus 4.8

Anthropic

Text to Text

Claude Opus 4.8 pricing

T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.

Try this model

HappyHorse 1.0

Alibaba

Text to Video
Image to Video
Reference to Video

HappyHorse 1.0 pricing

1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.

View details

GPT 5.5

OpenAI

Text to Text

T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.

Try this model

GPT Image 2

OpenAI

Text to Image
Image to Image

GPT Image 2 pricing

1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.

Try this model

Claude Opus 4.7

Anthropic

Text to Text

Claude Opus 4.7 pricing

T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.

Try this model

Wan 2.7

Alibaba

Text to Video
Image to Video
Reference to Video
Video to Video

Wan 2.7 pricing

Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.

Try this model

Wan 2.7 Video Edit

Alibaba

Video Edit

Wan 2.7 Video Edit pricing

400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.

View details

GPT 5.4 Mini

OpenAI

Text to Text

400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.

View details

GPT 5.4 Nano

OpenAI

Text to Text

Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.

View details

GPT 5.4

OpenAI

Text to Text

1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.

Try this model

Claude Sonnet 4.6

Anthropic

Text to Text

Claude Sonnet 4.6 pricing

Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.

Try this model

HappyHorse 1.0 Video Edit

Alibaba

Video Edit

HappyHorse 1.0 Video Edit pricing

1M context, 128k output, effort controls, top Arena Document and Search rank.

Try this model

Claude Opus 4.6

Anthropic

Text to Text

Claude Opus 4.6 pricing

Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.

Try this model

Kling 3.0

Kling

Text to Video
Image to Video
Reference to Video

Kling 3.0 pricing

Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.

Try this model

Kling 3.0 Motion Control

Kling

Image to Video
Reference to Video
Video to Video

Kling 3.0 Motion Control pricing

T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.

Try this model

Kling 3.0 Omni Image

Kling

Text to Image
Image to Image

Kling 3.0 Omni Image pricing

Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.

Try this model

Kling 3.0 Omni

Kling

Text to Video
Image to Video
Reference to Video
Video to Video

Kling 3.0 Omni pricing

Edit videos with reference (style guide) or transform mode, plus image and video elements.

Try this model

Kling 3.0 Omni Edit

Kling

Video Edit

Kling 3.0 Omni Edit pricing

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.

Try this model

SeeDream 5.0 Lite

ByteDance

Text to Image
Image to Image

SeeDream 5.0 Lite pricing

T2I with Chinese and English text rendering, 7 aspect ratios. No editing.

Try this model

Z-Image Turbo

Alibaba

Text to Image

Z-Image Turbo pricing

T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.

Try this model

Wan 2.6

Alibaba

Text to Video
Image to Video
Reference to Video

Wan 2.6 pricing

T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.

Try this model

Wan 2.6 Image

Alibaba

Text to Image
Image to Image

Wan 2.6 Image pricing

Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.

Try this model

Kling 2.6 Motion Control

Kling

Image to Video
Reference to Video
Video to Video

Kling 2.6 Motion Control pricing

T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.

Try this model

Kling 2.6

Kling

Text to Video
Image to Video

Kling 2.6 pricing

Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.

Try this model

Flux.2 Pro

Black Forest Labs

Text to Image
Image to Image

Flux.2 Pro pricing

9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.

Try this model

Flux.2 Klein 9B

Black Forest Labs

Text to Image
Image to Image

Flux.2 Klein 9B pricing

4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.

Try this model

Flux.2 Klein 4B

Black Forest Labs

Text to Image
Image to Image

Flux.2 Klein 4B pricing

T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.

Try this model

Qwen Image 2.0

Alibaba

Text to Image
Image to Image

Qwen Image 2.0 pricing

Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.

Try this model

Qwen Image 2.0 Pro

Alibaba

Text to Image
Image to Image

Qwen Image 2.0 Pro pricing

Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.

Try this model

Kling O1

Kling

Text to Video
Image to Video
Reference to Video
Video to Video

Kling O1 pricing

Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.

Try this model

Kling O1 Image

Kling

Text to Image
Image to Image

Kling O1 Image pricing

Reasoning video editing with reference or transform mode, up to 4 reference images.

Try this model

Kling O1 Edit

Kling

Video Edit

Kling O1 Edit pricing

Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.

Try this model

Nano Banana Pro

Google

Text to Image
Image to Image

Nano Banana Pro pricing

T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.

Try this model

Kling 2.5 Turbo

Kling

Text to Video
Image to Video

Kling 2.5 Turbo pricing

Prompt alone or with a start frame, 768p or 1080p, 6 or 10 seconds.

Try this model

MiniMax Hailuo 2.3

MiniMax

Text to Video
Image to Video

MiniMax Hailuo 2.3 pricing

Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.

Try this model

MiniMax Hailuo 2.3 Fast

MiniMax

Image to Video

MiniMax Hailuo 2.3 Fast pricing

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.

Try this model

SeeDream 4.5

ByteDance

Text to Image
Image to Image

SeeDream 4.5 pricing

4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.

Try this model

Veo 3.1

Google

Text to Video
Image to Video
Reference to Video
Video to Video

Veo 3.1 pricing

Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.

Try this model

Nano Banana 2

Google

Text to Image
Image to Image

Nano Banana 2 pricing

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.

Try this model

SeeDream 4.0

ByteDance

Text to Image
Image to Image

SeeDream 4.0 pricing

T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.

Try this model

SeeDance 1.5 Pro

ByteDance

Text to Video
Image to Video

SeeDance 1.5 Pro pricing

Prompt alone, a start frame, or start and end frames, 768p or 1080p, 6 or 10 seconds.

Try this model

MiniMax Hailuo 2.0

MiniMax

Text to Video
Image to Video

MiniMax Hailuo 2.0 pricing

Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.

Try this model

Nano Banana

Google

Text to Image
Image to Image

Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.

Try this model

Topaz Video Upscale

Topaz Labs

Video to Video

Topaz Video Upscale pricing

AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.

Try this model

Topaz Image Upscale

Topaz Labs

Image to Image

Topaz Image Upscale pricing

T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.

Try this model

Kling 2.1 Master

Kling

Text to Video
Image to Video

Kling 2.1 Master pricing

Grok Imagine 1.5 Fast Video Extend cover

Extend a finished Fast video by 6 or 10 seconds, preset or custom mode.

Try this model

Grok Imagine 1.5 Fast Video Extend

xAI

Video to Video

Grok Imagine 1.5 Fast Video Extend pricing

Upscale a finished Grok Imagine video to HD from its task ID.

Try this model

Grok Imagine Upscale

xAI

Video to Video

Grok Imagine Upscale pricing

I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.

Try this model

Kling 2.1

Kling

Image to Video

Kling 2.1 pricing

T2V or I2V at 480p/720p, 5 or 10 second clips.

Try this model

SeeDance 1.0

ByteDance

Text to Video
Image to Video

SeeDance 1.0 pricing

First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.

Try this model

SeeDance 1.0 Pro

ByteDance

Image to Video

SeeDance 1.0 Pro pricing

Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.

Try this model

SeeDance 1.0 Pro Fast

ByteDance

Text to Video
Image to Video

SeeDance 1.0 Pro Fast pricing

Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.

Try this model

Flux.2 Flex

Black Forest Labs

Text to Image
Image to Image

Flux.2 Flex pricing

Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.

Try this model

Flux.2 Max

Black Forest Labs

Text to Image
Image to Image

Flux.2 Max pricing

T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.

Try this model

Grok Imagine 1.5 Fast Video

xAI

Text to Video
Image to Video
Reference to Video

Grok Imagine 1.5 Fast Video pricing

Fast xAI text-to-image and reference editing with up to 5 images.

Try this model

Grok Imagine 1.0 Image

xAI

Text to Image
Image to Image

Grok Imagine 1.0 Image pricing

Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.

View details

Composer 2.5

Cursor

Text to Text

Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.

View details

Composer 2.5 Fast

Cursor

Text to Text

T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.

View details

Wan 2.7 Image

Alibaba

Text to Image
Image to Image

T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.

View details

Wan 2.7 Image Pro

Alibaba

Text to Image
Image to Image

Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.

View details

Wan 2.6 Flash

Alibaba

Text to Video
Image to Video
Reference to Video

T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.

View details

Wan 2.5 Image

Alibaba

Text to Image
Image to Image

T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.

View details

Wan 2.5

Alibaba

Text to Video
Image to Video

T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.

View details

Qwen Image

Alibaba

Text to Image
Image to Image

Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.

View details

Qwen Image Max

Alibaba

Text to Image
Image to Image

Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.

View details

Qwen Image Plus

Alibaba

Text to Image
Image to Image

Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.

View details

Wan 2.2 Image

Alibaba

Text to Image

Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.

View details

Wan 2.2 Image Flash

Alibaba

Text to Image

Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.

View details

Wan 2.2

Alibaba

Text to Video
Image to Video

Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.

View details

Wan 2.2 Fast

Alibaba

Text to Video
Image to Video

Browse model families

APIs by task

All models A–Z

Every model and variant on the platform, including the specialised routes that sit inside a family page.