WaveSpeedAI

wavespeed.ai

Accelerated inference for 1,000+ image, video and audio models.

45 models

Video

ByteDance8 providers

Seedance 2.5 Flash

Faster, lower-cost Seedance 2.5 (480p/720p): up to 30 s with native audio, first/last frame, multimodal references, video edit and extend.

Lowest
WaveSpeedAIVideo reference · Video Extend · 480p$0.064 / second
WaveSpeedAIVideo reference · 480p$0.071 / second
WaveSpeedAIVideo reference · Video Edit · 480p$0.071 / second
Highest
WaveSpeedAIVideo reference · Video Edit · 720p$0.142 / second
WaveSpeedAI720p$0.228 / second
WaveSpeedAIImage or audio reference · 720p$0.228 / second
ByteDance9 providers

Seedance 2.5

ByteDance’s flagship video model: up to 30 s in one pass, native synchronized audio, first/last-frame control.

Lowest
WaveSpeedAIVideo reference · Video Extend · 480p$0.094 / second
WaveSpeedAIVideo reference · 480p$0.104 / second
WaveSpeedAIVideo reference · Video Edit · 480p$0.104 / second
Highest
WaveSpeedAIVideo reference · Video Edit · 1080p$0.522 / second
WaveSpeedAI1080p$0.855 / second
WaveSpeedAIImage or audio reference · 1080p$0.855 / second
Google7 providers

Gemini Omni Flash 1.2

Google’s updated omni-modal Flash video model with native sound, 3–15 s (up to 10 s with an end frame), 360p up to 4K, closer reference following.

Lowest
WaveSpeedAI360p$0.022 / second
WaveSpeedAI720p$0.067 / second
WaveSpeedAI1080p$0.1 / second
Highest
WaveSpeedAI4k$0.2 / second
ByteDance9 providers

Seedance 2.0 Mini

Faster, lower-cost Seedance 2.0 for drafts and high-volume generation (480p/720p).

Lowest
WaveSpeedAIVideo reference · 480p$0.036 / second
WaveSpeedAI480p$0.057 / second
WaveSpeedAIVideo reference · Video Extend · 480p$0.057 / second
Highest
WaveSpeedAIVideo reference · 720p$0.071 / second
WaveSpeedAI720p$0.114 / second
WaveSpeedAIVideo reference · Video Extend · 720p$0.114 / second
Alibaba7 providers

Wan 3.0

Alibaba Tongyi Wanxiang 3.0: 2–30 s video with audio, first/last frame, 480p–1080p.

Lowest
WaveSpeedAI480p$0.048 / second
WaveSpeedAI720p$0.095 / second
WaveSpeedAI1080p$0.19 / second
Kuaishou7 providers

Kling 3.0 Turbo

Kling 3.0 Turbo: fast high-motion video with native audio; 720p (standard) or 1080p (pro), 3–15 s.

Lowest
WaveSpeedAI720p$0.106 / second
WaveSpeedAI1080p$0.133 / second
ByteDance9 providers

Seedance 2.0

Multi-shot Seedance generation with synchronized audio and first/last-frame control, 4–15 s.

Lowest
WaveSpeedAIVideo reference · 480p$0.071 / second
WaveSpeedAIVideo reference · Video Edit · 480p$0.071 / second
WaveSpeedAI480p$0.114 / second
Highest
WaveSpeedAI1080p$0.57 / second
WaveSpeedAIVideo reference · Video Extend · 1080p$0.57 / second
WaveSpeedAIImage or audio reference · 1080p$0.57 / second
MiniMax8 providers

MiniMax H3

MiniMax Hailuo H3 with native 768p and 2K output, 4–15 s, first/last frame.

Lowest
WaveSpeedAI768p$0.095 / second
WaveSpeedAI2k$0.133 / second
xAI10 providers

Grok Imagine Video 1.5

Grok Imagine Video 1.5: 1–15 second videos with synchronized audio, at 480p, 720p or 1080p. Image-to-video follows the source image aspect ratio.

Lowest
WaveSpeedAItext only · 480p$0.076 / second
WaveSpeedAItext only · 720p$0.133 / second
WaveSpeedAItext only · 1080p$0.237 / second
Google6 providers

Gemini Omni Flash 1.1

Google’s omni-modal Flash video model with native sound, 3–10 s, 360p up to 4K.

Lowest
WaveSpeedAI360p$0.029 / second
WaveSpeedAI720p$0.095 / second
WaveSpeedAI1080p$0.142 / second
Highest
WaveSpeedAI4k$0.285 / second
Alibaba6 providers

HappyHorse 1.1

Alibaba HappyHorse 1.1: strong character consistency and natural motion, 3–15 s.

Lowest
WaveSpeedAI480p$0.067 / second
WaveSpeedAI720p$0.133 / second
WaveSpeedAI1080p$0.171 / second
Black Forest Labs4 providers

FLUX 3 Video

Black Forest Labs’ FLUX 3 video model: 5–20 s with audio, FLUX-level visual quality.

Lowest
WaveSpeedAI720p$0.162 / second
WaveSpeedAI1080p$0.276 / second
Alibaba7 providers

Wan 2.7

Wan 2.7: reliable Tongyi Wanxiang video with first/last-frame control, 2–15 s, 720p/1080p.

Lowest
WaveSpeedAItext only · 720p$0.095 / second
WaveSpeedAIwith input image · 720p$0.095 / second
WaveSpeedAIVideo reference · Video Extend · 720p$0.095 / second
Highest
WaveSpeedAItext only · 1080p$0.142 / second
WaveSpeedAIwith input image · 1080p$0.142 / second
WaveSpeedAIVideo reference · Video Extend · 1080p$0.142 / second
Google6 providers

Veo 3.1

Google DeepMind Veo 3.1: cinematic 4–8 s video with native dialogue and sound effects.

Lowest
WaveSpeedAIno audio$0.19 / second
WaveSpeedAIwith audio$0.38 / second
WaveSpeedAI4k · no audio$0.38 / second
Highest
WaveSpeedAI4k · with audio$0.57 / second

Image

OpenAI6 providers

GPT Image 2.6 Flare

OpenAI GPT Image 2.6 Flare: 50% faster generation with stronger layouts for posters and product visuals.

Lowest
WaveSpeedAIlow · 1K$0.029 / image
WaveSpeedAIwith input image · low · 1K$0.043 / image
WaveSpeedAImedium · 1K$0.048 / image
Highest
WaveSpeedAIwith input image · max · 2K$0.461 / image
WaveSpeedAImax · 4K$0.807 / image
WaveSpeedAIwith input image · max · 4K$0.822 / image
OpenAI6 providers

GPT Image 2.6 Sunburst

OpenAI GPT Image 2.6 Sunburst: refined, higher-quality output with greater consistency across edits.

Lowest
WaveSpeedAIlow · 1K$0.029 / image
WaveSpeedAIwith input image · low · 1K$0.043 / image
WaveSpeedAImedium · 1K$0.048 / image
Highest
WaveSpeedAIwith input image · max · 2K$0.461 / image
WaveSpeedAImax · 4K$0.807 / image
WaveSpeedAIwith input image · max · 4K$0.822 / image
ByteDance7 providers

Seedream 5.5

ByteDance Seedream 5.5: stable multi-round editing, native transparent PNG and sharper text, up to 10 references.

Lowest
WaveSpeedAI1K$0.019 / image
WaveSpeedAI1.5K$0.019 / image
WaveSpeedAI2K$0.033 / image
Google8 providers

Nano Banana 2.1

Google Gemini image model: consistent multi-reference editing, 1K–4K output.

Lowest
WaveSpeedAI1K$0.038 / image
WaveSpeedAI2K$0.057 / image
WaveSpeedAI4K$0.128 / image
ByteDance6 providers

Seedream 5.0 Pro

ByteDance Seedream 5.0 Pro: photoreal images, multilingual text and up to 10-reference editing.

Lowest
WaveSpeedAI1K$0.043 / image
WaveSpeedAI2K$0.086 / image
OpenAI6 providers

GPT Image 2.5 Flare

OpenAI GPT Image 2.5 Flare: fast everyday generation and editing with precise text rendering.

Lowest
WaveSpeedAIlow · 1K$0.0095 / image
WaveSpeedAIlow · 2K$0.019 / image
WaveSpeedAImedium · 1K$0.023 / image
Highest
WaveSpeedAIwith input image · max · 2K$0.584 / image
WaveSpeedAImax · 4K$0.95 / image
WaveSpeedAIwith input image · max · 4K$0.964 / image
OpenAI6 providers

GPT Image 2.5 Sunburst

OpenAI GPT Image 2.5 Sunburst: tighter control for demanding edits and premium creative.

Lowest
WaveSpeedAIlow · 1K$0.0095 / image
WaveSpeedAIlow · 2K$0.019 / image
WaveSpeedAImedium · 1K$0.023 / image
Highest
WaveSpeedAIwith input image · max · 2K$0.584 / image
WaveSpeedAImax · 4K$0.95 / image
WaveSpeedAIwith input image · max · 4K$0.964 / image
MiniMax9 providers

MiniMax H3 Image

MiniMax H3 Image: precise instruction following, up to 16-reference editing and native output up to 20 MP.

Lowest
WaveSpeedAI1K$0.029 / image
WaveSpeedAI2K$0.029 / image
WaveSpeedAI4K$0.086 / image
ByteDance5 providers

Seedream 5.0 Flash

Low-latency Seedream 5.0: same price for 1K–2K, up to 10 reference images.

Lowest
WaveSpeedAI$0.026 / image
Alibaba4 providers

Qwen Image 3.0

Qwen Image 3.0: excellent Chinese/English text rendering, posters and precise editing.

Lowest
WaveSpeedAI$0.029 / image
xAI10 providers

Grok Imagine Image 2.0

xAI Grok Imagine Image 2.0: bold, detailed images with low/medium quality tiers at 1K or 2K.

Lowest
WaveSpeedAItext only · 1K · low$0.038 / request
WaveSpeedAIwith input image · 1K · low$0.048 / request
WaveSpeedAItext only · 1K · medium$0.057 / request
Highest
WaveSpeedAIwith input image · 2K · low$0.067 / request
WaveSpeedAItext only · 2K · medium$0.076 / request
WaveSpeedAIwith input image · 2K · medium$0.086 / request
Google7 providers

Nano Banana 2

Gemini 3.1 Flash Image: fast generation and editing with strong text rendering, 1K–4K.

Lowest
WaveSpeedAI1K$0.067 / image
WaveSpeedAI2K$0.1 / image
WaveSpeedAI4K$0.133 / image
Google7 providers

Nano Banana Pro

Gemini 3 Pro Image: studio-quality output with reasoning, up to 4K.

Lowest
WaveSpeedAI2K$0.133 / image
WaveSpeedAI1K$0.133 / image
WaveSpeedAI4K$0.228 / image
Black Forest Labs5 providers

FLUX.2 Pro

FLUX.2 [pro]: production photorealism and up to 8-reference editing, billed per megapixel.

Lowest
WaveSpeedAI$0.029 / image
WaveSpeedAIwith input image$0.057 / image
Recraft4 providers

Recraft V4

Recraft V4: brand-consistent illustrations, icons and design assets.

Lowest
WaveSpeedAI$0.038 / image
Alibaba7 providers

Z-Image Turbo

Tongyi Z-Image Turbo: sub-second, very low-cost photoreal images with bilingual text.

Lowest
WaveSpeedAI$0.0047 / image

Audio

Chat

OpenAI7 providers

GPT-6 Astra

OpenAI GPT-6 Astra: the most capable GPT-6 tier for hard reasoning, coding and agents. 1.05M context.

Lowest
WaveSpeedAI$9.5 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$19 / 1M input tokens
OpenAI7 providers

GPT-6 Sol

OpenAI GPT-6 Sol: balanced GPT-6 tier for everyday reasoning, coding and tool use. 1.05M context.

Lowest
WaveSpeedAI$1.9 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$3.8 / 1M input tokens
OpenAI8 providers

GPT-6 Luna

OpenAI GPT-6 Luna: the fastest, lowest-cost GPT-6 tier for high-volume tasks. 1.05M context.

Lowest
WaveSpeedAI$0.095 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$0.19 / 1M input tokens
OpenAI8 providers

GPT-5.6 Sol

OpenAI GPT-5.6 Sol: flagship GPT-5.6 tier for complex reasoning and coding.

Lowest
WaveSpeedAI$4.75 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$9.5 / 1M input tokens
OpenAI8 providers

GPT-5.6 Terra

OpenAI GPT-5.6 Terra: mid GPT-5.6 tier balancing quality and cost.

Lowest
WaveSpeedAI$1.9 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$3.8 / 1M input tokens
OpenAI8 providers

GPT-5.6 Luna

OpenAI GPT-5.6 Luna: small, fast GPT-5.6 tier.

Lowest
WaveSpeedAI$0.19 / 1M input tokens
WaveSpeedAIPrompt ≥ 272,000 tokens$0.38 / 1M input tokens
Anthropic7 providers

Claude Opus 5.5

Anthropic Claude Opus 5.5: frontier model for agentic coding, long-horizon tasks and deep analysis. 1M context.

Lowest
WaveSpeedAI$3.8 / 1M input tokens
Anthropic6 providers

Claude Sonnet 5.5

Anthropic Claude Sonnet 5.5: fast, capable everyday model for coding, writing and agents. 1M context.

Lowest
WaveSpeedAI$1.9 / 1M input tokens
Google7 providers

Gemini 4 Argon

Google Gemini 4 Argon: multimodal reasoning model with a 1M-token context.

Lowest
WaveSpeedAI$3.8 / 1M input tokens
Google7 providers

Gemini 3.8 Flash

Google Gemini 3.8 Flash: fast, low-cost multimodal model with a 1M-token context.

Lowest
WaveSpeedAI$1.567 / 1M input tokens
xAI7 providers

Grok 4.7

xAI Grok 4.7: reasoning model with real-time knowledge and a 500K context.

Lowest
WaveSpeedAI$1.9 / 1M input tokens
WaveSpeedAIPrompt ≥ 200,000 tokens$3.8 / 1M input tokens
DeepSeek8 providers

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash: very low-cost fast model with a 1M-token context.

Lowest
WaveSpeedAI$0.247 / 1M input tokens