Replicate
replicate.comOfficial and open models behind one predictions API.
视频

Seedance 2.5
ByteDance’s flagship video model: up to 30 s in one pass, native synchronized audio, first/last-frame control.

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

Seedance 2.0
Multi-shot Seedance generation with synchronized audio and first/last-frame control, 4–15 s.
MiniMax H3
MiniMax Hailuo H3 with native 768p and 2K output, 4–15 s, first/last frame.
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.
HappyHorse 1.1
Alibaba HappyHorse 1.1: strong character consistency and natural motion, 3–15 s.
FLUX 3 Video
Black Forest Labs’ FLUX 3 video model: 5–20 s with audio, FLUX-level visual quality.
LTX-2.5 Fast
Lightricks LTX-2.5 Fast: real-time speed with audio, 6–20 s, up to native 4K.

Wan 2.7
Wan 2.7: reliable Tongyi Wanxiang video with first/last-frame control, 2–15 s, 720p/1080p.
Veo 3.1
Google DeepMind Veo 3.1: cinematic 4–8 s video with native dialogue and sound effects.
图片

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

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

Nano Banana 2.1
Google Gemini image model: consistent multi-reference editing, 1K–4K output.

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

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

GPT Image 2.5 Sunburst
OpenAI GPT Image 2.5 Sunburst: tighter control for demanding edits and premium creative.
Grok Imagine Image 2.0
xAI Grok Imagine Image 2.0: bold, detailed images with low/medium quality tiers at 1K or 2K.

Nano Banana 2
Gemini 3.1 Flash Image: fast generation and editing with strong text rendering, 1K–4K.

Nano Banana Pro
Gemini 3 Pro Image: studio-quality output with reasoning, up to 4K.
FLUX.2 Pro
FLUX.2 [pro]: production photorealism and up to 8-reference editing, billed per megapixel.
Recraft V4
Recraft V4: brand-consistent illustrations, icons and design assets.
对话
GPT-5.6 Sol
OpenAI GPT-5.6 Sol: flagship GPT-5.6 tier for complex reasoning and coding.
GPT-5.6 Terra
OpenAI GPT-5.6 Terra: mid GPT-5.6 tier balancing quality and cost.
GPT-5.6 Luna
OpenAI GPT-5.6 Luna: small, fast GPT-5.6 tier.
Claude Opus 5.5
Anthropic Claude Opus 5.5: frontier model for agentic coding, long-horizon tasks and deep analysis. 1M context.