Vercel AI Gateway
vercel.comVercel’s multi-provider gateway (image and video models).
视频

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.

Seedance 2.5
ByteDance’s flagship video model: up to 30 s in one pass, native synchronized audio, first/last-frame control.
MiniMax H3 Max
MiniMax H3 post-trained by fal for speed: 5–15 s clips with first/last frame, ranked #1 on video arenas.

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

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

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

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.

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.
MiniMax H3 Image
MiniMax H3 Image: precise instruction following, up to 16-reference editing and native output up to 20 MP.
MiniMax H3 Image Highspeed
Faster MiniMax H3 Image: the same text-to-image and 16-reference editing, 1K–4K output.
Grok Imagine Image 2.0
xAI Grok Imagine Image 2.0: bold, detailed images with low/medium quality tiers at 1K or 2K.
Recraft V4
Recraft V4: brand-consistent illustrations, icons and design assets.
音频
对话
GPT-6 Astra
OpenAI GPT-6 Astra: the most capable GPT-6 tier for hard reasoning, coding and agents. 1.05M context.
GPT-6 Sol
OpenAI GPT-6 Sol: balanced GPT-6 tier for everyday reasoning, coding and tool use. 1.05M context.
GPT-6 Luna
OpenAI GPT-6 Luna: the fastest, lowest-cost GPT-6 tier for high-volume tasks. 1.05M context.
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.
Claude Sonnet 5.5
Anthropic Claude Sonnet 5.5: fast, capable everyday model for coding, writing and agents. 1M context.
Gemini 4 Argon
Google Gemini 4 Argon: multimodal reasoning model with a 1M-token context.
Gemini 3.8 Flash
Google Gemini 3.8 Flash: fast, low-cost multimodal model with a 1M-token context.
Grok 4.7
xAI Grok 4.7: reasoning model with real-time knowledge and a 500K context.
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash: very low-cost fast model with a 1M-token context.