MaxAPI public models
Image, video, and language models on MaxAPI share bearer authentication. Image and video models use MaxAPI generation endpoints, while Gemini language and image models support the Gemini-compatible /v1beta/models/<id>:generateContent format.
- GPT Image 2 — GPT Image 2 supports image generation and editing with token-based image billing on MaxAPI.
- Gemini 2.5 Flash Image — Gemini 2.5 Flash Image supports fast fixed-price image generation and reference-based editing on MaxAPI.
- Gemini 3.1 Flash Lite Image — Gemini 3.1 Flash Lite Image is the fastest, most cost-effective option for fixed-price 1K image generation and reference-based editing on MaxAPI.
- Nanobanana Pro — Nanobanana Pro supports high quality image generation and reference-based editing on MaxAPI.
- Gemini 3.1 Flash Image Preview — Gemini 3.1 Flash Image Preview supports fast high-resolution image generation and reference-based editing on MaxAPI.
- Gemini 3 Pro Image Preview Beta — Gemini 3 Pro Image Preview Beta supports 4K image generation and reference-based editing on MaxAPI.
- Gemini 3.1 Flash Image Preview Beta — Gemini 3.1 Flash Image Preview Beta supports high-resolution image generation and reference-based editing on MaxAPI.
- GPT Image 2 Beta — GPT Image 2 Beta supports image generation and editing with mix and official-cheap routes.
- Gemini 2.5 Flash — Gemini 2.5 Flash is a fast, low-cost language model for chat and text generation, billed per token on MaxAPI.
- Gemini 2.5 Flash-Lite — Gemini 2.5 Flash-Lite is the most economical Gemini 2.5 language model for high-volume chat and text, billed per token on MaxAPI.
- Gemini 2.5 Pro — Gemini 2.5 Pro is a high-capability reasoning model with a 200k+ token context, billed per token on MaxAPI.
- Gemini 3 Flash Preview — Gemini 3 Flash Preview is a fast next-generation language model for chat and text generation, billed per token on MaxAPI.
- Gemini 3.1 Flash-Lite — Gemini 3.1 Flash-Lite is the most economical Gemini language model for high-volume chat and text, billed per token on MaxAPI.
- Gemini 3.1 Pro Preview — Gemini 3.1 Pro Preview is a top-tier reasoning model with a 200k+ token context, billed per token on MaxAPI.
- Gemini 3.5 Flash — Gemini 3.5 Flash is a balanced next-generation language model for chat and text generation, billed per token on MaxAPI.
- Seedance 2.0 Fast Beta — Seedance 2.0 Fast Beta generates 4 to 15 second videos with per-second billing.
- Seedance 2.0 Beta — Seedance 2.0 Beta supports per-second-billed text-to-video and reference video generation, including 1080p.
- Seedance 2.0 Fast Beta Face — Seedance 2.0 Fast Beta variant tuned for face/character consistency, 4 to 15 second videos with per-second billing.
- Seedance 2.0 Beta Face — Seedance 2.0 Beta variant tuned for face/character consistency, with per-second billing and 1080p support.
- Seedance 2.0 Fast — Seedance 2.0 Fast generates video, billed per output token by resolution and reference mode.
- Seedance 2.0 — Seedance 2.0 supports up to 1080p, billed per output token by resolution and reference mode.
- Veo 3.1 Lite — Google Veo 3.1 Lite (relaxed queue) async video via /v1/videos; per-segment billing, pick resolution 720p/1080p/4k. Supports text-to-video, image-to-video (first frame), or reference video.
- Veo 3.1 Fast — Google Veo 3.1 Fast async video via /v1/videos; per-segment billing, pick resolution 720p/1080p/4k. Supports text-to-video, image-to-video (first frame), or reference video.
- Veo 3.1 Quality — Google Veo 3.1 Quality (Pro) async video via /v1/videos; per-segment billing, pick resolution 720p/1080p/4k. Supports text-to-video, image-to-video (first frame), or reference video.
- Omni Flash — Omni Flash text-to-video; per-second billing (seconds round up to 4/6/8/10), pick resolution 720p/1080p/4k.
- Omni Flash Components — Omni Flash reference-to-video (first/last-frame; up to 7 reference images required); per-second billing (4/6/8/10), pick resolution 720p/1080p/4k.
- Omni Flash Edit — Omni Flash video editing (supply video_url); per-segment billing, pick resolution 720p/1080p/4k.
- Grok Video — Grok 1.0 video generation; per-second billing (seconds round up to 10/16/20), pick resolution 480p/720p.
- Grok Imagine 1.5 — Grok Imagine 1.5 image-to-video (reference image required); per-second billing (6/10/12/15), pick resolution 480p/720p.