API Updates

Hey everyone! 👋

Nano Banana 2.1 is now available on SeeAPI for text-to-image generation and image-to-image editing.

Create images from a prompt, edit an existing image, or combine up to 10 reference images. Build product visuals, portraits, and creative compositions with output resolutions up to 4K.

Key Features

Text to Image and Image to Image: generate from text or guide an edit with image references.

Up to 10 reference images: provide 1–10 image URLs for image-to-image requests.

1K, 2K, and 4K output: choose the resolution that fits your workflow.

Flexible framing and formats: use auto or a supported aspect ratio, with PNG or JPG output.

API Pricing

1K: 6 credits per generation.

2K: 10 credits per generation.

4K: 12 credits per generation.

🚀 Start Building

Use nano-banana-2-1 with the text-to-image or image-to-image endpoint through POST /v1/generations. Retrieve the completed image by querying task status or receiving a webhook callback.

Explore the Text to Image API documentation and Image to Image API documentation to get started.

Hey everyone!👋

We’re excited to announce that MiniMax H3 Max 16-bit Pixel is now available on SeeAPI.

Bring a retro game aesthetic to your video workflows. Create 16-bit pixel-art videos from a text prompt or animate a starting image — a creative option for game-inspired scenes, character moments, and short social clips.

Key Features
• Distinctive 16-bit pixel-art style for retro-inspired visual storytelling.
• Text-to-video and image-to-video: start with a written scene or supply a first-frame image and motion prompt.
• 768p video with audio included, with durations from 5 to 15 seconds.
• Flexible framing for text-to-video: choose 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16.

API Pricing: 40 credits/sec (≈ $0.15/sec)

🚀 Start Building
Use minimax-h3-max-16bit-pixel with the text-to-video or image-to-video endpoint through the SeeAPI generation API.

Explore the API documentation to start creating pixel-art videos.

Hey everyone 👋

Text NSFW Filter joins SeeAPI’s image and video moderation tools, bringing contextual text checks to the unified inference API.

Seven moderation categories: explicit sexual content, sexually suggestive content, sexual content involving minors, violence, hate, harassment, and self-harm.

Configurable checks: check all categories by default or select a subset, and adjust the threshold to suit your application.

Structured results: receive an overall verdict, per-category scores and flags, and the applied threshold.

Usage visibility: completed task responses include consumed credits and input/output token counts.

Submit text through POST /v1/inferences with model text-nsfw-filter and endpoint text-moderation, then retrieve the result through GET /v1/inferences/{task_id}.

Moderation considers context rather than keywords alone. Results may include false positives or false negatives; evaluate them against your application’s moderation requirements.

🚀 Try Text NSFW Filter Now!

Hey everyone 👋

MiniMax H3 Max Turbo is now available on SeeAPI! Turn text prompts or images into videos, directly on the web or through the SeeAPI API.

✨ What’s available

Text to Video: Create videos from text prompts.

Image to Video: Animate a starting image, with an optional end frame for added control.

Flexible duration: Generate videos from 5 to 15 seconds.

Two resolutions: Choose 480P or 768P.

🔥 Limited-time launch offer

Start creating at special introductory prices:

480P — only 3 credits per second. A 5-second video costs just 15 credits.

768P — only 5 credits per second. A 5-second video costs just 25 credits.

The same launch prices apply on the web and via API.

⏰ Standard prices return on September 7, 2026, at 04:00 UTC. Make the most of the launch offer before it ends!

🛠️ For developers

Use model ID minimax-h3-max-turbo with the text-to-video or image-to-video endpoint.

🚀 Try MiniMax H3 Max Turbo on SeeAPI today!

Hey everyone 👋

We’re excited to announce that Seedance 2.5 is now available on SeeAPI.

ByteDance’s latest Seedance model brings longer video generation, expanded multimodal reference support, and more precise creative control — making it better suited for complex storytelling and production-ready video workflows.

🌟 Key Features

• Generate videos from 4 to 30 seconds in a single generation, enabling longer and more coherent storytelling. • Support up to 50 multimodal reference assets, including images, videos, and audio, for stronger character, scene, motion, and style consistency. • Support first-frame and last-frame control, multimodal reference workflows, and synchronized audio generation. • Improved reference understanding and precision video editing for more controllable and production-ready results.

🚀 Try Seedance 2.5 on SeeAPI