LLM Reference
Prodia

Using Nano Banana 2 (Gemini 3.1 Flash Image) on Prodia

Implementation guide · Gemini 3.1 · Google DeepMind

Serverless

Quick Start

  1. 1
    Create an account at Prodia and generate an API key.
  2. 2
    Use the Prodia SDK or REST API to call inference.gemini-3-1-flash.txt2img.v1 — see the documentation for request format.

Code Examples

See Prodia documentation for integration details.

About Prodia

Prodia provides a developer-friendly REST API for AI image and video generation. The platform supports a wide catalog of models via consistent endpoints, offering text-to-image, image-to-image, inpainting, upscaling, and video generation. Notable features include ultra-low latency (<200ms for Flux Schnell), per-megapixel pricing, volume discounts at scale, and an enterprise tier. Models available include FLUX.1 Schnell/Dev, FLUX.1.1 Pro/Ultra, Stable Diffusion 1.5 and XL, Recraft V4, Seedream, Google Veo 3, OpenAI Sora 2, Kling, Wan 2.2, and image utility models (ESRGAN upscaler, GFPGAN face restore, SAM 3 segmentation, BiRefNet). The API uses versioned inference endpoints (e.g. inference.flux-fast.schnell.txt2img.v2) and returns job results asynchronously.

Prodia is a high-speed AI inference API platform providing scalable access to image and video generation models. It offers a unified REST API for text-to-image, image-to-image, inpainting, upscaling, and video generation, hosting models from Black Forest Labs (Flux), Stability AI, Google, OpenAI, ByteDance, and others. Prodia is known for sub-second latency on Flux Schnell (reported ~190ms) and pay-as-you-go pricing without subscriptions. Utilities include background removal, NSFW detection, face restoration, and segmentation (SAM 3).

Pricing on Prodia

Capabilities

VisionMultimodalReasoningBatch API

About Nano Banana 2 (Gemini 3.1 Flash Image)

Nano Banana 2 is the GA Gemini 3.1 Flash Image model for image generation and editing through the Gemini API. It accepts text, image, PDF, and video inputs, adds video-to-image generation for thumbnails, posters, and infographics, returns text and images, supports search grounding and thinking, and replaces the gemini-3.1-flash-image-preview model retiring on 2026-06-25.

Model Specs

Released2026-05-28
Context131k
ArchitectureDecoder Only
Knowledge cutoff2025-01

Provider

Prodia
Prodia

San Francisco, California, United States