# apimartaafc2fr/nano-banana-reverse-api-ja

> Gateway to 300+ AI models behind a single OpenAI-compatible key: image, video and LLM generation with pay-as-you-go USD billing. Some models use reverse-engineered routes (the -ext suffix), the rest go through discounted official routes.

- Magnitude: 2.5 out of 10 — Early signal
- Stars: 61 total · +4 stars today, ≈ 20 by evening
- Star trust: star growth looks organic
- Category: AI agents · Created: 2026-09-28 · Last push: 2026-09-28
- GitHub: https://github.com/apimartaafc2fr/nano-banana-reverse-api-ja · Homepage: https://go.apimart.ai/k-1d99a9 · Page: https://gitnova.dev/en/r/apimartaafc2fr/nano-banana-reverse-api-ja

## Useful for

- Send an image generation request through the OpenAI-compatible endpoint with an APIMart key
- Build an async pipeline: submit a task, poll task_id and read the cost from the result
- Compare LLM, image and video prices from the published unit price table

## Why it’s here

- 4 stars so far today, about 20 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 6 days old and already has 61 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #194.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 11 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 8 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-04: 0, 0, 13, 12, 0, 0, 32, 4

## Spotted in now

- Top new repositories this week: #194

## Similar by description

1. **pbd91ed197/ai-api-proxy** — 0.0 · Steady · AI agents · Shell · +0 stars today, ≈ 0 by evening
   A gateway to 300+ AI models (images, video, LLM) via one OpenAI-compatible key with pay-as-you-go billing and per-call cost in every response. The repo documents APIMart's published prices.
   Full card: https://gitnova.dev/en/r/pbd91ed197/ai-api-proxy.md
2. **azle5biyd9td956/pixverse6-pixverse-v6-api** — 0.0 · Steady · Language models · Shell · +0 stars today, ≈ 0 by evening
   A gateway to 300+ AI models (images, video, LLMs) behind a single OpenAI-compatible key with pay-as-you-go billing and a $1 minimum top-up. The repository publishes current unit prices and documents the APIMart service.
   Full card: https://gitnova.dev/en/r/azle5biyd9td956/pixverse6-pixverse-v6-api.md
3. **apimartb1r/nano-banana-ext-reverse-api-id** — 2.4 · Early signal · Generative media · +3 stars today, ≈ 18 by evening
   Documentation for APIMart's reverse-engineered route to generate images via the gemini-2.5-flash-image-preview model: OpenAI-compatible API, async tasks, and cost returned in every response.
   Full card: https://gitnova.dev/en/r/apimartb1r/nano-banana-ext-reverse-api-id.md
4. **onji14obx6p/video-api-gateway** — 0.0 · Steady · AI agents · Shell · +0 stars today, ≈ 0 by evening
   An AI API gateway with a single OpenAI-compatible key and published per-call prices for images, video, and LLMs. It documents APIMart's rates for accessing 300+ models on a pay-as-you-go basis.
   Full card: https://gitnova.dev/en/r/onji14obx6p/video-api-gateway.md
5. **wqvdw3tl/nano-banana-api-cn** — 0.0 · Steady · Language models · Shell · +0 stars today, ≈ 0 by evening
   Chinese and English documentation for APIMart, a third-party AI API gateway offering one OpenAI-compatible key and base URL to 300+ models with pay-as-you-go billing. It publishes unit prices for images, video and LLM tokens.
   Full card: https://gitnova.dev/en/r/wqvdw3tl/nano-banana-api-cn.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-04 08:43 UTC, updated every 30 minutes.