GoogleText / ChatNano Banana API: Google AI's chat / LLM model, one key away
Nano Banana via the ApexApi gateway
Gemini 2.5 Flash with image understanding, known as Nano Banana. A chat model that reads images rather than an image generator, on a 32K window. Call it through ApexApi's unified, OpenAI-compatible API with one `ak-` key, alongside every other model in the catalog. It supports a 32,768-token context window, image (vision) input, and streaming responses. Pricing is $0.36 input and $3.00 output per 1M tokens, billed pay-per-use from your credit balance with no subscription.
Nano Banana is served through ApexApi's unified, OpenAI-compatible API. One key, one format, with smart routing and automatic failover. Provider: Google AI.
Why Nano Banana
32,768-token context
Reason over long documents, codebases, and multi-turn history in a single request.
Vision input
Send images alongside text for document, UI, and visual-understanding tasks.
OpenAI-compatible
Drop-in with any OpenAI SDK. Change the base URL and key, keep your code.
Specifications
- Modality
- chat
- Context window
- 32.8K tokens
- Max output
- 32.8K tokens
- Streaming
- Yes
- Tool / function calling
- —
- Vision input
- Yes
Nano Banana: measured reliability
From real calls ApexApi made to Nano Banana during health sweeps over the last 30 days. Our own measurements, not vendor claims.
- Success rate
- 100%
- Avg latency
- 3.5s
- Calls measured
- 1
- Last checked
- Aug 30
See how Nano Banana compares against every model we serve on the model rankings.
Nano Banana pricing
- A million tokens in and a million out costs $3.36 here, all-in.
- That makes it the 38th cheapest of the 81 chat models we serve, ranked on output price.
- It runs 4.8× cheaper than Gemini 3.1 Pro Preview, the pricier option from the same maker.
Getting started with Nano Banana
OpenAI-compatible. Point your client at ApexApi, swap your key, and call it. No new SDK to learn.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apexapi.dev/v1",
api_key="<YOUR_APEXAPI_KEY>",
)
response = client.chat.completions.create(
model="google/gemini-2.5-flash-image",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Nano Banana use cases
What teams build with Nano Banana on ApexApi.
Agents & automation
Tool-using agents that orchestrate multi-step workflows and call APIs.
Coding assistants
Code generation, refactoring, reviews, and multi-file reasoning.
RAG & knowledge apps
Summarization and long-document Q&A grounded in your own data.
Nano Banana vs other models
How it compares, and on ApexApi you can switch between any of them with a single string change, same key, same endpoint.
Nano Banana vs Claude Opus 4.7
Compare Nano Banana against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Claude Opus 4.7 API →Nano Banana vs GPT-5.5
Compare Nano Banana against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about GPT-5.5 API →Nano Banana vs Gemini 3.1 Pro Preview
Compare Nano Banana against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Gemini 3.1 Pro Preview API →Nano Banana API: FAQ
How do I call Nano Banana through ApexApi?
Create an ApexApi key, point your client at https://api.apexapi.dev/v1, and POST to /v1/chat/completions with the model set to `google/gemini-2.5-flash-image`. The API is OpenAI-compatible, so an existing OpenAI SDK works once you change the base URL and key.
How much does Nano Banana cost on ApexApi?
$0.36 per million input tokens and $3.00 per million output tokens, all-in with no separate platform fee. You buy credits and pay per call, with no subscription or minimum.
What is the context window for Nano Banana?
32,768 tokens. It can return up to 32,768 tokens in a single response.
Does Nano Banana support tool calling and image input?
Nano Banana supports image (vision) input and streaming responses, and it does not support tool / function calling.
What should I use instead of Nano Banana?
From the same maker, Gemini 3.1 Flash Lite costs less for lighter work and Gemini 3.6 Flash is the step up when this one falls short. Switching is one string: both run on the same endpoint and the same key, so there is nothing to re-integrate.
Ready to build with Nano Banana?
One API key. Every major AI model. Pay only for what you use.
Get your API key, free to start