Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
  1. Home
  2. /
  3. Compare

Nano Banana (Gemini 2.5 Flash Image) vs GPT-5.1-Codex-Mini

Compare Nano Banana (Gemini 2.5 Flash Image) from Google and GPT-5.1-Codex-Mini from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for google
Nano Banana (Gemini 2.5 Flash Image)
Favicon for openai
GPT-5.1-Codex-Mini
Favicon for google
Nano Banana (Gemini 2.5 Flash Image)
Favicon for openai
GPT-5.1-Codex-Mini

Overview

Nano Banana (Gemini 2.5 Flash Image)
Author
Google
GPT-5.1-Codex-Mini
Author
OpenAI
Nano Banana (Gemini 2.5 Flash Image)
Context length
33Ktokens
GPT-5.1-Codex-Mini
Context length
400Ktokens
Nano Banana (Gemini 2.5 Flash Image)
Reasoning
GPT-5.1-Codex-Mini
Reasoning
Nano Banana (Gemini 2.5 Flash Image)
Input modalities
GPT-5.1-Codex-Mini
Input modalities
Nano Banana (Gemini 2.5 Flash Image)
Output modalities
GPT-5.1-Codex-Mini
Output modalities

Nano Banana (Gemini 2.5 Flash Image) vs GPT-5.1-Codex-Mini: side-by-side summary

Nano Banana (Gemini 2.5 Flash Image) and GPT-5.1-Codex-Mini are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Nano Banana (Gemini 2.5 Flash Image), from Google, has a 32,768-token context window and is priced at $0.30/M tokens input, $30/M tokens output on OpenRouter.

GPT-5.1-Codex-Mini, from OpenAI, has a 400,000-token context window and is priced at $0.25/M tokens input, $2/M tokens output on OpenRouter.

Context window
  • Nano Banana (Gemini 2.5 Flash Image): 32,768 tokens
  • GPT-5.1-Codex-Mini: 400,000 tokens
Price
  • Nano Banana (Gemini 2.5 Flash Image): $0.30/M tokens input, $30/M tokens output
  • GPT-5.1-Codex-Mini: $0.25/M tokens input, $2/M tokens output
Provided by
  • Nano Banana (Gemini 2.5 Flash Image): Google
  • GPT-5.1-Codex-Mini: OpenAI
  • Nano Banana (Gemini 2.5 Flash Image) model details, providers and pricing
  • GPT-5.1-Codex-Mini model details, providers and pricing

Nano Banana (Gemini 2.5 Flash Image) vs GPT-5.1-Codex-Mini at a glance

Nano Banana (Gemini 2.5 Flash Image) vs GPT-5.1-Codex-Mini comparison
AttributeNano Banana (Gemini 2.5 Flash Image)GPT-5.1-Codex-Mini
Input priceNot applicable$0.25/M tokens
Output priceNot applicable$2/M tokens
Context window32,768 tokens400,000 tokens
Intelligence IndexNot available20.4
Coding IndexNot availableNot available
Agentic IndexNot availableNot available
Latency (p50)1.09 s3.71 s
Throughput (p50)62.0 tok/s62.0 tok/s

Benchmark data updated Oct 5, 2026

Frequently asked questions

Which has the longer context window, Nano Banana (Gemini 2.5 Flash Image) or GPT-5.1-Codex-Mini?

GPT-5.1-Codex-Mini has the longer context window at 400,000 tokens, compared with 32,768 tokens for Nano Banana (Gemini 2.5 Flash Image).

Which is faster, Nano Banana (Gemini 2.5 Flash Image) or GPT-5.1-Codex-Mini?

Nano Banana (Gemini 2.5 Flash Image) and GPT-5.1-Codex-Mini generate at the same median throughput on OpenRouter: 62.0 tokens per second.