Gemini 3.1 Flash Image
Gemini
Fast image creation ...
InputFileImageTextOutputImage API formatOpenAI · Image Generation
Nano Banana 2 delivers fast, production-grade image generation and conversational editing from 0.5K through 4K.
Context131.1K
Max output32.8K
Speed1792 tps
Per request / request$0.11
Availability 100% · Avg latency 8.9s
Gemini 3.1 Flash Lite Image
Gemini
Sub-2-second image g...
InputImageTextOutputImage API formatOpenAI · Image Generation
Nano Banana 2 Lite provides ultra-low-latency, cost-efficient 1K image generation and editing for interactive applications.
Context65.5K
Max output4.1K
Speed3971.6 tps
Per request / request$0.0245
Availability 100% · Avg latency 3.0s
Gemini 3 Pro Image
Gemini
Studio-grade visual ...
InputImageTextOutputImage API formatOpenAI · Image Generation
Nano Banana Pro is Google's reasoning-driven image model for studio-quality design, accurate text rendering, and grounded visual creation.
Context65.5K
Max output32.8K
Speed66.7 tps
Per request / request$0.176
Availability 100% · Avg latency 20.1s
DeepSeek V4 Flash
DeepSeek
68% offFast reasoning at a ...
API formatOpenAI
A fast open-weights reasoning model for coding, analysis, and everyday agent workflows.
Context1M
Max output384K
Speed73.3 tps
Input / 1M$0.07$0.22
Output / 1M$0.14$0.66
Cache read / 1M$0.00138$0.007
Availability 100% · Avg latency 2.7s
DeepSeek V4 Pro
DeepSeek
47% offDeep reasoning for d...
API formatOpenAI
A high-capability reasoning model for complex coding, research, and long-running agents.
Context1M
Max output384K
Speed42.9 tps
Input / 1M$0.348$0.66
Output / 1M$0.696$1.98
Cache read / 1M$0.00293$0.022
Availability 100% · Avg latency 5.0s
GLM 5.2
Zhipu AI
Reliable Chinese-fir...
API formatOpenAI
A general-purpose GLM model for Chinese and multilingual reasoning, coding, and enterprise assistants.
Context--
Max output--
Speed61.2 tps
Input / 1M$0.70
Output / 1M$2.20
Cache read / 1M$0.13
Availability 100% · Avg latency 10.0s
GLM 5.3
Zhipu AI
15% offAdvanced reasoning f...
API formatOpenAI
A newer general-purpose GLM model for advanced reasoning, coding, and tool-using assistants.
Context1.0M
Max output131.1K
Speed81.7 tps
Input / 1M$0.9579$1.126761
Output / 1M$3.0105$3.943662
Cache read / 1M$0.1779$0.28169
Availability 100% · Avg latency 127.7s
GPT 5.6 Luna
OpenAI
85% offEfficient GPT reason...
API formatOpenAI
An efficient GPT 5.6 tier for capable reasoning, coding, and multimodal assistant workflows.
Context400K
Max output128K
Speed22.6 tps
Input / 1M$0.1467$1.00
Output / 1M$0.8802$6.00
Availability 100% · Avg latency 3.3s
GPT Image 2
OpenAI
54% offHigh-quality image g...
InputImageTextOutputImage API formatOpenAI · Image Generation
An OpenAI image generation and editing model for high-quality visual creation.
Context--
Max output--
Speed--
Input / 1M$3.65$8.00
Output / 1M$7.30$40.00
Cache read / 1M$0.915
