Choose flagship
Use the top model when correctness, reasoning depth, and coding reliability matter more than cost.
Gemini collection
Gemini API Family
Use Gemini models for chat, low-latency multimodal tasks, and Google visual generation workflows.
Model comparison
| Model | Best For | Input | Output | Context | Cached |
|---|---|---|---|---|---|
Gemini 3.5 Flash Fast Chat | Responsive Gemini chat model with an OpenAI-compatible API and token billing. | 1 credit / 1K | 4 credits / 1K | 1M | 0.1 credit / 1K |
Gemini 2.5 Flash Lite Value Chat | Lower-cost Gemini model for high-throughput chat and automation tasks. | 1 credit / 1K | 2 credits / 1K | 1M | 0.1 credit / 1K |
Gemini Omni Video | Gemini Omni text-to-video and image-to-video models under one family. | Text / image | Video | 6s / 8s / 10s | Async |
Nano Banana 2 Visual | Image generation and editing for production creative workflows. | Text / image | Image | 0.5K / 1K / 2K / 4K | Async |
Choose balanced
Use value models for assistants, automation, support, and workflows that still need strong quality.
Choose budget
Use lightweight models for routing, classification, extraction, and high-volume background tasks.
Unified access
One API surface for the whole family
Keep product code stable while changing models, providers, pricing, and channel routes from the platform.
curl https://devnextapiany.mexxxxai.win/api/v1/chat/completions \
-H "Authorization: Bearer $APIANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"messages": [{ "role": "user", "content": "Plan an agent workflow" }]
}'