Skip to main content
Fhddos gives you unified access to Google’s entire Gemini model family through OpenAI-compatible endpoints. Whether you need fast text generation, photorealistic images, or cinematic video, you authenticate once with your Fhddos token and call the model that fits your task — no Google Cloud account or Gemini API key required.

​
Set Up Your Environment

Export these two variables before running any example on this page: 
export BASE_URL="https://aiapi.fhddos.com"
export TOKEN="your-fhddos-token"

​
Quick Test

Send your first request to verify everything is working: 
curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-2.5-flash","messages":[{"role":"user","content":"Hello"}]}'

​
Available Models

​
Text Generation

ModelHighlights
gemini-2.5-flashFast responses, cost-efficient — recommended starting point
gemini-2.5-proStronger reasoning for complex tasks
gemini-2.0-flashPrevious-generation fast model
gemini-1.5-proLong context window support

​
Image Generation

ModelNotes
imagen-3.0-generate-001Imagen 3 standard — highest quality
imagen-3.0-fast-generate-001Imagen 3 fast — lower latency

​
Video Generation

ModelNotes
veo-3.1-generate-previewVeo 3.1 standard — best visual quality
veo-3.1-fast-generate-previewVeo 3.1 fast — quicker turnaround

​
Endpoints at a Glance

CapabilityMethod & Endpoint
Chat / text generationPOST /v1/chat/completions
EmbeddingsPOST /v1/embeddings
Image generationPOST /v1/images/generations
Video generationPOST /v1/videos
All endpoints use OpenAI-compatible request and response shapes, so you can drop Fhddos into any existing OpenAI SDK integration by changing base_url and api_key.

​
Authentication

Every request must carry your Fhddos token as a Bearer credential: 
Authorization: Bearer <your-fhddos-token>
No additional headers or API keys are needed.

​
Explore the API

Generate Content

Text conversations, vision, thinking mode, tool calling, and streaming

Image Generation

Imagen 3 text-to-image with sync and async workflows

Video Generation

Veo 3.1 text-to-video and image-to-video with task polling

Embeddings

Semantic text vectors for search, RAG, and similarity