Build Smarter, Not Bigger, with the Fusion API.
A drop-in replacement for OpenAI that automatically optimizes for cost, speed, and accuracy. Your existing code is already 99% compatible.
Simple 3-Step Migration
- Sign up and generate your euqai API key. It starts with `q-`.
- In your application's code or environment variables, change the API host from `api.openai.com` to `api.euqai.eu`.
- Update the model identifier to `euqai-fusion-v1` to use our flagship intelligent orchestrator.
That's it. You're done. You are now running on a smarter, cost-effective, and EU-based GDPR-compliant infrastructure.
Our Flagship Orchestrator & Specialist Models
Euqai Fusion v1 (Recommended)
Our intelligent orchestration API. It analyzes your prompt and automatically selects the best tool: a deterministic solver for math, a web search for current events, or a large reasoning model for creativity. The most powerful and cost-effective solution for 99% of use cases.
Cost: Usage-based token pricing. See the docs for a detailed breakdown.
Direct Access to Specialist Models
For advanced use cases where you need to bypass the orchestrator and call a specific model directly.
qwen3-235b
A flagship large language model for complex reasoning, chat, and structured data extraction.
Input: €1.00 / 1M tokens
Output: €3.00 / 1M tokens
mistral-small-24b
An efficient and powerful multimodal model that can understand both text and images in chat conversations.
Input: €0.20 / 1M tokens
Output: €0.50 / 1M tokens
flux-schnell
A state-of-the-art, high-speed image generation model for creating photorealistic and artistic visuals.
Per Image: €0.04 (1024x1024)
Euqai Fusion API Examples
Basic Chat Completion
A standard request to the Fusion API. Our Triage Engine determines the best way to answer.
curl https://api.euqai.eu/v1/chat/completions \
-H "Authorization: Bearer q-..." \
-H "Content-Type: application/json" \
-d '{
"model": "euqai-fusion-v1",
"messages": [
{ "role": "user", "content": "Explain the concept of Occam's Razor in one sentence." }
]
}'
Web Search for Up-to-Date Info
Use the custom `grounding` parameter to allow the model to perform a live web search for questions about recent events.
curl https://api.euqai.eu/v1/chat/completions \
-H "Authorization: Bearer q-..." \
-H "Content-Type: application/json" \
-d '{
"model": "euqai-fusion-v1",
"messages": [
{ "role": "user", "content": "Who won the Best Picture award at the most recent Oscars?" }
],
"grounding": true
}'
Guaranteed JSON Mode
Enable JSON mode for structured, predictable outputs. Fusion's parser guarantees you get a valid, machine-readable JSON object every time.
curl https://api.euqai.eu/v1/chat/completions \
-H "Authorization: Bearer q-..." \
-H "Content-Type: application/json" \
-d '{
"model": "euqai-fusion-v1",
"messages": [
{ "role": "user", "content": "Create a JSON object for a user with name, email, and id from: The new user is Jane Doe (jane.d@example.com)." }
],
"response_format": { "type": "json_object" }
}'
Multimodal Chat (Image Input)
Send both text and images to the `euqai-fusion-v1` model for analysis. Fusion routes it to the best available vision model.
curl https://api.euqai.eu/v1/chat/completions \
-H "Authorization: Bearer q-..." \
-H "Content-Type: application/json" \
-d '{
"model": "euqai-fusion-v1",
"messages": [
{
"role": "user",
"content": [
{ "type": "text", "text": "What is the primary subject of this image?" },
{
"type": "image_url",
"image_url": { "url": "data:image/png;base64,YOUR_BASE64_ENCODED_IMAGE" }
}
]
}
]
}'
Debugging & Transparency
Use the `include_thinking` parameter to see the Fusion engine's internal reasoning, including which tools were used to generate the final response.
curl https://api.euqai.eu/v1/chat/completions \
-H "Authorization: Bearer q-..." \
-H "Content-Type: application/json" \
-d '{
"model": "euqai-fusion-v1",
"messages": [
{ "role": "user", "content": "What is 5 factorial?" }
],
"include_thinking": true
}'
Dive Deeper into Fusion
Read the introduction for the philosophy behind our approach or browse the full API reference for all parameters and response objects.
