Gemini 2.5 Pro is a Google Gemini model exposed on the Huzz API with a single Huzz key and one consistent, OpenAI-compatible interface. Capabilities: File analysis, Vision, Chat, Web search. It supports streaming responses. Long-running jobs run asynchronously with polling. Call it at https://api.huzz.ai using Authorization: Bearer $HUZZ_API_KEY — no per-provider accounts or SDKs required.
FamilyCapabilitiesStreamingAsyncPricing
Google GeminiFile analysis, Vision, Chat, Web searchYesYesUsage-based

​
Endpoints

MethodPathCapability
POST/v1/chat/completionsFile analysis
POST/v1/responsesFile analysis
POST/api/v3/google/gemini-2.5-pro/file-analysisFile analysis
POST/v1/chat/completionsVision
POST/v1/responsesVision
POST/api/v3/google/gemini-2.5-pro/image-to-textVision
POST/v1/chat/completionsChat
POST/v1/responsesChat
POST/api/v3/google/gemini-2.5-pro/text-to-textChat
POST/v1/chat/completionsWeb search
POST/v1/responsesWeb search
POST/api/v3/google/gemini-2.5-pro/web-searchWeb search

​
Code samples

Authenticate with Authorization: Bearer $HUZZ_API_KEY — get a key at huzz.ai/register. 
curl https://api.huzz.ai/v1/chat/completions \
  -H "Authorization: Bearer $HUZZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [{"role": "user", "content": "Hello from Huzz!"}]
  }'
Long-running jobs return a prediction id. See Async predictions for the full submit-and-poll lifecycle. This model supports token streaming — see the Streaming guide.