reasoning_effort set to low, medium, or high. Thinking tokens are billed as output tokens. Long reasoning at high can take several minutes, so stream the response and set client timeouts with headroom.
Try it in the browser: Gemini 4 Carbon API playground.
Model
Supported Endpoints
- Chat Completions —
POST /v1/chat/completions
Send LLM requests to
https://direct-api.unifically.com, not https://api.unifically.com. The main host sits behind Cloudflare, and Cloudflare’s proxy timeout cuts most LLM requests short before the model has finished writing. When that happens you receive a truncated reply and are still charged for every token generated up to the cut-off. direct-api.unifically.com reaches the same API without the Cloudflare proxy, so long responses complete in full.Example
Image Input
Send an image in animage_url content part alongside your text, either as a direct https link or inline as a base64 data URI.
Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.