OpenAI-compatible API

One API. Multiple models. No application rewrite.

Change the OpenAI SDK base URL, choose a model, and start. Prepaid balance, per-call metrics, and zero retention on supported models.

Create API key Full documentation

Base URLhttps://code.verboo.ai/router/v1

Input

Tokens sent in prompts, including instructions and history.

Cached input

Reused context costs less when the model supports caching.

Output

Tokens generated by the model in its response.

OpenAI SDK

Compatible with the SDK you already use

Use the same OpenAI interface with cURL, Python, or JavaScript.

curl https://code.verboo.ai/router/v1/chat/completions \
  -H "Authorization: Bearer $VERBOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.6-27b","messages":[{"role":"user","content":"Olá, Boo"}]}'

Live catalog

Models and pricing

5 models available

Model	Context	Speed	Inputper 1M tokens	Cachedper 1M tokens	Outputper 1M tokens
deepseek-v4-flash`deepseek-v4-flash`ZDR	1,048,576	64 tok/s	$0.14	$0.006	$0.22
deepseek-v4-flash-0731`deepseek-v4-flash-0731`ZDR	1,048,576	67 tok/s	$0.14	$0.006	$0.22
Qwen 3.6 27b`qwen3.6-27b`ZDR	262,144	74 tok/s	$0.15	$0.03	$1.50
glm-5.2`glm-5.2`ZDR	1,048,576	25 tok/s	$0.70	$0.15	$2.20
Kimi K3`kimi-k3`ZDR	1,048,576	20 tok/s	$2.50	$0.30	$9.00

USD prices per million tokens. Average speed is based on recent calls when enough data is available.

Start with prepaid balance

Add credits, create a key, and track every call in the dashboard. No required subscription.

Open API account