$ curl https://api.robevo.ai/v1/models

Local models.
Real API.

OpenAI-compatible gateway on our own infrastructure. This is the gateway for our self-hosted AI deployment - the foundation of the upcoming user API server. Plug in your tools: no rate limits, no data sharing, no surprises on the bill.

MODELS

UPTIME (30d)

99.97%

MEDIAN LATENCY

312ms

REGION

FRA-1

openai_client.py

# Works with the OpenAI SDK

from openai import OpenAI

client = OpenAI(

base_url="https://api.robevo.ai/v1",

api_key="sk-robevo-...",

)

r = client.chat.completions.create(

model="qwen3:8b",

messages=[{"role": "user", "content": "hi"}],

)

• online ollama backend OpenAI compatible self-hosted tool calling

02 / Endpoints

POST /v1/chat/completions chat & tool calling

POST /v1/completions stream completions

POST /v1/embeddings vector generation

GET /v1/models available models

03 / Models

qwen3:8b

general / tool-use

qwen3:32b

long context

nomic-embed

embeddings, 768d

llama3.3:70b

premium reasoning

Local models. Real API.

Local models.
Real API.