Protocol CompatibilityDEVUP AI for LiteLLM
Call DEVUP AI models through LiteLLM with three settings: api_base, your DEVUP AI key, and the catalog ID with openai/ in front. Use it as a Python library or run the LiteLLM Proxy for your team.
System Architecture
How LiteLLM Connects to DEVUP AI
Configuration
Two Settings That Matter
API base
Pass it as api_base.
Model
openai/ followed by the catalog ID, written exactly as listed.
Quick Start
Your First Request
basic.py
import os
import litellm
response = litellm.completion(
model="openai/deepseek-ai/DeepSeek-V4-Pro",
api_base="https://api.devupai.com/v1",
api_key=os.environ["DEVUP_API_KEY"],
messages=[{"role": "user", "content": "Reply with exactly: Salam DEVUP"}],
)
print(response.choices[0].message.content)Capabilities
Supported Capabilities
Chat, streaming and tools
litellm.completion streams tokens and runs tool calls on DEVUP AI models.
Embeddings
litellm.embedding with openai/BAAI/bge-m3 returns 1024-dimension vectors.
LiteLLM Proxy
List DEVUP AI models in config.yaml and serve them to any OpenAI-compatible client.
Local DZD billing
Metered billing in Algerian Dinar with BaridiMob, Edahabia, and CIB local payment support.
FAQ
LiteLLM and DEVUP AI
Does LiteLLM work with DEVUP AI?
Yes. Pass api_base https://api.devupai.com/v1, your DEVUP AI key, and the catalog ID with openai/ in front. Chat, streaming, tool calls, embeddings and structured output then run on DEVUP AI models.
How do I write the model name?
Put openai/ in front of the catalog ID, exactly as listed: openai/deepseek-ai/DeepSeek-V4-Pro. LiteLLM removes only that first prefix, so a catalog ID that starts with openai/ is written openai/openai/gpt-5.4-mini.
Can I run LiteLLM as a proxy for my team?
Yes. List DEVUP AI models in config.yaml, start litellm --config config.yaml, and point any OpenAI-compatible client at the proxy with its master key and a model_name from the file.
