Chat Completions

Tool Calling

Let models call external functions — the foundation of AI agents.

Tool call accuracy is a top priority for us. We invest significant engineering effort into ensuring our gateway correctly parses and routes function arguments. DEVUP AI achieves a top accuracy score across open-source benchmarks.

We provide an OpenAI-compatible tool calling API, meaning your existing agentic workflows and frameworks will work out of the box with zero modifications.

Setup

import openai
import json

client = openai.OpenAI(
    base_url="https://api.devupai.com/v1",
    api_key="$DEVUP_API_KEY",
)

Define your function

def get_current_weather(location):
    """Get the current weather in a given location"""
    if "tokyo" in location.lower():
        return json.dumps({"location": "Tokyo", "temperature": "75"})
    elif "san francisco" in location.lower():
        return json.dumps({"location": "San Francisco", "temperature": "60"})
    elif "paris" in location.lower():
        return json.dumps({"location": "Paris", "temperature": "70"})
    else:
        return json.dumps({"location": location, "temperature": "unknown"})

Step 1: Send tools to the model

tools = [{
    "type": "function",
    "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA"
                }
            },
            "required": ["location"]
        },
    }
}]

messages = [{"role": "user", "content": "What is the weather in San Francisco?"}]

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    tools=tools,
    tool_choice="auto",
)

tool_calls = response.choices[0].message.tool_calls
for tool_call in tool_calls:
    print(tool_call.model_dump())

Output:

json

{'id': 'call_X0xYqdnoUonPJpQ6HEadxLHE', 'function': {'arguments': '{"location": "San Francisco"}', 'name': 'get_current_weather'}, 'type': 'function'}

Step 2: Execute the function and send results back

# Extend conversation with assistant's reply
messages.append(response.choices[0].message)

for tool_call in tool_calls:
    function_name = tool_call.function.name
    if function_name == "get_current_weather":
        function_args = json.loads(tool_call.function.arguments)
        function_response = get_current_weather(
            location=function_args.get("location")
        )

    messages.append({
        "tool_call_id": tool_call.id,
        "role": "tool",
        "content": function_response,
    })

# Get a new response from the model with function results
second_response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    tools=tools,
    tool_choice="auto",
)

print(second_response.choices[0].message.content)

Output:

The current temperature in San Francisco, CA is 60 degrees Fahrenheit.

Tips

Write clear, detailed function descriptions — model quality depends heavily on them
Use lower temperatures (< 1.0) to avoid erratic parameter values
Avoid system messages when using tool calling
Model quality degrades with more functions — keep the list focused
Keep top_p and top_k at their defaults

Supported features

Feature	Supported
Single tool calls
Parallel tool calls	(quality may vary)
tool_choice: "auto"
tool_choice: "none"
Streaming mode
Nested calls

Notes

The tools array itself consumes tokens. The larger your function descriptions, the more prompt tokens you will be billed for.
Not all models are optimized for tool calling. DeepSeek and Llama 3 are highly recommended.

Streaming

Structured Outputs