For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

Usage

client.agent.chat.completions.create(
    model="llama3.3-70b-instruct",
    messages=[
        {"role": "user", "content": "What is the capital of Portugal?"},
    ],
)

Agent inference methods authenticate with an agent access key and require a per-agent endpoint URL:

client = Client(
    token=os.environ.get("AGENT_ACCESS_KEY"),
    agent_endpoint="https://$AGENT_URL",
)

Description

Creates a model response for the given chat conversation via a customer-provisioned agent endpoint.

Parameters

messages array of objects required

A list of messages comprising the conversation so far.

Show child properties

role string required

The role of the message author.

One of: system, developer, user, assistant, tool

content string or null optional

Example: Hello, how are you?

The contents of the message.

refusal string or null optional

The refusal message generated by the model (assistant messages only).

tool_calls array of objects optional

The tool calls generated by the model (assistant messages only).

Show child properties

id string required

Example: call_abc123

The ID of the tool call.

type string required

Example: function

The type of the tool. Currently, only function is supported.

function object required

Show child properties

name string required

Example: get_weather

The name of the function to call.

arguments string required

Example: {"location": "Boston"}

The arguments to call the function with, as generated by the model in JSON format.

tool_call_id string optional

Example: call_abc123

Tool call that this message is responding to (tool messages only).

reasoning_content string or null optional

The reasoning content generated by the model (assistant messages only).

model string required

Example: llama3-8b-instruct

Model ID used to generate the response.

max_tokens integer or null optional

The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length.

Min: 0

max_completion_tokens integer or null optional

The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run.

Min: 256

frequency_penalty number or null optional

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Min: -2

Max: 2

Default: 0

presence_penalty number or null optional

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Min: -2

Max: 2

Default: 0

top_logprobs integer or null optional

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Min: 0

Max: 20

tools array of objects optional

A list of tools the model may call. Currently, only functions are supported as a tool.

Show child properties

type string required

Example: function

The type of the tool. Currently, only function is supported.

function object required

Show child properties

name string required

Example: get_weather

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description string optional

Example: Get the current weather for a location.

A description of what the function does, used by the model to choose when and how to call the function.

parameters object optional

The parameters the function accepts, described as a JSON Schema object.

tool_choice object optional

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

Show child properties

type string required

Example: function

function object required

Show child properties

name string required

Example: get_weather

The name of the function to call.

stream boolean or null optional

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

Default: False

stop object optional

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

logit_bias object or null optional

Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

logprobs boolean or null optional

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

Default: False

n integer or null optional

Example: 1

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

Min: 1

Max: 128

Default: 1

stream_options object or null optional

Options for streaming response. Only set this when you set stream to true.

Show child properties

include_usage boolean optional

If set, an additional chunk will be streamed before the data [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array.

reasoning_effort string or null optional

Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

One of: none, minimal, low, medium, high, xhigh

seed integer or null optional

If specified, the system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed.

metadata object or null optional

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

temperature number or null optional

Example: 1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

Min: 0

Max: 2

top_p number or null optional

Example: 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Min: 0

Max: 1

user string optional

Example: user-1234

A unique identifier representing your end-user, which can help DigitalOcean to monitor and detect abuse.

Request Sample

import os
from pydo import Client

client = Client(
    token=os.environ.get("AGENT_ACCESS_KEY"),
    agent_endpoint=os.environ.get("AGENT_ENDPOINT"),
)

resp = client.agent.chat.completions.create(
    model="llama3.3-70b-instruct",
    messages=[
        {"role": "user", "content": "What is the capital of Portugal?"},
    ],
)

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

Response Example

{
  "id": "chatcmpl-abc123",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0
    }
  ],
  "created": 1677649420,
  "model": "llama3-8b-instruct",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 20,
    "prompt_tokens": 10,
    "cache_created_input_tokens": 0,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 0
    },
    "cache_read_input_tokens": 0,
    "total_tokens": 30
  }
}

More Information

See /api/v1/chat/completions in the API reference for additional detail on responses, headers, parameters, and more.