POST /api/v1/chat/completions
Creates a model response for the given chat conversation via a customer-provisioned agent endpoint.
Servers
- https://api.digitalocean.com
Request headers
| Name | Type | Required | Description |
|---|---|---|---|
Content-Type |
String | Yes |
The media type of the request body.
Default value: "application/json" |
Query parameters
| Name | Type | Required | Description |
|---|---|---|---|
agent |
Boolean | Yes |
Must be set to true for agent-based completion behavior. Default value: true |
Request body fields
| Name | Type | Required | Description |
|---|---|---|---|
stream |
Boolean | No |
If set to true, the model response data will be streamed to the client as it is generated using server-sent events. Default value: false |
stop |
No |
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. |
|
n |
Integer | No |
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. Default value: 1 |
max_completion_tokens |
Integer | No |
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. |
temperature |
Number | No |
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. |
tools[] |
Array | No |
A list of tools the model may call. Currently, only functions are supported as a tool. |
tools[].function |
Object | Yes | |
tools[].function.name |
String | Yes |
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. |
tools[].function.description |
String | No |
A description of what the function does, used by the model to choose when and how to call the function. |
tools[].function.parameters |
Object | No |
The parameters the function accepts, described as a JSON Schema object. |
tools[].type |
String | Yes |
The type of the tool. Currently, only function is supported. Valid values:
|
metadata |
Object | No |
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. |
tool_choice |
No |
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. |
|
model |
String | Yes |
Model ID used to generate the response. |
top_p |
Number | No |
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. |
frequency_penalty |
Number | No |
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. Default value: 0 |
reasoning_effort |
String | No |
Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Valid values:
|
seed |
Integer | No |
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. |
messages[] |
Array | Yes |
A list of messages comprising the conversation so far. |
messages[].refusal |
String | No |
The refusal message generated by the model (assistant messages only). |
messages[].tool_calls[] |
Array | No |
The tool calls generated by the model (assistant messages only). |
messages[].tool_calls[].id |
String | Yes |
The ID of the tool call. |
messages[].tool_calls[].function |
Object | Yes | |
messages[].tool_calls[].function.name |
String | Yes |
The name of the function to call. |
messages[].tool_calls[].function.arguments |
String | Yes |
The arguments to call the function with, as generated by the model in JSON format. |
messages[].tool_calls[].type |
String | Yes |
The type of the tool. Currently, only function is supported. Valid values:
|
messages[].tool_call_id |
String | No |
Tool call that this message is responding to (tool messages only). |
messages[].content |
String | No |
The contents of the message. |
messages[].reasoning_content |
String | No |
The reasoning content generated by the model (assistant messages only). |
messages[].role |
String | Yes |
The role of the message author. Valid values:
|
logit_bias |
Object | No |
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. |
user |
String | No |
A unique identifier representing your end-user, which can help DigitalOcean to monitor and detect abuse. |
stream_options |
Object | No |
Options for streaming response. Only set this when you set stream to true. |
stream_options.include_usage |
Boolean | No |
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. |
presence_penalty |
Number | No |
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. Default value: 0 |
max_tokens |
Integer | No |
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. |
logprobs |
Boolean | No |
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 value: false |
top_logprobs |
Integer | No |
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. |
How to start integrating
- Add HTTP Task to your workflow definition.
- Search for the API you want to integrate with and click on the name.
- This loads the API reference documentation and prepares the Http request settings.
- Click Test request to test run your request to the API and see the API's response.