Skip to main content
POST
/
ai
/
chat
/
completions
JavaScript
import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: 'My API Key',
});

const response = await client.ai.chat.createCompletion({
  messages: [
    { role: 'system', content: 'You are a friendly chatbot.' },
    { role: 'user', content: 'Hello, world!' },
  ],
});

console.log(response);
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
messages
ChatCompletionSystemMessageParam · object[]
required

A list of the previous chat messages for context.

Example:
[
  {
    "role": "system",
    "content": "You are a friendly chatbot."
  },
  {
    "role": "user",
    "content": "Hello, world!"
  }
]
​
model
string
default:meta-llama/Meta-Llama-3.1-8B-Instruct

The language model to chat with.

​
api_key_ref
string

If you are using an external inference provider like xAI or OpenAI, this field allows you to pass along a reference to your API key. After creating an integration secret for you API key, pass the secret's identifier in this field.

​
stream
boolean
default:false

Whether or not to stream data-only server-sent events as they become available.

​
temperature
number
default:0.1

Adjusts the "creativity" of the model. Lower values make the model more deterministic and repetitive, while higher values make the model more random and creative.

​
max_tokens
integer

Maximum number of completion tokens the model should generate.

​
tools
(Function · object | Retrieval · object)[]

The function tool type follows the same schema as the OpenAI Chat Completions API. The retrieval tool type is unique to Telnyx. You may pass a list of embedded storage buckets for retrieval-augmented generation.

  • Function
  • Retrieval
​
tool_choice
enum<string>
Available options:
none,
auto,
required
​
response_format
ChatCompletionResponseFormatParam · object

Use this is you want to guarantee a JSON output without defining a schema. For control over the schema, use guided_json.

​
guided_json
object

Must be a valid JSON schema. If specified, the output will follow the JSON schema.

​
guided_regex
string

If specified, the output will follow the regex pattern.

​
guided_choice
string[]

If specified, the output will be exactly one of the choices.

​
min_p
number

This is an alternative to top_p that many prefer. Must be in [0, 1].

​
n
number

This will return multiple choices for you instead of a single chat completion.

​
use_beam_search
boolean
default:false

Setting this to true will allow the model to explore more completion options. This is not supported by OpenAI.

​
best_of
integer

This is used with use_beam_search to determine how many candidate beams to explore.

​
length_penalty
number
default:1

This is used with use_beam_search to prefer shorter or longer completions.

​
early_stopping
boolean
default:false

This is used with use_beam_search. If true, generation stops as soon as there are best_of complete candidates; if false, a heuristic is applied and the generation stops when is it very unlikely to find better candidates.

​
logprobs
boolean
default:false

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.

​
top_logprobs
integer

This is used with logprobs. 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.

​
frequency_penalty
number
default:0

Higher values will penalize the model from repeating the same output tokens.

​
presence_penalty
number
default:0

Higher values will penalize the model from repeating the same output tokens.

​
top_p
number

An alternative or complement to temperature. This adjusts how many of the top possibilities to consider.

Response

Successful Response