Skip to main content
POST
/
v1
/
chat
/
completions
Completions Request
curl --request POST \
  --url https://enricher.getseam.ai/v1/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "researcher",
  "messages": [
    {
      "role": "user",
      "content": "What industry vertical does Seam AI operate in based on their website domain?"
    }
  ],
  "stream": false
}'
{
  "id": "24962ed7-5865-489e-b290-3ff8b62ee916",
  "model": "researcher",
  "created": 1739564194,
  "citations": [
    "https://www.getseam.ai/"
  ],
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "system",
        "content": "Seam AI operates in the Sales and Marketing industry vertical, with a specific focus on Sales Enablement and Go-to-Market (GTM) strategy, as indicated by their website domain, getseam.ai."
      }
    }
  ],
  "object": "chat.completion"
}

Authorizations

​
Authorization
string
header
required

Body

application/json

Model for /v1/chat/completions request body.

​
messages
Messages · array
required
  • ChatCompletionUserMessageParam
  • ChatCompletionSystemMessageParam
  • ChatCompletionDeveloperMessageParam
​
temperature
number | null
default: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.

Required range: 0 <= x <= 2
​
top_p
number | null
default: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.

Required range: 0 <= x <= 1
​
stop

Up to 4 sequences where the API will stop generating further tokens.

​
max_tokens
integer | null
deprecated

The maximum number of tokens to generate.

​
max_completion_tokens
integer | null

An upper bound for the number of tokens that can be generated for a completion.

​
presence_penalty
number | null
default:0

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.

Required range: -2 <= x <= 2
​
frequency_penalty
number | null
default:0

A number between -2.0 and 2.0 where a positive value decreases the likelihood of repeating tokens that have already been mentioned.

​
logit_bias
object | null

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 | null
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.

​
model
string
default:researcher
Allowed value: "researcher"
​
response_format
object | null

We currently support one type of structured output: JSON Schema. To use this feature, provide a JSON Schema as the response_format parameter in this format: {'type': 'json_schema', 'json_schema': {'schema': object}} where object is the valid JSON Schema. Extra keys provided to the object mapped by 'json_schema' will be ignored. Excluding this parameter, passing a null value, or passing {'type': 'text'} will return the completion as a string. This is the default behavior.

  • ResponseFormatJSONSchema
  • ResponseFormatText
​
stream
boolean | null
default:false

If true, stream tokens as Server-Sent Events as the model generates them instead of waiting for the full model response. The stream terminates with data: [DONE]. If false, return a single JSON object containing the results.

Response

Successful Response

​
id
string
required
​
model
string
required
​
created
integer
required
​
choices
Choices · object[]
required
​
citations
string[]
​
object
string
default:chat.completion