Skip to main content
POST
/
v1
/
chat
/
completions
Create chat completion
curl --request POST \
  --url https://api.studio.nebius.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
  "store": false,
  "messages": [
    {
      "content": "Hello!",
      "role": "user"
    }
  ],
  "max_tokens": 100,
  "temperature": 1,
  "top_p": 0.5,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": true
      }
    }
  ],
  "tool_choice": "none",
  "reasoning_effort": "low",
  "n": 64,
  "stream": true,
  "stream_options": null,
  "stop": null,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "logit_bias": null,
  "logprobs": true,
  "top_logprobs": null,
  "user": null,
  "response_format": null,
  "extra_body": null,
  "service_tier": "auto"
}'
{
  "id": "cmpl-bd18c4194f544c189578cfcb273a2f74",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?",
        "role": "assistant"
      }
    }
  ],
  "created": 1717516032,
  "model": "meta-llama/Llama-3.3-70B-Instruct",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 26,
    "prompt_tokens": 13,
    "total_tokens": 39
  }
}

Authorizations

​
Authorization
string
header
required

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

Query Parameters

​
ai_project_id
string | null

current project ID

Body

application/json
​
model
string
required

ID of the model to use.

Examples:

"meta-llama/Meta-Llama-3.1-70B-Instruct"

​
messages
ChatCompletionMessage · object[]
required

A list of messages comprising the conversation so far. Example Python code.

Minimum length: 1
Examples:
[{ "content": "Hello!", "role": "user" }]
​
store
boolean | null

Whether or not to store the output of this chat completion request for use in our model distillation.

Examples:

false

​
max_tokens
integer | null

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. Example Python code for counting tokens.

Required range: x >= 0
Examples:

100

​
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
​
tools
ChatCompletionTool · object[] | null
​
tool_choice
Available options:
TitleConst
Tool Choicenone
Tool Choiceauto
Tool Choicerequired
​
reasoning_effort
enum<string> | null
Available options:
low,
medium,
high
​
n
integer | null
default:1

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Required range: 1 <= x <= 128
​
stream
boolean | null
default:false

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

​
stream_options
object | null

If set to {"include_usage": True}, usage stats will be sent with the last chunk of dataExample Python code

Examples:

null

​
stop
string[] | null

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

Examples:

null

​
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.

See more information about frequency and presence penalties.

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

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.

See more information about frequency and presence penalties.

Required range: -2 <= x <= 2
​
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 GPT 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.

As an example, you can pass {"50256": -100} to prevent the token from being generated.

Examples:

null

​
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.

​
top_logprobs
integer | null

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.

Required range: 0 <= x <= 20
Examples:

null

​
user
string | null

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

Examples:

null

​
response_format
object | null

Similar to chat completion, this parameter specifies the format of output. Only {'type': 'json_object'} or {'type': 'text' } is supported.

Examples:

null

​
extra_body
object | null

To provide extra parameters.

Examples:

null

​
service_tier
enum<string> | null
default:auto

The service tier to use for the request. Represents the service tier for requests.

Attributes: Auto: Automatically choose the best available tier for the request (Default or OverLimit). Analyze response to determine which tier was used. Default: Return 429 errors on hitting the rate limit, do not exceed to the OverLimit tier. OverLimit: Indicate that the request was over the user limit. This tier cannot be set by user in the request, but us used in a response for tier=Auto. Flex: Do not consume rate-limit credits, but run with lower priority. May still result in 429 errors in case of if there is no resources to process.

Available options:
auto,
default,
over-limit,
flex
Examples:

"auto"

"flex"

Response

OK

  • ChatCompletionResponse
  • ChatCompletionChunk
​
id
string
required

A unique identifier for the chat completion.

​
object
enum<string>
required

The object type, which is always chat.completion.

Available options:
TitleConst
ChatCompletionObjectchat.completion
​
created
integer
required

The Unix timestamp (in seconds) of when the chat completion was created.

​
model
string
required

The model used for the chat completion.

​
choices
ChatCompletionChoice · object[]
required

A list of chat completion choices. Can be more than one if n is greater than 1.

​
usage
object
required

Usage statistics for the completion request.

​
service_tier
enum<string>
required

The service tier used for the request. Represents the service tier for requests.

Attributes: Auto: Automatically choose the best available tier for the request (Default or OverLimit). Analyze response to determine which tier was used. Default: Return 429 errors on hitting the rate limit, do not exceed to the OverLimit tier. OverLimit: Indicate that the request was over the user limit. This tier cannot be set by user in the request, but us used in a response for tier=Auto. Flex: Do not consume rate-limit credits, but run with lower priority. May still result in 429 errors in case of if there is no resources to process.

Available options:
auto,
default,
over-limit,
flex