Create chat-based completion

JavaScript

import SambaNova from 'sambanova';

const client = new SambaNova({
  apiKey: process.env['SAMBANOVA_API_KEY'], // This is the default and can be omitted
});

const completion = await client.chat.completions.create({
  messages: [{ content: 'create a poem using palindromes', role: 'user' }],
  model: 'gpt-oss-120b',
});

console.log(completion);

import os
from sambanova import SambaNova

client = SambaNova(
    api_key=os.environ.get("SAMBANOVA_API_KEY"),  # This is the default and can be omitted
)
for completion in client.chat.completions.create(
    messages=[{
        "content": "create a poem using palindromes",
        "role": "user",
    }],
    model="gpt-oss-120b",
):
  print(completion)

curl --request POST \
  --url https://api.sambanova.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "create a poem using palindromes"
    }
  ],
  "model": "gpt-oss-120b"
}
'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.sambanova.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'messages' => [
        [
                'role' => 'user',
                'content' => 'create a poem using palindromes'
        ]
    ],
    'model' => 'gpt-oss-120b'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.sambanova.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.sambanova.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.sambanova.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}"

response = http.request(request)
puts response.read_body

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "In madam moon's silver glow,  Aha, a palindrome to know,  Radar spins, a circular tale,  Level heads prevail, without fail.  A man, a plan, a canal, Panama!  Able was I ere I saw Elba,  A Santa at NASA, a curious sight,  Do geese see God, in the pale moonlight?  Mr. Owl ate my metal worm,  Do nine men interpret? Nine men, I nod,  Never odd or even, a palindrome's might,  Madam, in Eden, I'm Adam.  Aibohphobia, a fear to confess,  A palindrome's symmetry, I must address,  Refer, a word that reads the same,  A palindrome's beauty, in its circular game.  In the stillness of the night,  Ava, a palindrome, shining bright,  Hannah, a name that reads the same,  A palindrome's magic, in its circular flame.  Note: Please keep in mind that creating a poem using palindromes can be a challenging task,  and the resulting poem may not be as cohesive or flowing as one that doesn't rely on palindromes.  However, I hope you enjoy the attempt!",
        "role": "assistant"
      }
    }
  ],
  "created": 1737583288.6076705,
  "id": "83a7809d-e18f-44f9-9ab7-2bc494c6c661",
  "model": "gpt-oss-120b",
  "object": "chat.completion",
  "system_fingerprint": "fastcoe",
  "usage": {
    "acceptance_rate": 4.058139324188232,
    "completion_tokens": 350,
    "completion_tokens_after_first_per_sec": 248.09314856382406,
    "completion_tokens_after_first_per_sec_first_ten": 249.67922929952655,
    "completion_tokens_per_sec": 238.91966176995348,
    "end_time": 1737583289.7345645,
    "is_last_response": true,
    "prompt_tokens": 43,
    "start_time": 1737583288.264706,
    "time_to_first_token": 0.06312894821166992,
    "total_latency": 1.4649275719174653,
    "total_tokens": 393,
    "total_tokens_per_sec": 268.27264878740493
  }
}

POST

chat

completions

JavaScript

import SambaNova from 'sambanova';

const client = new SambaNova({
  apiKey: process.env['SAMBANOVA_API_KEY'], // This is the default and can be omitted
});

const completion = await client.chat.completions.create({
  messages: [{ content: 'create a poem using palindromes', role: 'user' }],
  model: 'gpt-oss-120b',
});

console.log(completion);

import os
from sambanova import SambaNova

client = SambaNova(
    api_key=os.environ.get("SAMBANOVA_API_KEY"),  # This is the default and can be omitted
)
for completion in client.chat.completions.create(
    messages=[{
        "content": "create a poem using palindromes",
        "role": "user",
    }],
    model="gpt-oss-120b",
):
  print(completion)

curl --request POST \
  --url https://api.sambanova.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "create a poem using palindromes"
    }
  ],
  "model": "gpt-oss-120b"
}
'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.sambanova.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'messages' => [
        [
                'role' => 'user',
                'content' => 'create a poem using palindromes'
        ]
    ],
    'model' => 'gpt-oss-120b'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.sambanova.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.sambanova.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.sambanova.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"create a poem using palindromes\"\n    }\n  ],\n  \"model\": \"gpt-oss-120b\"\n}"

response = http.request(request)
puts response.read_body

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "In madam moon's silver glow,  Aha, a palindrome to know,  Radar spins, a circular tale,  Level heads prevail, without fail.  A man, a plan, a canal, Panama!  Able was I ere I saw Elba,  A Santa at NASA, a curious sight,  Do geese see God, in the pale moonlight?  Mr. Owl ate my metal worm,  Do nine men interpret? Nine men, I nod,  Never odd or even, a palindrome's might,  Madam, in Eden, I'm Adam.  Aibohphobia, a fear to confess,  A palindrome's symmetry, I must address,  Refer, a word that reads the same,  A palindrome's beauty, in its circular game.  In the stillness of the night,  Ava, a palindrome, shining bright,  Hannah, a name that reads the same,  A palindrome's magic, in its circular flame.  Note: Please keep in mind that creating a poem using palindromes can be a challenging task,  and the resulting poem may not be as cohesive or flowing as one that doesn't rely on palindromes.  However, I hope you enjoy the attempt!",
        "role": "assistant"
      }
    }
  ],
  "created": 1737583288.6076705,
  "id": "83a7809d-e18f-44f9-9ab7-2bc494c6c661",
  "model": "gpt-oss-120b",
  "object": "chat.completion",
  "system_fingerprint": "fastcoe",
  "usage": {
    "acceptance_rate": 4.058139324188232,
    "completion_tokens": 350,
    "completion_tokens_after_first_per_sec": 248.09314856382406,
    "completion_tokens_after_first_per_sec_first_ten": 249.67922929952655,
    "completion_tokens_per_sec": 238.91966176995348,
    "end_time": 1737583289.7345645,
    "is_last_response": true,
    "prompt_tokens": 43,
    "start_time": 1737583288.264706,
    "time_to_first_token": 0.06312894821166992,
    "total_latency": 1.4649275719174653,
    "total_tokens": 393,
    "total_tokens_per_sec": 268.27264878740493
  }
}

Authorizations

Authorization

string

header

required

SambaNova API key, sent as a bearer token in the Authorization header (Authorization: Bearer <key>). Default authentication scheme used by the SambaNova SDK across every OpenAI compatible endpoint.

Body

application/json

Chat prompt and parameters

chat completions request object. Unknown fields are rejected with a 400 (unknown_parameter) error.

model

required

The model ID to use (e.g. gpt-oss-120b). See available models

messages

(System Message · object | User Message · object | Assistant Message · object | Tool Message · object)[]

required

A list of messages comprising the conversation so far.

Minimum array length: 1

System Message
User Message
Assistant Message
Tool Message

Show child attributes

Example:

[
  {
    "role": "user",
    "content": "create a poem using palindromes"
  }
]

max_tokens

integer | null

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.

Example:

2048

max_completion_tokens

integer | null

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.

Example:

2048

temperature

number | null

default:0.7

What sampling temperature to use, determines the degree of randomness in the response. 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. Is recommended altering this, top_p or top_k but not more than one of these.

Required range: 0 <= x <= 2

Example:

0.7

top_p

number | null

Cumulative probability for token choices. 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. Is recommended altering this, top_k or temperature but not more than one of these.

Required range: 0 <= x <= 1

Example:

1

top_k

integer | null

Amount limit of token choices. An alternative to sampling with temperature, the model considers the results of the first K tokens with higher probability. So 10 means only the first 10 tokens with higher probability are considered. Is recommended altering this, top_p or temperature but not more than one of these.

Required range: 1 <= x <= 100

Example:

5

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. Not currently implemented; accepted for API compatibility

Required range: -2 <= x <= 2

frequency_penalty

number

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. Not currently implemented; accepted for API compatibility

Required range: -2 <= x <= 2

repetition_penalty

number | null

Penalizes repeated tokens. A value of 1.0 applies no penalty; values above 1.0 discourage repetition. Only supported for some models (currently MiniMax and gpt-oss models); silently ignored on models that do not support it.

Required range: 1 <= x <= 2

stop

Sequences where the API will stop generating tokens. The returned text will not contain the stop sequence.

Example:

"\n"

stream

boolean | null

default:false

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

stream_options

StreamOptions · object | null

Options for streaming response. Only set this when setting stream as true

Show child attributes

response_format

ResponseFormatJSONSchema · object

Specifies that the model should produce output conforming to a given JSON schema.

ResponseFormatJSONSchema
ResponseFormatJSONObject
ResponseFormatText

Show child attributes

Example:

{
  "type": "json_schema",
  "json_schema": {
    "name": "User",
    "description": "JSON schema for a simple user object",
    "strict": false,
    "schema": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier for the user"
        },
        "name": {
          "type": "string",
          "description": "Full name of the user"
        }
      },
      "required": ["id", "name"]
    }
  }
}

reasoning_effort

enum<string> | null

Value specifying the amount of reasoning the model is allowed to do, increasing it will increase the number of output reasoning tokens generated by the model, but will improve quality of the responses. allowed values are 'low', 'medium', 'high'

Available options:

low,

medium,

high

tool_choice

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.

Available options:

none,

auto,

required

parallel_tool_calls

boolean | null

Whether to enable parallel function calling during tool use.

tools

Tool · object[] | null

A list of tools the model may call. Use this to provide a list of functions the model may generate JSON inputs for.

Maximum array length: 128

Show child attributes

chat_template_kwargs

Chat Template Kwargs · object | null

A dictionary of additional keyword arguments to pass into the chat template. Use this to provide extra context or parameters that the model's chat template can process. Keys must be strings; values may be any valid JSON type.

Show child attributes

Example:

{ "enable_thinking": true }

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

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.

Required range: 1 <= x <= 8

Example:

1

logit_bias

Logit Bias · object | null

Modify the likelihood of specified tokens appearing in the generation. Accepts a JSON object that maps tokens (specified by their token ID in the model 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. 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.

seed

integer | null

If specified, our 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, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

Response

Successful Response, Returns a ChatCompletionResponse object (non-streaming), or a stream of server-sent ChatCompletionStreamResponse object events ending with a response.completed event (when stream: true).

Chat Completion Response
Chat Completion Stream Response

chat completion response returned by the model

choices

Chat Completion Choice · object[]

required

Minimum array length: 1

Show child attributes

created

number

required

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

string

required

A unique identifier for the chat completion.

model

string

required

The model used for the chat completion.

object

enum<string>

required

The object type, always chat.completion.

Available options:

chat.completion

Allowed value: "chat.completion"

system_fingerprint

string

required

Backend configuration that the model runs with.

usage

Usage · object | null

required

Usage metrics for the completion, embeddings,transcription or translation request

Show child attributes

Examples:

{
  "completion_tokens": 260,
  "completion_tokens_after_first_per_sec": 422.79282728043336,
  "completion_tokens_after_first_per_sec_first_ten": 423.6108998455803,
  "completion_tokens_after_first_per_sec_graph": 423.6108998455803,
  "completion_tokens_per_sec": 314.53312043711406,
  "completion_tokens_details": { "reasoning_tokens": 55 },
  "end_time": 1776189309.02061,
  "is_last_response": true,
  "prompt_tokens": 90,
  "prompt_tokens_details": { "cached_tokens": 0 },
  "start_time": 1776189308.193988,
  "stop_reason": "stop",
  "time_to_first_token": 0.21402883529663086,
  "time_to_first_token_graph": 0.2102978229522705,
  "total_latency": 0.8266220092773438,
  "total_tokens": 350,
  "total_tokens_per_sec": 423.40996981919204
}

{ "prompt_tokens": 43, "total_tokens": 393 }

Overview

Inference API

Chat Agents API

Using the API

Authorizations

Body

Response