SambaNova Systems Completions API
The Completions API from SambaNova Systems — 1 operation(s) for completions.
OpenAPI Specification
openapi: 3.1.0
info:
title: Sambanova Agents Service Audio Completions API
description: Service for Sambanova agents
version: 0.0.1
termsOfService: https://sambanova.ai/cloud-end-user-license-agreement
contact:
email: info@sambanova.ai
name: SambaNova information
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0.html
servers:
- url: https://chat.sambanova.ai/api
security:
- api_key: []
tags:
- name: Completions
paths:
/completions:
post:
operationId: createCompletion
tags:
- Completions
summary: Create completion
security:
- api_key: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
description: text prompt and parameters
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/CompletionResponse'
- $ref: '#/components/schemas/CompletionStreamResponse'
'400':
description: Bad Request - Missing or invalid parameters
content:
text/plain:
schema:
type: string
example: 'Invalid request body: - missing property ''model''"'
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/GeneralError'
- $ref: '#/components/schemas/SimpleError'
examples:
missing_model:
summary: No model parameter provided
value:
error:
message: you must provide a model parameter
type: invalid_request_error
param: null
code: null
request_id: a4fa849e
invalid_json:
summary: Malformed JSON body
value:
error:
code: null
message: 'We could not parse the JSON body of your request. (HINT: This likely means you aren''t using your HTTP library correctly. A JSON payload is expected, but what was sent was not valid JSON.)'
param: null
type: invalid_request_error
request_id: 3f7db127
simple:
summary: Simple error (unhandled cases)
value:
error: Model name is required
'401':
description: Unauthorized access
content:
application/json:
schema:
$ref: '#/components/schemas/GeneralError'
examples:
invalid_api_key:
summary: Invalid API key provided
value:
error:
message: 'Incorrect API key provided: *****. You can find your API key at https://cloud.sambanova.ai/apis.'
type: invalid_request_error
param: null
code: invalid_api_key
request_id: d79vcq57os633dverhi0
missing_api_key:
summary: No API key provided
value:
error:
message: 'You didn''t provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY).'
type: invalid_request_error
param: null
code: null
request_id: d7a0dct7os633dvesi60
'404':
description: Not found - model does not exist or wrong endpoint called
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/GeneralError'
- $ref: '#/components/schemas/SimpleError'
examples:
model_not_found:
summary: Model does not exist or is not accessible
value:
error:
code: model_not_found
message: The model `abc` does not exist or you do not have access to it.
param: model
type: invalid_request_error
request_id: 887a8227
simple:
summary: Simple error (unhandled cases e.g. wrong endpoint)
value:
error: Not found
'408':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/SimpleError'
'410':
description: Gone - model is no longer available (deprecated or removed)
content:
application/json:
schema:
$ref: '#/components/schemas/SimpleError'
'429':
description: Too Many Requests
content:
application/json:
schema:
$ref: '#/components/schemas/GeneralError'
'500':
description: Internal Server Error. Unexpected issue on server side.
content:
text/plain:
schema:
type: string
'503':
description: Service Temporarily Unavailable
content:
text/plain:
schema:
type: string
example: Service Temporarily Unavailable
x-codeSamples:
- lang: JavaScript
source: "import SambaNova from 'sambanova';\n\nconst client = new SambaNova({\n apiKey: process.env['SAMBANOVA_API_KEY'], // This is the default and can be omitted\n});\n\nconst completion = await client.completions.create({\n model: 'gpt-oss-120b',\n prompt:\n '<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|> create a poem using palindromes<|eot_id|><|start_header_id|>assistant<|end_header_id|>',\n});\n\nconsole.log(completion);"
- lang: Python
source: "import os\nfrom sambanova import SambaNova\n\nclient = SambaNova(\n api_key=os.environ.get(\"SAMBANOVA_API_KEY\"), # This is the default and can be omitted\n)\nfor completion in client.completions.create(\n model=\"gpt-oss-120b\",\n prompt=\"<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|> create a poem using palindromes<|eot_id|><|start_header_id|>assistant<|end_header_id|>\",\n):\n print(completion)"
components:
schemas:
CompletionResponseMessage:
title: Completion Response Message
type: object
description: completion response message object
additionalProperties: true
properties:
role:
title: Role
type: string
description: The role of the messages author
enum:
- assistant
- user
- system
- tool
content:
title: Content
type: string
description: The contents of the assistant message.
nullable: true
tool_calls:
title: Tool Calls
type: array
items:
$ref: '#/components/schemas/AssistantToolCall'
description: The tool calls generated by the model.
nullable: true
required:
- role
- content
TopLogProbs:
title: TopLogProbs
type: object
additionalProperties: true
properties:
bytes:
title: Bytes
anyOf:
- items:
type: integer
type: array
- type: 'null'
logprob:
title: Logprob
type: number
token:
title: Token
type: string
required:
- token
- logprob
examples:
- token: ' Hello'
logprob: -0.00012340000000000002
bytes:
- 32
- 72
- 101
- 108
- 108
- 111
- token: ' Hi'
logprob: -8.243
bytes:
- 32
- 72
- 105
CompletionResponse:
title: Completion Response
type: object
description: ompletion response returned by the model
properties:
choices:
title: Choices
type: array
items:
$ref: '#/components/schemas/CompletionChoice'
minItems: 1
created:
title: Created
type: number
description: The Unix timestamp (in seconds) of when the chat completion was created.
id:
title: Id
type: string
description: A unique identifier for the chat completion.
model:
title: Model
description: The model used for the chat completion.
type: string
object:
title: Object
type: string
description: The object type, always `chat.completion`.
enum:
- chat.completion
const: chat.completion
system_fingerprint:
title: System fingerprint
type: string
description: Backend configuration that the model runs with.
usage:
$ref: '#/components/schemas/Usage'
required:
- choices
- created
- id
- model
- object
- system_fingerprint
- usage
examples:
- choices:
- finish_reason: stop
index: 0
text: '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!'
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
CompletionChunkChoice:
title: Completion Chunk Choice
type: object
additionalProperties: true
properties:
text:
title: Text
type: string
description: model generation response
finish_reason:
title: Finish Reason
type: string
description: The reason the model stopped generating tokens. Will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `tool_calls` if the model called a tool.
enum:
- stop
- length
nullable: true
index:
title: Index
type: integer
description: The index of the choice in the list of choices
logprobs:
title: Logprobs
anyOf:
- $ref: '#/components/schemas/LogProbs'
description: currently not supported in completions API, always null will be returned
nullable: true
required:
- text
Usage:
title: Usage
type: object
description: Usage metrics for the completion, embeddings,transcription or translation request
additionalProperties: true
properties:
acceptance_rate:
title: Acceptance Rate
type: number
description: acceptance rate
completion_tokens:
title: Completion Tokens
type: integer
description: number of tokens generated in completion
completion_tokens_after_first_per_sec:
title: Completion Tokens After First Per Sec
type: number
description: completion tokens per second after first token generation
completion_tokens_after_first_per_sec_first_ten:
title: Completion Tokens After First Per Sec First Ten
type: number
description: completion tokens per second after first token generation first ten
completion_tokens_after_first_per_sec_graph:
title: Completion Tokens After First Per Sec Graph
type: number
description: completion tokens per second after first token generation
completion_tokens_per_sec:
title: Completion Tokens Per Sec
type: number
description: completion tokens per second
end_time:
title: End Time
type: number
description: The Unix timestamp (in seconds) of when the generation finished.
is_last_response:
title: Is Last Response
type: boolean
description: whether or not is last response, always true for non streaming response
const: true
prompt_tokens_details:
title: Prompt tokens details
type: object
description: Extra tokens details
additionalProperties: true
properties:
cached_tokens:
title: Cached tokens
description: amount of cached tokens
type: integer
prompt_tokens:
title: Prompt Tokens
type: integer
description: number of tokens used in the prompt sent
start_time:
title: Start Time
type: number
description: The Unix timestamp (in seconds) of when the generation started.
time_to_first_token:
title: Time To First Token
type: number
description: also TTF, time (in seconds) taken to generate the first token
time_to_first_token_graph:
title: Time To First Token Graph
type: number
description: Time (in seconds) to first token, adjusted for graph rendering. May differ slightly from time_to_first_token.
stop_reason:
title: Stop Reason
type: string
description: The reason generation stopped (e.g. "stop", "length"). Mirrors the choice-level finish_reason but reported at the usage level.
nullable: true
completion_tokens_details:
title: Completion Tokens Details
type: object
description: Breakdown of completion token consumption.
additionalProperties: true
properties:
reasoning_tokens:
title: Reasoning Tokens
type: integer
description: Number of tokens consumed by the model's internal reasoning process. Only present on reasoning-capable models.
nullable: true
total_latency:
title: Total Latency
type: number
description: total time (in seconds) taken to generate the full generation
total_tokens:
title: Total Tokens
type: integer
description: prompt tokens + completion tokens
total_tokens_per_sec:
title: Total Tokens Per Sec
type: number
description: tokens per second including prompt and completion
nullable: true
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
CompletionRequest:
title: Completion Request
type: object
description: completions request object
additionalProperties: true
properties:
model:
title: Model
description: The model ID to use (e.g. gpt-oss-120b). See available [models](https://docs.sambanova.ai/docs/en/models/sambacloud-models)
anyOf:
- type: string
- enum:
- Meta-Llama-3.3-70B-Instruct
- Meta-Llama-3.2-1B-Instruct
- Meta-Llama-3.2-3B-Instruct
- Llama-3.2-11B-Vision-Instruct
- Llama-3.2-90B-Vision-Instruct
- Meta-Llama-3.1-8B-Instruct
- Meta-Llama-3.1-70B-Instruct
- Meta-Llama-3.1-405B-Instruct
- Qwen2.5-Coder-32B-Instruct
- Qwen2.5-72B-Instruct
- QwQ-32B-Preview
- Meta-Llama-Guard-3-8B
- DeepSeek-R1
- DeepSeek-R1-0528
- DeepSeek-V3-0324
- DeepSeek-V3.1
- DeepSeek-V3.1-cb
- DeepSeek-V3.1-Terminus
- DeepSeek-V3.2
- DeepSeek-R1-Distill-Llama-70B
- Llama-4-Maverick-17B-128E-Instruct
- Llama-4-Scout-17B-16E-Instruct
- Qwen3-32B
- Qwen3-235B
- Llama-3.3-Swallow-70B-Instruct-v0.4
- gpt-oss-120b
- ALLaM-7B-Instruct-preview
- MiniMax-M2.5
- MiniMax-M2.7
- gemma-3-12b-it
prompt:
title: Prompt
type: string
description: Prompt to send to the model.
examples:
- '<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
create a poem using palindromes<|eot_id|><|start_header_id|>assistant<|end_header_id|>
'
max_tokens:
title: Max Tokens
type: integer
description: 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.
nullable: true
example: 2048
max_completion_tokens:
title: Max Completion Tokens
type: integer
description: 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.
nullable: true
example: 2048
temperature:
title: Temperature
type: number
description: 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.
minimum: 0
maximum: 2
default: 0.7
nullable: true
example: 0.7
top_p:
title: Top P
type: number
description: 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.
minimum: 0
maximum: 1
nullable: true
example: 1
top_k:
title: Top K
type: integer
description: 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.
minimum: 1
maximum: 100
nullable: true
example: 5
presence_penalty:
title: Presence Penalty
type: number
description: 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
maximum: 2
minimum: -2
default: 0
nullable: true
frequency_penalty:
title: Frequency Penalty
type: number
description: 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
maximum: 2
minimum: -2
default: 0
do_sample:
title: do_sample
type: boolean
description: If true, sampling is enabled during output generation. If false, deterministic decoding is used.
nullable: true
stop:
title: Stop
description: Sequences where the API will stop generating tokens. The returned text will not contain the stop sequence.
oneOf:
- type: string
example: '
'
nullable: true
- type: array
items:
type: string
example: '["\n"]'
nullable: true
stream:
title: Stream
type: boolean
description: 'If set, partial message deltas will be sent. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message.'
default: false
nullable: true
stream_options:
title: StreamOptions
type: object
description: Options for streaming response. Only set this when setting stream as true
additionalProperties: true
properties:
include_usage:
anyOf:
- type: boolean
title: Include Usage
description: Whether to include the usage metrics in a final chunk or not
nullable: true
nullable: true
logprobs:
title: Logprobs
type: boolean
description: This is not yet supported by our models in completions API. 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: false
nullable: true
top_logprobs:
title: Top Logprobs
type: integer
description: This is not yet supported by our models in completions API. 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.
maximum: 20
minimum: 0
nullable: true
n:
title: N
type: integer
description: '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`.'
maximum: 1
minimum: 1
default: 1
nullable: true
example: 1
logit_bias:
title: Logit Bias
type: object
description: 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.
nullable: true
seed:
title: Seed
description: '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.'
nullable: true
type: integer
required:
- model
- prompt
examples:
- prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|> create a poem using palindromes<|eot_id|><|start_header_id|>assistant<|end_header_id|>
max_tokens: 2048
model: gpt-oss-120b
stream: false
temperature: 0.7
top_p: 1
SimpleError:
title: SimpleError
type: object
description: other kind of simple schema errors
properties:
error:
title: error
type: string
description: error detail.
nullable: true
required:
- error
CompletionStreamResponse:
title: Completion Stream Response
type: object
description: streamed chunk of a completion response returned by the model
additionalProperties: true
properties:
choices:
title: Choices
type: array
description: A list of chat completion choices.
items:
$ref: '#/components/schemas/CompletionChunkChoice'
minItems: 0
nullable: true
created:
title: Created
type: number
description: The Unix timestamp (in seconds) of when the chat completion was created.
id:
title: Id
type: string
description: A unique identifier for the chat completion.
model:
title: Model
description: The model used for the chat completion.
type: string
object:
title: Object
type: string
description: The object type, always `chat.completion.chunk`.
enum:
- chat.completion.chunk
const: chat.completion.chunk
system_fingerprint:
title: System fingerprint
type: string
description: Backend configuration that the model runs with.
usage:
$ref: '#/components/schemas/Usage'
required:
- choices
- created
- id
- model
- object
- system_fingerprint
examples:
- choices:
- delta:
role: assistant
content: ''
index: 0
finish_reason: null
logprobs: null
created: 1737642515.6076705
id: 15fcaba4-1c4a-48fc-bc6e-05b55ddfb30b
model: gpt-oss-120b
object: chat.completion.chunk
system_fingerprint: fastcoe
- choices:
- delta:
role: assistant
content: in
index: 0
finish_reason: null
logprobs: null
created: 1737642515.6076705
id: 15fcaba4-1c4a-48fc-bc6e-05b55ddfb30b
model: gpt-oss-120b
object: chat.completion.chunk
system_fingerprint: fastcoe
- choices:
- delta:
content: ''
index: 0
finish_reason: length
logprobs: null
created: 1737642515.6076705
id: 15fcaba4-1c4a-48fc-bc6e-05b55ddfb30b
model: gpt-oss-120b
object: chat.completion.chunk
system_fingerprint: fastcoe
- choices: []
created: 1737642515.6076705
id: 15fcaba4-1c4a-48fc-bc6e-05b55ddfb30b
model: gpt-oss-120b
object: chat.completion.chunk
system_fingerprint: fastcoe
usage:
acceptance_rate: 3
completion_tokens: 100
completion_tokens_after_first_per_sec: 262.2771255106759
completion_tokens_after_first_per_sec_first_ten: 266.98193514986144
completion_tokens_after_first_per_sec_graph: 266.98193514986144
completion_tokens_per_sec: 217.87260449707574
end_time: 1737642515.9077535
is_last_response: true
prompt_tokens: 43
prompt_tokens_details:
cached_tokens: 0
start_time: 1737642515.4458635
time_to_first_token: 0.0844266414642334
total_latency: 0.4589838186899821
total_tokens: 143
total_tokens_per_sec: 311.55782443081836
AssistantToolCallFunction:
title: AssistantToolCallFunction
type: object
description: The tool that the model called.
additionalProperties: true
properties:
name:
title: Name
type: string
description: The name of the function to call.
nullable: true
arguments:
title: Arguments
type: string
description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
nullable: true
LogProbs:
title: Completion Log Probs
type: object
description: Completion Log Probs object
additionalProperties: true
properties:
content:
$ref: '#/components/schemas/LogProbsContent'
required:
- content
examples:
- content:
- token: ' Hello'
logprob: -0.00012340000000000002
bytes:
- 32
- 72
- 101
- 108
- 108
- 111
top_logprobs:
- token: ' Hello'
logprob: -0.00012340000000000002
bytes:
- 32
- 72
- 101
- 108
- 108
- 111
- token: ' Hi'
logprob: -8.243
bytes:
- 32
- 72
- 105
- token: '!'
logprob: -0.0023456
bytes:
- 33
top_logprobs:
- token: '!'
logprob: -0.0023456
bytes:
- 33
- token: ','
logprob: -6.712
bytes:
- 44
LogProbsContent:
title: Log Probs Content
additionalProperties: true
properties:
bytes:
title: Bytes
anyOf:
- items:
type: integer
type: array
nullable: true
logprob:
title: Logprob
type: number
token:
title: Token
type: string
top_logprobs:
$ref: '#/components/schemas/TopLogProbs'
required:
- token
- logprob
- top_logprobs
examples:
- token: ' Hello'
logprob: -0.00012340000000000002
bytes:
- 32
- 72
- 101
- 108
- 108
- 111
top_l
# --- truncated at 32 KB (35 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/sambanova-systems/refs/heads/main/openapi/sambanova-systems-completions-api-openapi.yml