GPT OSS 120B

POST

/project/p-{Project_Id}/genai/gpt_oss_120b/v1/chat/completions

curl --request POST \
  --url 'https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/genai/gpt_oss_120b/v1/chat/completions?project_id=<PROJECT_ID>&apikey=<API_KEY>' \
  --header 'Authorization: Bearer <API_TOKEN>' \
  --header 'Content-Type: application/json' \
  --data '{
  "temperature": 0.5,
  "max_tokens": 1024,
  "top_p": 1,
  "frequency_penalty": 0,
  "presence_penalty": 1,
  "stream": false,
  "model": "gpt_oss_120b",
  "messages": [
    {
      "role": "user",
      "content": "Can you write a poem about open source machine learning?"
    }
  ]
}'

GPT OSS 120B is a large-scale open-source reasoning model with exceptional performance in complex reasoning tasks and natural language understanding.

Parameters

Path Parameters

Project_Id

required

string

Path parameter Project_Id.

Query Parameters

project_id

required

integer

Project ID

Request Body

Media typeapplication/json

object

temperature

number

Example

0.5

max_tokens

integer

Example

1024

top_p

number

Example

1

frequency_penalty

number

Example

0

presence_penalty

number

Example

1

stream

boolean

Example

false

model

string

Example

gpt_oss_120b

messages

Array<object>

object

role

string

Example

user

content

string

Example

Can you write a poem about open source machine learning?

Responses

default

Successful response (Non-streaming)

Media typeapplication/json

object

id

string

object

string

created

integer

model

string

choices

Array<object>

object

index

integer

message

object

role

string

content

string

refusal

string

nullable

annotations

string

nullable

audio

string

nullable

function_call

string

nullable

tool_calls

Array<string>

reasoning

The internal reasoning process of the model before generating the final response

string

reasoning_content

The internal reasoning process of the model (duplicate field for compatibility)

string

logprobs

string

nullable

finish_reason

string

stop_reason

string

nullable

token_ids

string

nullable

service_tier

string

nullable

system_fingerprint

string

nullable

usage

object

prompt_tokens

integer

total_tokens

integer

completion_tokens

integer

prompt_tokens_details

string

nullable

prompt_logprobs

string

nullable

prompt_token_ids

string

nullable

kv_transfer_params

string

nullable

Example

{
  "id": "chatcmpl-82c7e2c5-a99c-4869-8068-49aa705812ba",
  "object": "chat.completion",
  "created": 1770614085,
  "model": "gpt_oss_120b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "**Open-Source Machine Learning**\n\nIn a lattice of pull-requests and bright PRs,  \nthe code breathes—free as wind through silicon trees...",
        "tool_calls": [],
        "reasoning": "The user asks: \"Can you write a poem about open source machine learning?\" So we need to produce a poem...",
        "reasoning_content": "The user asks: \"Can you write a poem about open source machine learning?\" So we need to produce a poem..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 76,
    "total_tokens": 461,
    "completion_tokens": 385
  }
}