gpt-oss-20b

Text Generation • OpenAI • Hosted

OpenAI's open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.

Model Info
Context Window ↗	128,000 tokens
Function calling ↗	Yes
Reasoning	Yes
Unit Pricing	$0.20 per M input tokens, $0.30 per M output tokens

Usage

export default {
  async fetch(request, env): Promise<Response> {
    const response = await env.AI.run('@cf/openai/gpt-oss-20b', {
      instructions: 'You are a concise assistant.',
      input: 'What is the origin of the phrase Hello, World?',
    });

    return Response.json(response);
  },
} satisfies ExportedHandler<Env>;

import os
import requests

ACCOUNT_ID = os.environ.get("CLOUDFLARE_ACCOUNT_ID")
AUTH_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")

prompt = "Tell me all about PEP-8"
response = requests.post(
  f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1/responses",
    headers={"Authorization": f"Bearer {AUTH_TOKEN}"},
    json={
      "model": "@cf/openai/gpt-oss-20b",
      "input": "Tell me all about PEP-8"
    }
)
result = response.json()
print(result)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses   -H "Content-Type: application/json"   -H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN"   -d '{
    "model": "@cf/openai/gpt-oss-20b",
    "input": "What are the benefits of open-source models?"
  }'

Parameters

Synchronous — Send a request and receive a complete response

Input
Output

prompt

stringrequiredminLength: 1The input text prompt for the model to generate a response.

lora

stringName of the LoRA (Low-Rank Adaptation) model to fine-tune the base model.

▶response_format{}

object

raw

booleandefault: falseIf true, a chat template is not applied and you must adhere to the specific model's expected formatting.

stream

booleandefault: falseIf true, the response will be streamed back incrementally using SSE, Server Sent Events.

max_tokens

integerdefault: 256The maximum number of tokens to generate in the response.

temperature

numberdefault: 0.6minimum: 0maximum: 5Controls the randomness of the output; higher values produce more random results.

top_p

numberminimum: 0.001maximum: 1Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses.

top_k

integerminimum: 1maximum: 50Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises.

seed

integerminimum: 1maximum: 9999999999Random seed for reproducibility of the generation.

repetition_penalty

numberminimum: 0maximum: 2Penalty for repeated tokens; higher values discourage repetition.

frequency_penalty

numberminimum: -2maximum: 2Decreases the likelihood of the model repeating the same lines verbatim.

presence_penalty

numberminimum: -2maximum: 2Increases the likelihood of the model introducing new topics.

response

stringThe generated text response from the model

▶usage{}

objectUsage statistics for the inference request

▶tool_calls[]

arrayAn array of tool calls requests made during the response generation

Streaming — Send a request with `stream: true` and receive server-sent events

Input
Output

prompt

stringrequiredminLength: 1The input text prompt for the model to generate a response.

lora

stringName of the LoRA (Low-Rank Adaptation) model to fine-tune the base model.

▶response_format{}

object

raw

booleandefault: falseIf true, a chat template is not applied and you must adhere to the specific model's expected formatting.

stream

booleandefault: falseIf true, the response will be streamed back incrementally using SSE, Server Sent Events.

max_tokens

integerdefault: 256The maximum number of tokens to generate in the response.

temperature

numberdefault: 0.6minimum: 0maximum: 5Controls the randomness of the output; higher values produce more random results.

top_p

top_k

integerminimum: 1maximum: 50Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises.

seed

integerminimum: 1maximum: 9999999999Random seed for reproducibility of the generation.

repetition_penalty

numberminimum: 0maximum: 2Penalty for repeated tokens; higher values discourage repetition.

frequency_penalty

numberminimum: -2maximum: 2Decreases the likelihood of the model repeating the same lines verbatim.

presence_penalty

numberminimum: -2maximum: 2Increases the likelihood of the model introducing new topics.

type

string

title

Stream_Output

description

Server-Sent Events stream when streaming is enabled

contentType

text/event-stream

format

binary

Batch — Send multiple requests in a single API call

Input
Output

▶requests[]

arrayrequired

response

stringThe generated text response from the model

▶usage{}

objectUsage statistics for the inference request

▶tool_calls[]

arrayAn array of tool calls requests made during the response generation

API Schemas (Raw)

Synchronous Input

Synchronous Output

Streaming Input

Streaming Output

Batch Input

Batch Output