kilo-logo
kilo-logo
kilo-logo

/

/

GPT-OSS 20B

GPT-OSS 20B

by OpenAI

GPT-OSS 20B pricing, context window and specs

GPT-OSS 20B is an OpenAI model with a 131,072 token context window. It costs $0.05 per million input tokens and $0.20 per million output tokens, and supports reasoning, tool calling and structured output.

GPT-OSS 20Bopenai/gpt-oss-20b
Updated Nov 20, 2026
Input price$0.05per 1M tokens
Output price$0.20per 1M tokens
Context window131,072tokens, about 98,000 words
Tool callingStructured outputVisionReasoning

GPT-OSS 20B specs

Provider

OpenAI

Model ID

openai/gpt-oss-20b

Input price

$0.05 per 1M tokens

Output price

$0.20 per 1M tokens

Context window

131,072 tokens

Modalities

Text in, text out

Tool calling

โœ“ Supported

Structured output

โœ“ Supported

Reasoning

โœ“ Supported

Vision

Not supported

Prices checked on

When to use GPT-OSS 20B

Pick GPT-OSS 20B for work you run in bulk, where the cost of each call matters more than depth.

High volume steps. Classifying, tagging, routing and pulling fields out of text.

Problems that need thinking. It can reason through a task before it answers.

Agents that use tools. It supports tool calling and structured output, so it can act and hand back clean JSON.

If you need more capability, GPT 4.1 Nano costs $0.10 per million input tokens.

Cost calculator

What GPT-OSS 20B costs at your volume

Pick a workload or move the sliders. The estimate uses the prices in the table above.

Start from a workload
Estimated GPT-OSS 20B cost per month$2.03
Input 56%Output 44%
Per request$0.00014
Per day$0.068
Per 1,000 requests$0.14
Context window used1.4% of 131.1K

Worked out from the provider list price. Fetch Hive charges that price to your AI wallet with no markup per call, and each model call uses one task from your plan.

Templates

Templates you can run with GPT-OSS 20B

Ready-made workflows and agents. Copy one, pick GPT-OSS 20B in the AI step and run it.

Build with it

Use GPT-OSS 20B in Fetch Hive

Fetch Hive is an AI agent builder. Pick this model in any prompt, workflow or agent step, or call it from your own code with one API request.

Call GPT-OSS 20B through the AI Gateway

1

Create a prompt and pick the model

Write your prompt in Fetch Hive and choose this model from the model library. Add a fallback model if you want a backup.

2

Deploy the prompt

Deploying gives the prompt a deployment name and a variant that your code can call.

3

Send one POST request

Call the invoke endpoint with your API key. Usage is charged to your AI wallet at the provider list price, and each call uses one task.

bash
curl -X POST \
  https://api.fetchhive.com/v1/prompt/invoke \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "deployment": "your-deployment",
    "variant": "default",
    "inputs": { "ticket": "Where is my order?" },
    "streaming": false
  }'

Compare

Compare GPT-OSS 20B with similar models

List prices per 1M tokens and context window, next to the models people most often weigh it against.

VS

GPT 5 Nano

by OpenAI
GPT-OSS 20BGPT 5 Nano
Input per 1M tokensSame
$0.05
$0.05
Output per 1M tokens2x the price
$0.20
$0.40
Context window3.1x larger
131K tokens
400K tokens
See GPT 5 Nano pricing and specs
VS

GPT 6 Luna

by OpenAI
GPT-OSS 20BGPT 6 Luna
Input per 1M tokens2x the price
$0.05
$0.10
Output per 1M tokens2.5x the price
$0.20
$0.50
Context window8x larger
131K tokens
1.05M tokens
See GPT 6 Luna pricing and specs
VS

Gemini 2.0 Flash Lite

by Google
GPT-OSS 20BGemini 2.0 Flash Lite
Input per 1M tokens50% pricier
$0.05
$0.075
Output per 1M tokens50% pricier
$0.20
$0.30
Context window8x larger
131K tokens
1.05M tokens
See Gemini 2.0 Flash Lite pricing and specs

FAQ

GPT-OSS 20B questions, answered

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with GPT-OSS 20B

on Fetch Hive today.

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with GPT-OSS 20B

on Fetch Hive today.

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with GPT-OSS 20B

on Fetch Hive today.