AI model comparison

gpt-oss-20b vs GPT-4o-mini

Side by side comparison of gpt-oss-20b and GPT-4o-mini on pricing, benchmark scores, context window, and more.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

Input / 1M
$0.02
Output / 1M
$0.09
Context
131K

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

Input / 1M
$0.15
Output / 1M
$0.60
Context
128K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

openai logo

gpt-oss-20b

7.8x cheaper for a typical chat

Higher intelligence score

openai logo

gpt-oss-20b

10 vs 6.7 on Artificial Analysis

Larger context window

openai logo

gpt-oss-20b

131K vs 128K tokens

Newer release

openai logo

gpt-oss-20b

Released August 5, 2025

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

openai logogpt-oss-20b10
openai logoGPT-4o-mini6.7

Coding index

openai logogpt-oss-20b20.7
openai logoGPT-4o-mini11.4

Agentic index

openai logogpt-oss-20b1.2
openai logoGPT-4o-miniNot available

Pricing

gpt-oss-20b vs GPT-4o-mini API pricing

Per-token API rates. Cheaper option highlighted.

Metricopenai logogpt-oss-20bopenai logoGPT-4o-mini
Input tokensPer 1M tokens$0.02$0.15
Output tokensPer 1M tokens$0.09$0.60
Cached input (read)Per 1M tokens$0.01$0.08
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

openai logogpt-oss-20b$0.08
openai logoGPT-4o-mini$0.60

Coding task

30K in, 4K out

openai logogpt-oss-20b$0.85$0.60 cached
openai logoGPT-4o-mini$6.90$4.65 cached

Long document summary

150K in, 2K out

openai logogpt-oss-20b$2.72$1.45 cached
openai logoGPT-4o-mini$23.70$12.45 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricopenai logogpt-oss-20bopenai logoGPT-4o-mini
Context window131K tokens128K tokens
Max output118K tokens16K tokens
Input typesTextFile, Image, Text
Output typesTextText
Reasoning effort levelsHigh, Medium, LowNot available
Default reasoning effortMediumNot available
Release dateAugust 5, 2025July 18, 2024

Features

Supported features

API features available for each model.

Metricopenai logogpt-oss-20bopenai logoGPT-4o-mini
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

gpt-oss-20b is 7.8x cheaper for a typical chat. gpt-oss-20b scores higher on the Artificial Analysis Intelligence Index (10 vs 6.7). gpt-oss-20b has the larger context window (131K vs 128K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is gpt-oss-20b or GPT-4o-mini cheaper?

gpt-oss-20b is cheaper for a typical chat (2K input tokens and 500 output tokens). gpt-oss-20b costs $0.02 per 1M input tokens and $0.09 per 1M output tokens, while GPT-4o-mini costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.

Which has a bigger context window, gpt-oss-20b or GPT-4o-mini?

gpt-oss-20b supports up to 131K tokens of context, compared with 128K for GPT-4o-mini.

Is gpt-oss-20b smarter than GPT-4o-mini?

On the Artificial Analysis Intelligence Index, gpt-oss-20b scores 10 and GPT-4o-mini scores 6.7, putting gpt-oss-20b ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use gpt-oss-20b and GPT-4o-mini at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see gpt-oss-20b and GPT-4o-mini answer side by side and keep the better response.

openai logoopenai logo

Why choose? Ask both.

Send one prompt to gpt-oss-20b and GPT-4o-mini at the same time. Compare the answers side by side and keep the best one.