AI model comparison

DeepSeek V4 Flash 0423 vs gpt-oss-20b

Side by side comparison of DeepSeek V4 Flash 0423 and gpt-oss-20b on pricing, benchmark scores, context window, and more.

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.

Input / 1M: $0.09
Output / 1M: $0.18
Context: 1.05M

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

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

gpt-oss-20b

3.4x cheaper for a typical chat

Higher intelligence score

Not available

Not enough benchmark data

Larger context window

DeepSeek V4 Flash 0423

1.05M vs 131K tokens

Newer release

DeepSeek V4 Flash 0423

Released April 24, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

DeepSeek V4 Flash 0423Not available

gpt-oss-20bNot available

Coding index

DeepSeek V4 Flash 042356.2

gpt-oss-20b20.7

Agentic index

DeepSeek V4 Flash 042322.2

gpt-oss-20b1.2

Pricing

DeepSeek V4 Flash 0423 vs gpt-oss-20b API pricing

Per-token API rates. Cheaper option highlighted.

Metric	DeepSeek V4 Flash 0423	gpt-oss-20b
Input tokensPer 1M tokens	$0.09	$0.02
Output tokensPer 1M tokens	$0.18	$0.09
Cached input (read)Per 1M tokens	$0.02	$0.01
Cache writePer 1M tokens	Not available	Not 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

DeepSeek V4 Flash 0423$0.27

gpt-oss-20b$0.08

Coding task

30K in, 4K out

DeepSeek V4 Flash 0423$3.46$1.27 cached

gpt-oss-20b$0.90$0.63 cached

Long document summary

150K in, 2K out

DeepSeek V4 Flash 0423$14.01$3.09 cached

gpt-oss-20b$2.88$1.53 cached

Specs

Context window and capabilities

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

Metric	DeepSeek V4 Flash 0423	gpt-oss-20b
Context window	1.05M tokens	131K tokens
Max output	944K tokens	33K tokens
Input types	Text	Text
Output types	Text	Text
Reasoning effort levels	Extra high, High, None	High, Medium, Low
Default reasoning effort	High	Medium
Release date	April 24, 2026	August 5, 2025

Features

Supported features

API features available for each model.

Metric	DeepSeek V4 Flash 0423	gpt-oss-20b
Tool calling	Supported	Supported
Structured outputs	Supported	Supported
JSON mode	Supported	Supported
Reasoning	Supported	Supported
Temperature	Supported	Supported
Stop sequences	Supported	Supported
Deterministic seed	Supported	Supported
Verbosity control	Not supported	Not supported

Our take

gpt-oss-20b is 3.4x cheaper for a typical chat. DeepSeek V4 Flash 0423 has the larger context window (1.05M vs 131K 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 DeepSeek V4 Flash 0423 or gpt-oss-20b 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 DeepSeek V4 Flash 0423 costs $0.09 per 1M input tokens and $0.18 per 1M output tokens.

Which has a bigger context window, DeepSeek V4 Flash 0423 or gpt-oss-20b?

DeepSeek V4 Flash 0423 supports up to 1.05M tokens of context, compared with 131K for gpt-oss-20b.

Can I use DeepSeek V4 Flash 0423 and gpt-oss-20b at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4 Flash 0423 and gpt-oss-20b answer side by side and keep the better response.

Why choose? Ask both.

Send one prompt to DeepSeek V4 Flash 0423 and gpt-oss-20b at the same time. Compare the answers side by side and keep the best one.

Get started See a preview