All OpenAI models

gpt-oss-20b

OpenAI · released August 2025

gpt-oss-20b is a OpenAI model with a 131K token context window — about 190 pages of text. It reads Text and replies in Text. It can show its reasoning before it answers.

$0.035

input / 1M tokens

$0.149

output / 1M tokens

131K

context — about 190 pages

0.03¢

a client proposal

Pricing

Input
$0.035 per million tokens
Output
$0.149 per million tokens
Cached input
$0.035 per million tokens

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
OpenAI
Released
August 2025 (2025-08-05)
Context window
131K tokens — about 190 pages
Max output
131K tokens per reply
Input
Text
Output
Text
Reasoning
Shows its thinking before answering
Knowledge cutoff
2024-06-30

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free2.9¢$0.060 tokens250k500k750k1000k
gpt-oss-20b

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

gpt-oss-20b

OpenAI

0.01¢

for this task

48% input · 52% output

Full pricing →

Your $5 welcome credit covers about 34,782 of these.

Compare gpt-oss-20b

Closest in price on a typical task:

gpt-oss-20b vs Qwen3.7 Flash →gpt-oss-20b vs Llama 3 8B Lunaris →gpt-oss-20b vs Nova Micro 1.0 →gpt-oss-20b vs Llama 3.2 1B Instruct →Any other combination →

Questions, answered

How much does gpt-oss-20b cost on Alyph?

gpt-oss-20b costs $0.035 per million input tokens and $0.149 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.03¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is gpt-oss-20b's context window?

131K tokens — about 190 pages. Replies can be up to 131K tokens long.

Can gpt-oss-20b read images and files?

gpt-oss-20b is text-only. The canvas still serializes uploads into plain text, so you can work with files — but it cannot see images.

Does gpt-oss-20b show its reasoning?

Yes. gpt-oss-20b can expose its thinking before the final answer, so you can watch how it got there.

Test gpt-oss-20b against Qwen3.7 Flash

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.

Sign up free Try the demo