OpenAI

OpenAI: gpt-oss-20b (batch)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

ReasoningStreamingJSON mode
131.1K token context Released Aug 5, 2025

Intelligence overview

0
Intelligence
0
Coding
0
Agentic

131.1K tok

Context window

118.0K tok

Max output

Capabilities

What OpenAI: gpt-oss-20b (batch) can do.

Reasoning

Extended reasoning

Works through problems step by step before answering, trading latency for accuracy on harder tasks.

Adjustable effort

Choose how much the model deliberates per request — trade speed for depth as the task demands.

Development

Structured output

Returns responses constrained to a JSON schema, ready to parse without cleanup.

Streaming

Streams tokens as they're generated instead of waiting on the full response.

Performance

Intelligence9.0
Artificial Analysis
Coding20.7
Artificial Analysis
Agentic1.4
Artificial Analysis

Design Arena — ranked #112 across 2 categories

Pricing

Pay for what you use.

Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.

INPUT

$0.05 / 1M tok

OUTPUT

$0.2 / 1M tok

Use cases

Built for serious work.

Build

Generate and refactor code, with the ability to return structured, parseable output.

Think

Works through hard problems with adjustable reasoning effort — high, medium, low.

Research

Holds up to 131.1K tokens of source material in context without losing the thread.

Preview

Ask OpenAI: gpt-oss-20b (batch) anything.

A preview of the real UltraGPT composer — the model you see here is the model you get.

OpenAI: gpt-oss-20b (batch) Ready

Continues in the UltraGPT app — one login, every model.

Comparison

How OpenAI: gpt-oss-20b (batch) stacks up.

The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.

Specification

Technical details.

Specification

Context window
131.1K tokens
Max output
118.0K tokens
Input modalities
Text
Output modalities
Text
Knowledge cutoff
Jun 30, 2024
Release date
Aug 5, 2025
Reasoning effort
high, medium, low (always on)
Streaming
Supported
Tool calling
Not supported
JSON mode
Supported

Model identity

Provider
OpenAI
Provider ID
openai

Model ID

Reasoning

Effort: high, medium, low · always on
Directory

More from OpenAI, and everything else.

This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.

OpenAI: gpt-oss-20b (batch), one subscription away.

UltraGPT puts this model — and every other one in the directory — behind a single login and one flat monthly price.