gpt-oss-20b — OpenAI | Modeldex

gpt-oss-20b

Active

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...

Updated 4 days agoStructured data from Modeldex catalog

FastBudget

Knowledge cutoff

Jun 30, 2024(1.8 years ago)

API release

Aug 5, 2025(9 months ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

gpt-oss-20b became available via the OpenAI API on 2025-08-05.

Training & availability

Training data has a knowledge cutoff of 2024-06-30 — information about events after that date is unlikely to appear in the model's responses. OpenAI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 131K tokens.
Input modalities: text.

Recommended for: fast, cheap.

Limitations

The knowledge cutoff is 21 months old — this model will not know about recent events, releases, or API changes.
Text-only — cannot process images, audio, or video inputs.

Pricing

Input: $0.0300 per 1M tokens
Output: $0.1400 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the openai API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(api_key="sk-...")
resp = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.03/1M

Output tokens / month2.0M

@ $0.14/1M

Input cost

$0.15

5.0M × $0.03/1M

Output cost

$0.28

2.0M × $0.14/1M

Total / month

$0.43

$5.16 / year

Providers & performance

12 providers

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Groq	712tok/s	99ms	$0.075	$0.3	131K	—	tools · json
WandB	323tok/s	267ms	$0.05	$0.2	131K	fp4	tools · json
Amazon Bedrock	203tok/s

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

6.4M/ month

HuggingFace likes

4.5K

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.