gpt-oss-20b
VerifiedOpenAI's gpt-oss-20b handles long-context text tasks with precision.
About gpt-oss-20b
gpt-oss-20b uses a transformer architecture optimized for extended sequences. OpenAI keeps the weights proprietary while providing API access. The 131072-token context enables coherent processing of lengthy documents and multi-turn dialogues.
Developers integrate the model into applications that require detailed text analysis or generation. Its text-only design suits tasks such as summarization, translation, and content creation. Organizations value the controlled deployment for consistent performance.
Capabilities
How gpt-oss-20b compares
gpt-oss-20b (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · gpt-oss-20b ranks #8 of 98
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long document analysis
The 131072 token context enables processing of full-length reports, books, or legal contracts within one session for summarization and extraction.
Extended conversation threads
Large context supports maintaining coherence across multi-turn dialogues that reference earlier details without truncation.
Large codebase review
The model can ingest entire repositories or multiple source files at once to identify patterns, dependencies, or issues.
Strengths & limitations
Strengths
- +Efficient inference for a 20B model
- +Strong long-context handling
- +Flexible text-only deployment
- +Good instruction adherence
Limitations
- –Smaller scale limits depth on hard reasoning
- –Text modality only
- –May lag behind larger frontier models
Cost calculator
Estimate what gpt-oss-20b would cost for your usage.
Based on gpt-oss-20b's $0.03/1M input · $0.14/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "openai/gpt-oss-20b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: openai/gpt-oss-20b
Editor's verdict
gpt-oss-20b is OpenAI's proprietary language models with a 131K-token context window.
At $0.14 per 1M output tokens, it is very cost-efficient for its class.
It is available through OpenAI's API and aggregators like OpenRouter.
Best suited to efficient inference for a 20b model and strong long-context handling.
Frequently asked questions
The model supports a context length of 131072 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other gpt-oss models
Sibling versions in the gpt-oss family from OpenAI.
Similar models
Other language models worth comparing.