OpenAIFree
GPT-OSS 20B
API model name: gpt-oss-20b
GPT-OSS 20B is OpenAI's chat model, served on the Api.Airforce unified API. It has a 131K-token context window. Capabilities include Tool calling, Reasoning. It is available on the free tier at no per-token cost. Knowledge cutoff: 2024-06. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.
Pricing
Specifications
- Provider
- OpenAI
- Type
- chat model
- Context window
- 131K tokens
- Max output
- 33K tokens
- Knowledge cutoff
- 2024-06
- Input
- text
- Output
- text
Capabilities
Tool callingReasoningStreaming
Benchmarks
Independent evaluations and measured speed from Artificial Analysis.
Measured atSame model, different reasoning effort.
Intelligence Index
10.0/100
Math Index
62.3/100
MMLU-Pro72%
GPQA Diamond61%
Humanity's Last Exam5%
LiveCodeBench65%
AIME 202562%
τ²-bench50%
Output speed272.9 tok/s
Time to first token0.40 s
gpt-oss-20b (Low) · 9.0–10.0
Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)
What is GPT-OSS 20B used for?
- Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
- Agents & automation — function calling and tool use for multi-step workflows.
- Complex reasoning — math, coding and step-by-step problem solving.
- Real-time experiences — stream tokens for responsive chat and apps.
GPT-OSS 20B vs. similar models
| Model | Intelligence | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| GPT-OSS 20B | 10.0 | 131K | Free | Free |
| Babbage 002 | — | — | $0.34 | $0.34 |
| ChatGPT-4o Latest | — | — | $2.75 | $14.50 |
| Codex Auto Review | — | — | $0.09 | $0.56 |
Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.
Related models
Babbage 002OpenAI · $0.34 / 1MChatGPT-4o LatestOpenAI · $2.75 / 1MChatGPT Image LatestOpenAI · $5.25 / 1MCodex Auto ReviewOpenAI · $0.09 / 1MCodex MiniOpenAI · $1.95 / 1MDALL·E 2OpenAI · $36.60 / 1MDavinci 002OpenAI · $2.00 / 1MGPT-3.5OpenAI · $1.11 / 1MGPT-3.5 TurboOpenAI · $0.66 / 1MGPT-3.5 TurboOpenAI · $0.59 / 1MGPT-3.5 TurboOpenAI · $0.50 / 1MGPT-3.5 Turbo 16KOpenAI · $3.00 / 1M
GPT-OSS 20B — frequently asked questions
- How much does GPT-OSS 20B cost?
- GPT-OSS 20B is available on the free tier at no token cost — create an API key and start building. Paid plans add higher rate limits.
- What is the context window of GPT-OSS 20B?
- GPT-OSS 20B supports a context window of up to 131K tokens. It can return up to 33K tokens in a single response.
- What can GPT-OSS 20B do?
- GPT-OSS 20B supports Tool calling, Reasoning.
- Is GPT-OSS 20B free to use?
- Yes — GPT-OSS 20B is on the free tier. You can use it with an Api.Airforce API key at no cost.
- How do I use GPT-OSS 20B via the API?
- GPT-OSS 20B is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID gpt-oss-20b with your Api.Airforce API key.
- Who makes GPT-OSS 20B?
- GPT-OSS 20B is OpenAI's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.
Loading live metrics…
Loading live metrics…
Loading live metrics…
Use GPT-OSS 20B via the API
OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass gpt-oss-20b as the model.
cURL
curl https://api.airforce/v1/chat/completions \
-H "Authorization: Bearer $AIRFORCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-20b",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Python
from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
model="gpt-oss-20b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
model: "gpt-oss-20b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);