gpt-oss-20b
OpenAIReleased Aug 5, 2025
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...
- Context window
- 131K tokens
- Input
- text
- Output
- text
- Tokenizer
- GPT
- Knowledge cutoff
- Jun 30, 2024
- Released
- Aug 5, 2025
- Reasoning
- always on
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.029 | $0.0009 | $0.030 |
| Output | $0.140 | $0.0042 | $0.144 |
Benchmarks
Artificial Analysis
- Intelligence index
- 14.9
- Coding index
- 20.7
- Agentic index
- 3.1
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| Data vizmodels | 978 | 39.7% | #92 |
| Websitesmodels | 895 | 27.9% | #107 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-oss-20b.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-oss-20b",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="openai/gpt-oss-20b",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_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);Questions
- How much does gpt-oss-20b cost via API?
- Through OpenKey, gpt-oss-20b costs $0.030 per 1M input tokens and $0.144 per 1M output tokens. That is the provider price ($0.029 / $0.140) plus a flat 3% fee — nothing else.
- What is gpt-oss-20b's context window?
- gpt-oss-20b accepts up to 131K tokens of context.
- Is gpt-oss-20b OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-oss-20b" using any OpenAI SDK — only the base URL and API key change.
- What inputs does gpt-oss-20b support?
- gpt-oss-20b accepts text input and produces text output. Its knowledge cutoff is Jun 30, 2024.
More from OpenAI
All OpenAI models →GPT Chat Latest
GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...
ctx 400Kin $5.15out $30.90
OpenAI GPT Latest
This model always redirects to the latest model in the OpenAI GPT family.
ctx 1.1Min $5.15out $30.90
OpenAI GPT Mini Latest
This model always redirects to the latest model in the OpenAI GPT Mini family.
ctx 400Kin $0.772out $4.63
GPT-5.5
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
ctx 1.1Min $5.15out $30.90