OpenAI
gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
At a glance
- Input / 1M
- $0.02
- Output / 1M
- $0.09
- Context
- 131K
- Max output
- 33K
- Intelligence
- 10
- Released
- Aug 2025
Pricing
gpt-oss-20b API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.02 |
|---|---|
| Output tokensPer 1M tokens | $0.09 |
| Cached input (read)Per 1M tokens | $0.01 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.08
per 1,000 requests
Coding task
30K in, 4K out
$0.90
per 1,000 requests
Long document summary
150K in, 2K out
$2.88
per 1,000 requests
Benchmarks
gpt-oss-20b benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
10
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 131K tokens
- Max output
- 33K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- High, Medium, Low
- Release date
- August 5, 2025
- Knowledge cutoff
- June 30, 2024
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
gpt-oss-20b vs other models
See how gpt-oss-20b stacks up head to head on price, benchmarks, and features.
VS
gpt-oss-20b vs Gemini 2.5 Flash Lite
OpenAI vs Google
See comparisonVSgpt-oss-20b vs gpt-oss-120b
OpenAI vs OpenAI
See comparisonVS
gpt-oss-20b vs Mistral Nemo
OpenAI vs Mistral
See comparisonVSgpt-oss-20b vs GPT-5 Nano
OpenAI vs OpenAI
See comparisonVSgpt-oss-20b vs Llama 3.1 8B Instruct
OpenAI vs Meta
See comparisonVS
gpt-oss-20b vs Mercury 2.5
OpenAI vs Inception
See comparisonAlternatives
gpt-oss-20b alternatives
Similar models worth considering, and where each one has the edge.
Qwen
Qwen3.5-9B
OpenAI
GPT-5 Nano
NVIDIA
Nemotron 3.5 Lightning
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does gpt-oss-20b cost?
gpt-oss-20b costs $0.02 per 1M input tokens and $0.09 per 1M output tokens through the API. A typical chat message costs about $0.08 per 1,000 messages.
What is the context window of gpt-oss-20b?
gpt-oss-20b accepts up to 131K tokens of input and can write up to 33K tokens in a single response.
What is the best alternative to gpt-oss-20b?
Qwen3.5-9B from Qwen is a strong alternative. It offers: higher intelligence score, larger 262k context, accepts image and video.
Can I use gpt-oss-20b alongside other models?
Yes. Shortcut Chat sends one prompt to gpt-oss-20b and any other models you pick at the same time, so you can compare answers side by side.
Try gpt-oss-20b next to every other model.
Use gpt-oss-20b alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.