gpt-oss-20b (free) pricing
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... Below you will find 1 current row with input and output dollars per million. Right now the lowest input is $0.0000 and the lowest output is $0.0000.
Pricing across providers
Every row is a seller of gpt-oss-20b (free) with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.0000 | $0.0000 | — | — |
Input vs output · 1M tokens
Cost calculator
Pick any provider row and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for gpt-oss-20b (free).
Model specifications
Quick spec sheet for gpt-oss-20b (free) before you dive back into pricing. Reported under OpenAI.
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Aug 2025
- Primary provider
- OpenAI
- Model family
- N/A
Compare gpt-oss-20b (free)
Open a pair page to see gpt-oss-20b (free) next to another model with a shared provider matrix. 6 shortcuts below.
Locked
Compare with
Pick a model on both sides.
Popular gpt-oss-20b (free) comparisons
- gpt-oss-20b (free) vs GPT-4o
Compare pricing side by side
- gpt-oss-20b (free) vs GPT-4o mini
Compare pricing side by side
- gpt-oss-20b (free) vs o3
Compare pricing side by side
- gpt-oss-20b (free) vs Claude Sonnet 4.6
Compare pricing side by side
- gpt-oss-20b (free) vs Gemini 2.0 Flash
Compare pricing side by side
- gpt-oss-20b (free) vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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...
Also from OpenAI
Other models by OpenAI with live pricing in our catalog.