OpenAI: gpt-oss-20b (batch)openai
Bottom Line
OpenAI: gpt-oss-20b (batch): $0.02/1M input, $0.11/1M output, 131K context. 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...
API Pricing (per 1M tokens)
| Input | $0.02 |
| Output | $0.11 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.05 |
Specs & Performance
| Context Length | 131K |
| Max Output | 118K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from openai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the OpenAI: gpt-oss-20b (batch) API cost?
OpenAI: gpt-oss-20b (batch) costs $0.02/1M input tokens and $0.11/1M output tokens. Blended cost at a 3:1 ratio is about $0.05/1M tokens.
What is the context window of OpenAI: gpt-oss-20b (batch)?
OpenAI: gpt-oss-20b (batch) supports a 131K token context window with up to 118K output tokens.
Is OpenAI: gpt-oss-20b (batch) worth it?
OpenAI: gpt-oss-20b (batch) has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.