Home / Models / OpenAI / gpt-oss-safeguard-20b

gpt-oss-safeguard-20b pricing and routing profile

gpt-oss-safeguard-20b from OpenAI lists at $0.075 per million input tokens and $0.30 per million output tokens, with a 131,072-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.075
Output, per 1M tokens$0.30
Cached input, per 1M$0.0375
Context window131K
Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.048
Chat reply (2,000 in, 400 out)$0.27
Retrieval-augmented answer (8,000 in, 500 out)$0.75

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for gpt-oss-safeguard-20b. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below gpt-oss-safeguard-20b that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3 Coder 30B A3B Instruct$0.07 / $0.287%
Gemma 4 26B A4B $0.0675 / $0.22517%
Granite 4.2 8B$0.06 / $0.2519%
Nemotron 3 Nano 30B A3B$0.05 / $0.2033%
Llama 3.1 8B Instruct$0.05 / $0.0851%
Qwen3.7 Flash$0.03 / $0.1359%

Questions

How much does gpt-oss-safeguard-20b cost?

gpt-oss-safeguard-20b lists at $0.075 per million input tokens and $0.30 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.27 per 1,000 requests.

What is the context window of gpt-oss-safeguard-20b?

131,072 tokens.

Can a cheaper model replace gpt-oss-safeguard-20b?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match gpt-oss-safeguard-20b on one half of your requests and make at most three answers worse on the other.