Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

OpenAI · Chat · openai/gpt-oss-20b

gpt-oss-20b

Short answer

gpt-oss-20b is listed by OpenAI and is marked new, not yet reviewed. gpt-oss-20b is listed at $0.018 input and $0.09 output per million tokens, with a 131,072-token context window. In: text. Out: text. Tools: Yes. Open weights: Yes.

New, not yet reviewed

Tools: Yes.

Facts

Facts for gpt-oss-20b. OpenRouter models API, checked 20 Nov 2026.
FactValueSource
Release date 5 Aug 2025 OpenRouter field created. This is the listing date the feed publishes. Checked 20 Nov 2026.
Context window 131,072 tokens OpenRouter field context_length. Checked 20 Nov 2026.
Max output 117,964 tokens OpenRouter field top_provider.max_completion_tokens. Checked 20 Nov 2026.
Input price $0.018 per million tokens. Published per-token rate 0.000000018. OpenRouter field pricing.prompt, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Output price $0.09 per million tokens. Published per-token rate 0.00000009. OpenRouter field pricing.completion, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Batch input price $0.024 per million tokens Sibling OpenRouter id ending in :batch, field pricing.prompt. Checked 20 Nov 2026.
Batch output price $0.112 per million tokens Sibling OpenRouter id ending in :batch, field pricing.completion. Checked 20 Nov 2026.
Input modalities text OpenRouter field architecture.input_modalities. Checked 20 Nov 2026.
Output modalities text OpenRouter field architecture.output_modalities. Checked 20 Nov 2026.
Tools Yes OpenRouter field supported_parameters contains tools. Checked 20 Nov 2026.
Open weights Yes — openai/gpt-oss-20b OpenRouter field hugging_face_id. Empty means no public weights id is listed, which is not a legal opinion. Checked 20 Nov 2026.
Knowledge cutoff 2024-06-30 OpenRouter field knowledge_cutoff. Checked 20 Nov 2026.
Reasoning Supported, and the feed marks it required OpenRouter field reasoning. Missing means unknown, not unsupported. Checked 20 Nov 2026.
Other published prices input_cache_read: 0.000000009 USD Other OpenRouter pricing fields, shown raw. The documented unit is USD per token, request, or unit — not converted to per million. Checked 20 Nov 2026.

A $0 token price does not mean the model is free to use. Another published price field is non-zero and may be the one you are billed on.

Listing blurb

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...

Listing blurb, via OpenRouter. It is their text, not a measurement by this site.

No third-party index was included for this model in the feed. The Best Model For does not fill that gap.

Questions

How much does gpt-oss-20b cost?

gpt-oss-20b is listed at $0.018 input and $0.09 output per million tokens, with a 131,072-token context window. A batch route is listed at $0.024 input and $0.112 output per million tokens. Other price fields, if any, are on this page and are not converted.

Does gpt-oss-20b have open weights?

The feed lists a Hugging Face id: openai/gpt-oss-20b. That is what The Best Model For means by open weights.

What is gpt-oss-20b good for?

The Best Model For has not reviewed this model. The safe default is a small sample of the real task, not a production queue.