DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
Context window on the 2026-08-19 OpenRouter row: 131,072 tokens.
Max completion tokens on that row: 65,536.
Input / output on that row: $0.07 / $0.30 per 1M tokens.
Architecture fields: text->text · GPT.
Hugging Face id on that row: openai/gpt-oss-safeguard-20b.
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.
When you want the 2025-10-29 catalog SKU, not a later rename.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: GPT-5.6 Sol, 73% ±3% Pass@1 at max on the DeepSWE official board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Official weights id on the 2026-08-19 OpenRouter row: openai/gpt-oss-safeguard-20b. Community GGUF is a quant, not a second Continuum card.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
usedStorage and the sum of .safetensors sizes can differ (LFS pointers, non-shard files, duplicate copies). Cited separately. Source: recursive tree API, 2026-08-19.
| Path | Bytes |
|---|---|
model-00000-of-00002.safetensors | 4,792,272,488 |
model-00001-of-00002.safetensors | 4,798,702,184 |
model-00002-of-00002.safetensors | 4,170,342,232 |
tokenizer.json | 27,868,174 |
model.safetensors.index.json | 36,355 |
chat_template.json | 17,461 |
chat_template.jinja | 16,663 |
LICENSE | 11,358 |
tokenizer_config.json | 4,200 |
README.md | 4,031 |
config.json | 1,806 |
.gitattributes | 1,570 |
USAGE_POLICY | 236 |
generation_config.json | 165 |
special_tokens_map.json | 98 |
All 15 files the tree API returned are listed: every one of the 3 safetensor shards plus 12 other files. Files tab: https://huggingface.co/openai/gpt-oss-safeguard-20b/tree/main.
OpenRouter slug openai/gpt-oss-safeguard-20b on the 2026-08-19 catalog.
First party: https://platform.openai.com/docs/models.
Not on the Continuum host list fetched 2026-08-19.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
OpenRouter 2026-08-19: $0.07 in / $0.30 out per 1M tokens. Context 131,072 in / 65,536 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id openai/gpt-oss-safeguard-20b; context 131072; created 1761752836; $0.07 / $0.30 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id openai/gpt-oss-safeguard-20b, context 131,072 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 116,420 | Hugging Face API openai/gpt-oss-safeguard-20b | 2026-08-19 |
| HF safetensors.total: 21,511,953,984 stored tensors; HF API usedStorage 13,789,185,078 bytes; created 2025-09-18T18:51:08.000Z; HF tensors BF16 + U8 | Hugging Face API openai/gpt-oss-safeguard-20b | 2026-08-19 |
| 3 safetensor shards; shard bytes 13,761,316,904; tree files 15 | Hugging Face tree API openai/gpt-oss-safeguard-20b | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through OpenAI's model family with GPT-5 Pro.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. Use the first-party API or the OpenRouter slug openai/gpt-oss-safeguard-20b.