Get started

gpt-oss-safeguard-20b

Sold by 2 sellers, timed at 438 tok/s, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/OpenAI/gpt-oss-safeguard-20bUSD per 1M tokens · as OpenRouter routes it
openai/gpt-oss-safeguard-20bOpenAI · base listing · GPT tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.075per 1M tokens
Output$0.30per 1M tokens
Cached input$0.0375per 1M tokens
Context131k131,072 tokens
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorOpenAI
Listed
Context131,072 tokens
Max output65,536 tokens
Modalitiestext → text
TokenizerGPT
Reasoningalways on
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licenceapache-2.0
Parameters21.5B · 21,511,953,984 declared
Model classGptOssForCausalLM
Downloadnot gated
Published

What sellers charge

2 sellers · 1.07x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.07 at Amazon Bedrock to $0.075 at Groq. 1 seller undercuts the $0.075 listed; 0 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

8,747 requests · 2 endpoints · 30-minute window
Throughput438 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token244msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread206 to 571The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

2 priced · 2 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock/us-east-2$0.07$0.20not listednot declared118k206 tok/s160352ms3,185 req100%
  2. Groqgroq · listed$0.075$0.30$0.0375not declared66k571 tok/s286182ms5,562 req69.79%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 1 of the 2 timed routes are slower than it, and the middle route runs at 389 tok/s. The widest median-to-p90 gap is Groq's, 2x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 1 of the 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Groq at 48.75% on 20 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

12 parameters · 2 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. stopevery seller
  5. temperatureevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. top_pevery seller
  9. response_format1 of 2not Amazon Bedrock
  10. seed1 of 2not Amazon Bedrock
  11. structured_outputs1 of 2not Amazon Bedrock
  12. top_k1 of 2not Groq

8 of these 12 are accepted by every one of the 2 sellers that publish a list; the other 4 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.131 per million tokens, 3 in to 1 out: cheaper than 295 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board
Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed gpt-oss-safeguard-20b on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for gpt-oss-safeguard-20b under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.