InferIndex
Language, English, EN
Account

ModelsOpenAIgpt-oss-safeguard-20b

gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b128k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.131
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.131
Offers
11
Providers
6

Cheapest right now

Amazon Bedrock

via Vercel AI GatewayThe provider's published policy: prompts are not used for training.

128k

$0.103 blended / 1M tokens

No change7D
in
$0.07
out
$0.20
Cached input
–

gpt-oss-safeguard-20b costs from $0.103 per million tokens (at a 3:1 input:output mix): the cheapest of 4 comparable offers, at Amazon Bedrock, checked on ; 11 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (7)

  • $0.103 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.103 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.131 · Groq via Eden AI · cannot be designated the cheapest
  • $0.131 · Groq via Kilo Gateway · cannot be designated the cheapest
  • $0.131 · Glama via Glama · cannot be designated the cheapest
  • $0.131 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.131 · Groq via OpenRouter · another route of the same provider

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.103, Amazon Bedrock–
2026-10-03$0.103, Amazon Bedrock–
2026-10-04$0.103, Amazon Bedrock–
2026-10-05$0.103, Amazon Bedrock–
2026-10-06$0.103, Amazon Bedrock–
2026-10-07$0.103, Amazon Bedrock–
2026-10-08$0.103, Amazon Bedrock–
2026-10-09$0.103, Amazon Bedrock–
2026-10-10$0.103, Amazon Bedrock–
2026-10-11$0.103, Amazon Bedrock–
2026-10-12$0.103, Amazon Bedrock–
2026-10-13$0.103, Amazon Bedrock–
2026-10-14$0.103, Amazon Bedrock–
2026-10-15$0.103, Amazon Bedrock–
2026-10-16$0.103, Amazon Bedrock–
2026-10-17$0.103, Amazon Bedrock–
2026-10-18$0.103, Amazon Bedrock–
2026-10-19$0.103, Amazon Bedrock–
2026-10-20$0.103, Amazon Bedrock–
2026-10-21$0.103, Amazon Bedrock–
2026-10-22$0.103, Amazon Bedrock–
2026-10-23$0.103, Amazon Bedrock–
2026-10-24$0.103, Amazon Bedrock–
2026-10-25$0.103, Amazon Bedrock–
2026-10-26$0.103, Amazon Bedrock–
2026-10-27$0.103, Amazon Bedrock–
2026-10-28$0.103, Amazon Bedrock–
2026-10-29$0.103, Amazon Bedrock–
2026-10-30$0.103, Amazon Bedrock–
2026-10-31$0.103, Amazon Bedrock–

Cheapest offer

Offers

11 of 11 offers

Offers for gpt-oss-safeguard-20b, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 Amazon Bedrockvia Eden AI 0.07  0.20 0.103 128k Unverified. No public page for this offer: listed, not designated cheapest
2 Amazon Bedrockvia Eden AI 0.07  0.20 0.103 128k United States Unverified. No public page for this offer: listed, not designated cheapest
3 Amazon Bedrockvia Vercel AI Gateway 0.07  0.20 0.103 128k
4 NanoGPT 0.075 0.30 0.131 128k
5 Featherless 0.075 0.30 0.131 33k
6 Groqvia Eden AI 0.075 0.30 0.131 131k Unverified. No public page for this offer: listed, not designated cheapest
7 Groqvia Kilo Gateway 0.075 0.30 0.131 131k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
8 Groqvia Vercel AI Gateway 0.075 0.30 0.131 131k
9 Glama 0.075 0.30 0.131 131k Unverified. No public page for this offer: listed, not designated cheapest
10 Nous Portal 0.075 0.30 0.131 131k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
11 Groqvia OpenRouter 0.075 0.30 0.131 131k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Amazon Bedrock$7.20per month
  2. NanoGPT$9.00per month+$1.80 vs the cheapest
  3. Featherless$9.00per month+$1.80 vs the cheapest

Host it yourself instead? See the break-even

Compare gpt-oss-safeguard-20b with

Related models

More from OpenAI

All OpenAI models

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=openai/gpt-oss-safeguard-20b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.