LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT OSS Safeguard 20B

openai·openai/gpt-oss-safeguard-20b·BETA·Open weights·gpt-oss series·Classify / Safety
Safety model for policy screening, moderation, and risk-aware routing workflows

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Amazon BedrockCloud
$0.07 / $0.20
Blended $0.10 · 1.1× spread
Context
131,072
Output limit
65,536
Knowledge cutoff
—
Released / updated
2025-10-29 / 2025-10-29
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

GPT OSS Safeguard 20B by openai is offered by 12 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Amazon Bedrock at $0.07 / $0.20 per 1M.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 4,096 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Available at 12 providers12 with public prices

  • ProviderInput / Output
  • Amazon BedrockCloud
    openai.gpt-oss-safeguard-20b
    $0.07 / $0.20
    Context 128,000 ⚠Output limit 16,384
  • Merge GatewayGateway
    $0.07 / $0.20
    Cache read $0Context 4,096 ⚠Output limit 4,096
  • Eden AIGateway
    amazon/openai.gpt-oss-safeguard-20b
    $0.07 / $0.20
    Context 128,000 ⚠Output limit 128,000
  • Eden AIGateway
    amazon/openai.gpt-oss-safeguard-20b@us
    $0.07 / $0.20
    Context 128,000 ⚠Output limit 128,000
  • Kilo GatewayGateway
    $0.07 / $0.20
    Context 131,072Output limit 65,536
  • Vercel AI GatewayCloud
    $0.07 / $0.20
    Context 128,000 ⚠Output limit 16,000
  • LowRouterGateway
    $0.08 / $0.24
    Context 131,072Output limit 131,072
  • NanoGPTGateway
    $0.075 / $0.30
    Context 131,072Output limit 65,536
  • OpenRouterGateway
    $0.075 / $0.30
    Cache read $0.038Context 131,072Output limit 65,536
  • GroqCloud
    $0.075 / $0.30
    Cache read $0.038Context 131,072Output limit 65,536beta
  • Eden AIGateway
    $0.075 / $0.30
    Cache read $0.038Context 131,072Output limit 131,072
  • AI/ML APIGateway
    $0.079 / $0.32
    Cache read $0.04Context 131,072Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Amazon Bedrock
openai.gpt-oss-safeguard-20b
Cloud$0.07$0.20——128,000 ⚠16,384
Merge GatewayGateway$0.07$0.20$0$04,096 ⚠4,096
Eden AI
amazon/openai.gpt-oss-safeguard-20b
Gateway$0.07$0.20——128,000 ⚠128,000
Eden AI
amazon/openai.gpt-oss-safeguard-20b@us
Gateway$0.07$0.20——128,000 ⚠128,000
Kilo GatewayGateway$0.07$0.20——131,07265,536
Vercel AI GatewayCloud$0.07$0.20——128,000 ⚠16,000
LowRouterGateway$0.08$0.24——131,072131,072
NanoGPTGateway$0.075$0.30——131,07265,536
OpenRouterGateway$0.075$0.30$0.038—131,07265,536
GroqCloud$0.075$0.30$0.038—131,07265,536beta
Eden AIGateway$0.075$0.30$0.038—131,072131,072
AI/ML APIGateway$0.079$0.32$0.04—131,07265,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = high

2 / 12 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Merge Gateway$15.60
2Amazon Bedrock$24.00
3Eden AI$24.00
4Eden AI$24.00
5Kilo Gateway$24.00
6Vercel AI Gateway$24.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.10

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

GPT OSS Safeguard 120Bsame series—GPT OSS 120Bsame series—GPT OSS 20Bsame series—GPT Sol Latestsame lab—
Data partly from models.dev (MIT)