GPT OSS Safeguard 20B

openai· 2025-10-29· 131K ctx· apache-2.0

open weightsreasoning quant: unknown

spread (output)

1.5×

$0.200 – $0.300 · 10 providers

10 providers priced

Provider	Input	Output	Cache rd	Blended
Amazon Bedrock hyperscaler	$0.070	$0.200	—	$0.082^*
Eden AI relay router	$0.070	$0.200	—	$0.082^*
Eden AI relay router	$0.070	$0.200	—	$0.082^*
Merge Gateway unknown	$0.070	$0.200	$0	$0.037
Vercel AI Gateway unknown	$0.070	$0.200	—	$0.082^*
Kilo Gateway relay router	$0.075	$0.300	$0.037	$0.072
OpenRouter unknown	$0.075	$0.300	$0.037	$0.072
NanoGPT relay router	$0.075	$0.300	—	$0.095^*
Eden AI relay router	$0.075	$0.300	$0.037	$0.072
Groq unknown	$0.075	$0.300	—	$0.095^*

Cheapest (output)

Amazon Bedrock

$0.200 /M

opencode.json

{
  "provider": {
    "amazon-bedrock": {
      "npm": "@ai-sdk/amazon-bedrock",
      "models": {
        "openai.gpt-oss-safeguard-20b": {}
      }
    }
  }
}

Set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION, AWS_BEARER_TOKEN_BEDROCK in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.