OpenAI: gpt-oss-safeguard-20b
budgetopenai/gpt-oss-safeguard-20b
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...
AA INDEXN/A
CONTEXT131K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED2 min ago
Input
$0.07 /M
Output
$0.30 /M
Blended (40/60)
$0.21 /M
Cost / IQ
N/A /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price. No AA score available for this model.
24h0%
7d0%
Price History
30-day view, daily close
Low: $0.18/M
High: $0.21/M
Average: $0.21/M
Pricing Variants
Cached Input
$0.04/M
50% cheaper than standard
Provider Comparison
1 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Groq | $0.07 | $0.30 | $0.21 | median |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)N/A (no AA score)
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #110 of 167 budget models
← YOU ARE HERE | OpenAI: gpt-oss-safeguard-20b
Data Sources
Source
Direct provider data
1 source · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/openai/gpt-oss-safeguard-20b
# Response (truncated)
{ "model_id": "openai/gpt-oss-safeguard-20b", "name": "OpenAI: gpt-oss-safeguard-20b", "blended_price_per_m": 0.21, "sit_adjusted_price": null }