GPT-OSS-Safeguard-20b API pricing
4 providers serve GPT-OSS-Safeguard-20b. GPT-OSS-Safeguard-20b is a proprietary API model, up to 131K context. Prices below are per 1M tokens, cheapest input first.
Refreshed 2026-08-23 · list prices from provider APIs| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context | |
|---|---|---|---|---|---|
| AWS Bedrock | $0.070 | $0.200output floor | - | 128K | Use |
| Groq | $0.075 | $0.300 | $0.037 | 131K | Use |
| OpenRouter marketplace quote | $0.075 | $0.300 | $0.037 | 131K | Use |
| Fireworks AI | $0.500 | $0.500 | - | 131K | Use |
The cheapest way to run GPT-OSS-Safeguard-20b
On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $10.90/month, at AWS Bedrock. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.
Your actual monthly cost
Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.
Related models
| Model | Cheapest in $/1M | Cheapest out $/1M | Providers |
|---|---|---|---|
| GPT-OSS 120B | $0.050 | $0.250 | 20 |
| GPT-OSS 20B | $0.015 | $0.070 | 14 |
| GPT-5 | $1.25 | $10.00 | 8 |
| GPT-5 Mini | $0.250 | $1.20 | 7 |
| GPT-5 Nano | $0.050 | $0.400 | 7 |
| GPT-4o | $2.50 | $10.00 | 6 |
FAQ
What is the cheapest API for GPT-OSS-Safeguard-20b?
As of 2026-08-23, the lowest input price for GPT-OSS-Safeguard-20b is AWS Bedrock at $0.070 per 1M input tokens. The lowest output price is AWS Bedrock at $0.200 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Groq at $0.075, a 7% difference.
← All models · GPU rental prices · Breakeven calculator · Get this data as JSON