GPT OSS Safeguard 20B
nano-gpt/openai/gpt-oss-safeguard-20b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.13
Blended $/1M (3:1)
$0.075
Input $/1M
$0.3
Output $/1M
$0.38
1M in + 1M out
—
Cache read $/1M
#1125 of 8,513
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GPT OSS Safeguard 20B” is offered by 6 providers — cheapest-effective first. Amazon Bedrock is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Amazon Bedrock | $0.07 | $0.2 | $0.10 | 128k |
| Merge Gateway | $0.07 | $0.2 | $0.10 | 4k |
| LowRouter | $0.08 | $0.24 | $0.12 | 131k |
| NanoGPT (this) | $0.075 | $0.3 | $0.13 | 131k |
| OpenRouter | $0.075 | $0.3 | $0.13 | 131k |
| Kilo Gateway | $0.075 | $0.3 | $0.13 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-safeguard-20b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):