Context
131K
Max output
66K
Input / 1M
$0.075
Output / 1M
$0.30
Modality
Chat
Cutoff
unknown
About this model
OpenAI's first open-weight reasoning model, specifically trained for safety classification tasks. 20B parameters, hosted on GroqCloud.
Best suited for
- Safety classification
- Content moderation
- Reasoning over policy guidelines
Capabilities
System prompt
Honours a dedicated system role, separate from the user turn.
Supported parameters
creativity_levelControls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.
max_tokensMax Tokens LimitSpecifies the maximum number of text units (tokens) allowed in a response, limiting its length.
probability_cutoffProbability Cutoff (Top P)Focuses on the most likely words based on a percentage of probability.
response_typeDefines the format or type of the generated response.
stopThis parameter tells the model to stop generating text when it reaches any of the specified sequences (like a word or punctuation)
streamSends the response in real-time as it's being generated.
Use this model
OpenAI-SDK compatible, with gateway fallback and routing across providers.
Other Groq models
| Model | Context | Max output | Input | Output | Capabilities |
|---|---|---|---|---|---|
| qwen/qwen3.8-27b Chat | 131K | 16K | $0.80 | $4.00 | Files, Tools, System prompt, Reasoning |
| openai/gpt-oss-20b Chat | 131K | 66K | $0.075 | $0.30 | Tools, System prompt |
| openai/gpt-oss-120b Chat | 131K | 66K | $0.15 | $0.60 | Tools, System prompt |
Pricing & provider details
Groq
groq/openai/gpt-oss-safeguard-20b
- Input · per 1M
- $0.075
- Output · per 1M
- $0.30
- Cached input · per 1M
- —
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Knowledge cutoff
- unknown
- Auto-router
- Not supported
Start building today
Route openai/gpt-oss-safeguard-20b — and every other model in the catalogue — through one endpoint, with failover built in.