GPT-OSS 20B

Groq
Model weights

OpenAI's compact 20B open-weight reasoning model for ultra-fast agents and structured outputs.

Modalities
IntextOuttext
Input / output
$0.07 / $0.45USD per 1M tokens
Context
131K
Providers
4 live
Released
Aug 5, 2025
Knowledge cutoff
Jun 2024

Playground

Preparing playground

Providers

primary
emergency
emergency
emergency

API

POST/api/v1/chat/completionsOpenAI-compatible
gpt-oss-20b
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-20b",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceresponse_formatreasoningreasoning_effort

Pricing

Input
$0.075/M tokens
Cached input
$0.007/M tokens
Output
$0.45/M tokens

Published USD rates. Actual cost depends on input, output, cache usage and request options.