GPT-OSS 120B
OpenAI's Apache-2.0 open-weight 120B reasoning model for high-volume tool use.
- Modalities
- IntextOuttext
- Input / output
- $0.35 / $0.75USD per 1M tokens
- Context
- 131K
- Providers
- 20 live
- Released
- Aug 5, 2025
- Knowledge cutoff
- Jun 2024
Playground
Preparing playground
API
POST/api/v1/chat/completionsOpenAI-compatible
gpt-oss-120b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-120b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceresponse_formatreasoningreasoning_effort
Pricing
- Input
- $0.35/M tokens
- Cached input
- $0.035/M tokens
- Output
- $0.75/M tokens
Published USD rates. Actual cost depends on input, output, cache usage and request options.
Further reading
- We ran the same 3 prompts on 12 AI models
Unedited answers, latency and price for every model, measured through the NinjaChat API in September 2026.