GPT-OSS 120B
o200k_harmony
Structural tokenization analysis engine. Optimized for GPT-OSS 120B inputs. Calibrate context windows and compute precise API economics in real-time.
Context
128k
Type
LLM
Encoding
o 200k harmony
CH44
WORD9
ENCODINGo200k_harmony
// HAPPYTOKENIZER: WAITING FOR INPUT STREAM
Quick Answers
What is the GPT-OSS 120B token limit?
GPT-OSS 120B supports a 128,000 token context window. Paste your text above to see how much of that window your prompt fills.
What tokenizer does GPT-OSS 120B use?
GPT-OSS 120B uses the o200k_harmony encoding (OpenAI open-weight models). This page counts tokens with the vendor's real vocabulary, so the numbers match what the API sees.
How much does GPT-OSS 120B cost per million tokens?
GPT-OSS 120B costs $2.50 per million input tokens and $10.00 per million output tokens, with cached input at $1.25 per million.
Model Insights
Modalities
InText
OutText
Supported Features
StreamingFunction CallingReasoning Tokens
Supported Endpoints
Chat CompletionsResponses
Cost Manifest
Input / 1M$2.50
Output / 1M$10.00
Cached Write$1.25
* Rates are estimated based on OpenAI standard tier. Actual billing may vary based on batch processing and enterprise agreements.
// Technical Specifications
- ARCHITECTURE ID
- gpt-oss-120b
- TOKEN ENCODING
- o200k_harmony
- MAX CONTEXT
- 128,000TOKENS