Back to all models
essentialai
essentialaiEssentialAI: Rnj 1 Instruct
Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance across multiple programming languages, tool-use workflows, and agentic execution environments (e.g., mini-SWE-agent).
essentialai/rnj-1-instruct
Context Size
32.768K
Input Price
922.5 Ks/M
Output Price
922.5 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerOther
Provider Context32.768K tokens
ModeratedNo