EssentialAI: Rnj 1 Instruct reasoning

openrouter
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).

Capabilities

Context Window 32k tokens
Max Output 0 tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.15
Output $0.15
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings