Essentialai
EssentialAI: 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).
| Specifications | |
|---|---|
| Provider | Essentialai |
| Input pricing | $0.15/M tokens |
| Output pricing | $0.15/M tokens |
| Context length | 33K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Other |
| Content moderated | No |
| HuggingFace | EssentialAI/rnj-1-instruct |
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p