All Models
RNJ-1 Instruct 8B
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).
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 NanoGPT | essentialai/rnj-1-instruct | $0.15/MTok | $0.15/MTok | 128K | 8.2K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output