Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.00 |
| Output tokens | $2.00 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Palmyra X 002
The Palmyra X 002, crafted by Writer, stands as a proprietary large language model with an undisclosed architecture. Although specifics about its context and response lengths remain hidden, it is noted for its pricing strategy: $1.00 per million input tokens and $2.00 per million output tokens. While detailed performance metrics are scarce, it is recognized for being more cost-effective than models like GPT-4 and is notably 66.7% less expensive than Yi-Large. However, it is priced 300% higher than Mistral 7B Instruct and 11.1% more expensive than Llama 3.1 70b. Despite these cost comparisons, the model's full performance capabilities and architectural details remain largely unexplored.
Model Specs
Released2024-03-01
ArchitectureDecoder Only