Inflection: Inflection 3 Pi

Text input Text output
Author's Description

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi has been trained to mirror your tone and style, if you use more emojis, so will Pi! Try experimenting with various prompts and conversation styles.

Key Specifications
Cost
$$$$$
Context
8K
Released
Oct 10, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Top P Temperature Max Tokens
Performance Summary

Inflection 3 Pi, created on October 10, 2024, consistently ranks among the fastest models available, demonstrating exceptional speed performance across various benchmarks. It also offers highly competitive pricing, making it a cost-effective solution. The model exhibits strong reliability, with a 92nd percentile ranking, indicating consistent delivery of usable responses with minimal technical issues. In terms of benchmark performance, Inflection 3 Pi excels in classification tasks, achieving 97.0% accuracy in Email Classification, and demonstrates strong ethical reasoning with 98.0% accuracy in the Ethics benchmark. Its Reasoning capabilities are solid at 60.0% accuracy. However, a significant weakness is observed in Instruction Following, where it scored 0.0% accuracy, suggesting a need for improvement in handling complex, multi-step directives. Its Coding performance is modest at 56.0% accuracy, and General Knowledge is fair at 88.5%. While its speed and cost are standout strengths, the model's ability to precisely follow instructions requires substantial development.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2.5
Completion $10

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Inflection
Inflection | inflection/inflection-3-pi 8K $2.5 / 1M tokens $10 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by inflection