Public AI: Models Intelligence, Performance & Price
Analysis of Public AI's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Public AI for your use-case.
Most Intelligent
Apertus 70B InstructApertus 8B InstructIntelligence index
Total 2 models
Fastest
Apertus 8B InstructApertus 70B InstructOutput speed
Total 2 models
Lowest Price
Apertus 8B InstructApertus 70B InstructBlended price (per 1M tokens)
Total 2 models
Public AI offers 2 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Public AI are Apertus 70B Instruct (8), Apertus 8B Instruct (6).
- For output speed, the fastest models are Apertus 8B Instruct (136 t/s), Apertus 70B Instruct (62 t/s).
- For latency, Apertus 8B Instruct (2.13s), Apertus 70B Instruct (2.14s) offer the lowest time to first token.
- For pricing, Apertus 8B Instruct ($0.13), Apertus 70B Instruct ($1.34) offer the lowest blended prices per 1M tokens.
- For context window size, Apertus 70B Instruct (64k), Apertus 8B Instruct (64k) support the largest context windows on Public AI.
- Apertus 8B Instruct offers both the fastest output and best pricing, making it attractive for throughput-sensitive and cost-conscious applications. Apertus 70B Instruct leads in intelligence for tasks that require the highest quality.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Intelligence vs. Price
Context Window
Context Window
JSON Mode & Function Calling
Function (Tool) Calling & JSON Mode
| Models | Function calling | JSON Mode |
|---|---|---|
 Apertus 70B Instruct, Public AI | ||
| Apertus 8B Instruct, Public AI |
Pricing
Intelligence vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Key definitions
Frequently Asked Questions
Common questions about Public AI
Public AI offers 2 models that we track: Apertus 70B Instruct and Apertus 8B Instruct.
The most intelligent model available on Public AI is Apertus 70B Instruct with an Intelligence Index score of 8.
The fastest model on Public AI by output speed is Apertus 8B Instruct at 135.7 tokens per second.
The model with the lowest time to first token on Public AI is Apertus 8B Instruct at 2.13s. Lower latency means faster initial response time.
The most affordable model on Public AI by blended price is Apertus 8B Instruct at $0.13 per 1M tokens (3:1 input to output ratio).
Prices on Public AI vary up to 11x across models, from $0.13 per 1M tokens for Apertus 8B Instruct to $1.34 per 1M tokens for Apertus 70B Instruct.
Yes, Public AI offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 2 models on Public AI support JSON mode for structured output.
Yes, all 2 models on Public AI support function calling (tool use).
Yes, all 2 models on Public AI are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Public AI, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.