CompactifAI: Models Intelligence, Performance & Price
Analysis of CompactifAI'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 CompactifAI for your use-case.
Most Intelligent
Intelligence index
Total 3 models
Fastest
Output speed
Total 3 models
Lowest Price
Blended price (per 1M tokens)
Total 3 models
CompactifAI offers 3 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 CompactifAI are Qwen3.6 27B (38), Qwen3.6 27B (31), and Mistral Small 3.1 (15).
- For output speed, the fastest models are Qwen3.6 27B (192 t/s), Qwen3.6 27B (191 t/s), and Mistral Small 3.1 (76 t/s).
- For latency, Qwen3.6 27B (1.29s), Mistral Small 3.1 (1.53s), and Qwen3.6 27B (30.94s) offer the lowest time to first answer token.
- For pricing, Mistral Small 3.1 ($0.12), Qwen3.6 27B ($0.23), and Qwen3.6 27B ($0.23) offer the lowest blended prices per 1M tokens.
- For context window size, Qwen3.6 27B (262k), Qwen3.6 27B (262k), and Mistral Small 3.1 (128k) support the largest context windows on CompactifAI.
- Qwen3.6 27B offers the best combination of intelligence and speed. For cost optimization, Mistral Small 3.1 provides the most competitive pricing.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index 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
Latency: Time To First Answer 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 CompactifAI
CompactifAI offers 3 models that we track: Qwen3.6 27B, Qwen3.6 27B, and Mistral Small 3.1.
The most intelligent model available on CompactifAI is Qwen3.6 27B with an Intelligence Index score of 38.
The fastest model on CompactifAI by output speed is Qwen3.6 27B at 191.9 tokens per second.
The model with the lowest time to first answer token on CompactifAI is Qwen3.6 27B at 1.29s. Lower latency means faster initial response time.
The most affordable model on CompactifAI by blended price is Mistral Small 3.1 at $0.12 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on CompactifAI vary up to 2x across models, from $0.12 per 1M tokens for Mistral Small 3.1 to $0.23 per 1M tokens for Qwen3.6 27B.
Yes, CompactifAI offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 3 models on CompactifAI support JSON mode for structured output.
2 of 3 models on CompactifAI support function calling (tool use).
Yes, CompactifAI offers 1 reasoning model: Qwen3.6 27B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 3 models on CompactifAI 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 CompactifAI, 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.