Paid Models
The pricing for different providers and models varies depending on the specific model and usage requirements. Here's an overview of different providers and models for both the large language models and embeddings:
Embedding Models
Embedding models are used to convert text data into numerical representations called embeddings. These embeddings capture the semantic meaning and relationships between different pieces of text. When the documents/ directory is updated, the content is sent to the embedding API. The resulting embeddings are saved to the cache/ directory, allowing the AI to find relevant context efficiently without reprocessing or making new API requests for each query.
| Platform | Model Name | MTEB | Embedding Dimensions | API Price (per 1K tokens) |
|---|---|---|---|---|
64.59 | 3072 | Usage: $0.00013 | ||
62.26 | 1536 | Usage: $0.00002 | ||
60.99 | 1536 | Usage: $0.0001 |
Large Language Models
Large Language Models (LLMs) are powerful AI models that can understand and generate human-like text based on the input they receive. In ServerAssistantAI, when a user asks a question, the system retrieves relevant cached context from the embedding API results. This context, along with the user's question, is sent to the LLM to generate accurate and context-aware responses.
| Platform | Model Name | ELO | Speed (tokens per second) | API Price (per 1K tokens) |
|---|---|---|---|---|
1337 | 49.97 TPS | Input: $0.005 Output: $0.015 | ||
1272 | 166 TPS | Input: $0.00015 Output: $0.0006 | ||
1269 | 113.28 TPS | Input: $0.003 Output: $0.015 | ||
1260 | 57.2 TPS | Input: $0.0035 Output: $0.0105 | ||
1257 | 38.90 TPS | Input: $0.03 Output: $0.06 | ||
1248 | 25.51 TPS | Input: $0.015 Output: $0.075 | ||
1227 | 133.3 TPS | Input: $0.00035 Output: $0.00105 | ||
1179 | 214.95 TPS | Input: $0.00025 Output: $0.00125 | ||
1106 | 53.07 TPS | Input: $0.0005 Output: $0.0015 |
Last updated