Getting Started
Supported Models
Getting Started
Supported Models
Perplexity Sonar Models
| Model | Parameter Count | Context Length | Model Type |
|---|---|---|---|
llama-3.1-sonar-small-128k-online | 8B | 127,072 | Chat Completion |
llama-3.1-sonar-large-128k-online | 70B | 127,072 | Chat Completion |
llama-3.1-sonar-huge-128k-online | 405B | 127,072 | Chat Completion |
The search subsystem of the Online LLMs do not attend to the system prompt. You can use the system prompt to provide instructions related to style, tone, and language of the response.
Beta Access: The Online LLMs have some features in closed beta - to request access to them, please fill out this form.
Perplexity Chat Models
| Model | Parameter Count | Context Length | Model Type |
|---|---|---|---|
llama-3.1-sonar-small-128k-chat | 8B | 127,072 | Chat Completion |
llama-3.1-sonar-large-128k-chat | 70B | 127,072 | Chat Completion |
Open-Source Models
Where possible, we try to match the Hugging Face implementation.
| Model | Parameter Count | Context Length | Model Type |
|---|---|---|---|
llama-3.1-8b-instruct | 8B | 131,072 | Chat Completion |
llama-3.1-70b-instruct | 70B | 131,072 | Chat Completion |
Special Tokens
We do not raise any exceptions if your chat inputs contain messages with special tokens. If avoiding prompt injections is a concern for your use case, it is recommended that you check for special tokens prior to calling the API. For more details, read Meta’s recommendations for Llama.