docs: providers

Author: samestrin

docs/providers/ai21.md

@@ -46,14 +46,14 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `logprobs`: _Details not available, please refer to the LLM provider documentation._
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `n`: _Details not available, please refer to the LLM provider documentation._
-- `stop`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
+- `logprobs`: Includes the log probabilities of the most likely tokens, providing insights into the model's token selection process.
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `n`: Specifies the number of responses to generate for each input message. Note that costs are based on the number of generated tokens across all choices. Keeping n as 1 minimizes costs.
+- `stop`: Up to 4 sequences where the API will stop generating further tokens.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
 - `top_logprobs`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ### Features

docs/providers/ailayer.md

@@ -42,8 +42,8 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
 
 
 ## Getting an API Key

docs/providers/aimlapi.md

@@ -48,11 +48,11 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `frequency_penalty`: _Details not available, please refer to the LLM provider documentation._
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `frequency_penalty`: Penalizes new tokens based on their existing frequency in the text so far, reducing the likelihood of repeating the same line. Positive values reduce the frequency of tokens appearing in the generated text.
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ### Features

docs/providers/anthropic.md

@@ -42,16 +42,16 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `metadata`: _Details not available, please refer to the LLM provider documentation._
-- `stop_sequences`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `system`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
-- `tool_choice`: _Details not available, please refer to the LLM provider documentation._
-- `tools`: _Details not available, please refer to the LLM provider documentation._
-- `top_k`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `metadata`: Additional information about the input or environment that might influence the AI's response.
+- `stop_sequences`: Sequences that indicate to the model when to stop generating further tokens.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `system`: Defines the role and instructions for the system component of the AI interaction, guiding the overall behavior.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
+- `tool_choice`: Specifies which external tools the AI can use to assist in generating its response.
+- `tools`: A list of external tools available for the AI to use in generating responses.
+- `top_k`: The number of highest probability vocabulary tokens to keep for top-k sampling.
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ### Features

docs/providers/anyscale.md

@@ -48,10 +48,10 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `frequency_penalty`: _Details not available, please refer to the LLM provider documentation._
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `frequency_penalty`: Penalizes new tokens based on their existing frequency in the text so far, reducing the likelihood of repeating the same line. Positive values reduce the frequency of tokens appearing in the generated text.
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ## Features

docs/providers/cloudflareai.md

@@ -48,8 +48,8 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
 
 
 ### Features

docs/providers/cohere.md

@@ -53,20 +53,20 @@ The following parameters can be passed through `options`.
 - `conversation_id`: _Details not available, please refer to the LLM provider documentation._
 - `documents`: _Details not available, please refer to the LLM provider documentation._
 - `force_single_step`: _Details not available, please refer to the LLM provider documentation._
-- `frequency_penalty`: _Details not available, please refer to the LLM provider documentation._
+- `frequency_penalty`: Penalizes new tokens based on their existing frequency in the text so far, reducing the likelihood of repeating the same line. Positive values reduce the frequency of tokens appearing in the generated text.
 - `k`: _Details not available, please refer to the LLM provider documentation._
 - `max_input_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
 - `p`: _Details not available, please refer to the LLM provider documentation._
 - `preamble`: _Details not available, please refer to the LLM provider documentation._
-- `presence_penalty`: _Details not available, please refer to the LLM provider documentation._
+- `presence_penalty`: Penalizes new tokens based on whether they appear in the text so far, encouraging the model to talk about new topics. Positive values increase the likelihood of new tokens appearing in the generated text.
 - `prompt_truncation`: _Details not available, please refer to the LLM provider documentation._
-- `seed`: _Details not available, please refer to the LLM provider documentation._
-- `stop_sequences`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
+- `seed`: A random seed for reproducibility. If specified, the system will attempt to sample deterministically, ensuring repeated requests with the same seed and parameters return the same result. Determinism is not guaranteed.
+- `stop_sequences`: Sequences that indicate to the model when to stop generating further tokens.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
 - `tool_results`: _Details not available, please refer to the LLM provider documentation._
-- `tools`: _Details not available, please refer to the LLM provider documentation._
+- `tools`: A list of external tools available for the AI to use in generating responses.
 
 
 ### Features

docs/providers/corcel.md

@@ -42,10 +42,10 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ### Features

docs/providers/deepinfra.md

@@ -1,4 +1,4 @@
-![DeepInfra](https://deepinfra.com/deepinfra-logo-512.webp)
+![DeepInfra](https://repository-images.githubusercontent.com/575606070/57777f22-77f7-469a-8749-3f82398d28b1)
 
 # [DeepInfra](https://deepinfra.com)
 
@@ -48,18 +48,18 @@ The following model aliases are provided for this provider.
 
 The following parameters can be passed through `options`.
 
-- `echo`: _Details not available, please refer to the LLM provider documentation._
-- `frequency_penalty`: _Details not available, please refer to the LLM provider documentation._
-- `max_tokens`: _Details not available, please refer to the LLM provider documentation._
-- `n`: _Details not available, please refer to the LLM provider documentation._
-- `presence_penalty`: _Details not available, please refer to the LLM provider documentation._
-- `response_format`: _Details not available, please refer to the LLM provider documentation._
-- `stop`: _Details not available, please refer to the LLM provider documentation._
-- `stream`: _Details not available, please refer to the LLM provider documentation._
-- `temperature`: _Details not available, please refer to the LLM provider documentation._
-- `tool_choice`: _Details not available, please refer to the LLM provider documentation._
-- `tools`: _Details not available, please refer to the LLM provider documentation._
-- `top_p`: _Details not available, please refer to the LLM provider documentation._
+- `echo`: If set to true, the input prompt is echoed back in the output.
+- `frequency_penalty`: Penalizes new tokens based on their existing frequency in the text so far, reducing the likelihood of repeating the same line. Positive values reduce the frequency of tokens appearing in the generated text.
+- `max_tokens`: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
+- `n`: Specifies the number of responses to generate for each input message. Note that costs are based on the number of generated tokens across all choices. Keeping n as 1 minimizes costs.
+- `presence_penalty`: Penalizes new tokens based on whether they appear in the text so far, encouraging the model to talk about new topics. Positive values increase the likelihood of new tokens appearing in the generated text.
+- `response_format`: Defines the format of the AI's response. Setting this to { "type": "json_object" } enables JSON mode, ensuring the message generated by the model is valid JSON.
+- `stop`: Up to 4 sequences where the API will stop generating further tokens.
+- `stream`: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
+- `temperature`: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
+- `tool_choice`: Specifies which external tools the AI can use to assist in generating its response.
+- `tools`: A list of external tools available for the AI to use in generating responses.
+- `top_p`: Controls the cumulative probability of token selections for nucleus sampling. It limits the tokens to the smallest set whose cumulative probability exceeds the threshold. It is recommended to alter this or temperature, but not both.
 
 
 ### Features
@@ -82,12 +82,3 @@ To get an API key, first create a DeepInfra account, then visit the link below.
 ## [DeepInfra Documentation](https://deepinfra.com/docs/)
 
 [DeepInfra documentation](https://deepinfra.com/docs/) is available [here](https://deepinfra.com/docs/).
-
-
-## [DeepInfra X](https://www.x.com/DeepInfra)
-
-![@DeepInfra](https://pbs.twimg.com/profile_images/1798110641414443008/XP8gyBaY_normal.jpg)
-
-[@DeepInfra](https://www.x.com/DeepInfra)
-
-