Model ID used to generate the response.

The weight of the model, which determines its influence on the Confidence Score. Must match the weight strategy of the parent Model.

The output mode of the model, which determines how it's constrained to select from provided choices.

For non-reasoning LLMs, whether to enable synthetic reasoning to make the selection more thought-out. Requires output_mode of "json_schema" or "tool_call".

If set, and the LLM supports it, turns the vote into a probability distribution. This increases score quality by allowing the LLM to express uncertainty.

A list of messages to prepend to every request to this LLM. Useful for setting context or influencing behavior.

A list of messages to append to every request to this LLM. Useful for setting context or influencing behavior.

This setting aims to control the repetition of tokens based on how often they appear in the input. It tries to use less frequently those tokens that appear more in the input, proportional to how frequently they occur. Token penalty scales with the number of occurrences. Negative values will encourage token reuse.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

This setting aims to control the presence of tokens in the output. It tries to encourage the model to use tokens that are less present in the input, proportional to their presence in the input. Token presence scales with the number of occurrences. Negative values will encourage more diverse token usage.

Stop generation immediately if the model encounters any token specified in the stop array.

This setting influences the variety in the model’s responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.

This setting limits the model’s choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model’s responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

This sets the upper limit for the number of tokens the model can generate in response. It won’t produce more than this limit. The maximum value is the context length minus the prompt length.

Represents the minimum probability for a token to be considered, relative to the probability of the most likely token. (The value changes depending on the confidence level of the most probable token.) If your Min-P is set to 0.1, that means it will only allow for tokens that are at least 1/10th as probable as the best possible option.

OpenRouter provider preferences.

OpenRouter reasoning configuration.

Helps to reduce the repetition of tokens from the input. A higher value makes the model less likely to repeat tokens, but too high a value can make the output less coherent (often with run-on sentences that lack small words). Token penalty scales based on original token’s probability.

Consider only the top tokens with “sufficiently high” probabilities based on the probability of the most likely token. Think of it like a dynamic Top-P. A lower Top-A value focuses the choices based on the highest probability token but with a narrower scope. A higher Top-A value does not necessarily affect the creativity of the output, but rather refines the filtering process based on the maximum probability.

This limits the model’s choice of tokens at each step, making it choose from a smaller set. A value of 1 means the model will always pick the most likely next token, leading to predictable results. By default this setting is disabled, making the model to consider all choices.

Controls the verbosity and length of the model response. Lower values produce more concise responses, while higher values produce more detailed and comprehensive responses.

Fallback models. Will be tried in order if the first one fails.

The number of most similar training table entries to consider when computing the dynamic weight.

A base62 22-character unique identifier for the Score LLM. This is a hash of all parameters.

A base62 22-character unique identifier for the Multichat LLM. This is a hash of some parameters.

A base62 22-character unique identifier for the LLM's Training Table. This is a hash of some parameters. Only present with Training Table Weight.

The index of the Score LLM within the parent Score Model.

The index of the Multichat LLM within the parent Multichat Model.

The index of the Score LLM within the Training Table. Only present with Training Table Weight.

Model ID used to generate the response.

The weight of the model, which determines its influence on the Confidence Score. Must match the weight strategy of the parent Model.

The output mode of the model, which determines how it's constrained to select from provided choices.

For non-reasoning LLMs, whether to enable synthetic reasoning to make the selection more thought-out. Requires output_mode of "json_schema" or "tool_call".

If set, and the LLM supports it, turns the vote into a probability distribution. This increases score quality by allowing the LLM to express uncertainty.

A list of messages to prepend to every request to this LLM. Useful for setting context or influencing behavior.

A list of messages to append to every request to this LLM. Useful for setting context or influencing behavior.

This setting aims to control the repetition of tokens based on how often they appear in the input. It tries to use less frequently those tokens that appear more in the input, proportional to how frequently they occur. Token penalty scales with the number of occurrences. Negative values will encourage token reuse.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

This setting aims to control the presence of tokens in the output. It tries to encourage the model to use tokens that are less present in the input, proportional to their presence in the input. Token presence scales with the number of occurrences. Negative values will encourage more diverse token usage.

Stop generation immediately if the model encounters any token specified in the stop array.

This setting influences the variety in the model’s responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.

This setting limits the model’s choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model’s responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

This sets the upper limit for the number of tokens the model can generate in response. It won’t produce more than this limit. The maximum value is the context length minus the prompt length.

Represents the minimum probability for a token to be considered, relative to the probability of the most likely token. (The value changes depending on the confidence level of the most probable token.) If your Min-P is set to 0.1, that means it will only allow for tokens that are at least 1/10th as probable as the best possible option.

OpenRouter provider preferences.

OpenRouter reasoning configuration.

Helps to reduce the repetition of tokens from the input. A higher value makes the model less likely to repeat tokens, but too high a value can make the output less coherent (often with run-on sentences that lack small words). Token penalty scales based on original token’s probability.

Consider only the top tokens with “sufficiently high” probabilities based on the probability of the most likely token. Think of it like a dynamic Top-P. A lower Top-A value focuses the choices based on the highest probability token but with a narrower scope. A higher Top-A value does not necessarily affect the creativity of the output, but rather refines the filtering process based on the maximum probability.

This limits the model’s choice of tokens at each step, making it choose from a smaller set. A value of 1 means the model will always pick the most likely next token, leading to predictable results. By default this setting is disabled, making the model to consider all choices.

Controls the verbosity and length of the model response. Lower values produce more concise responses, while higher values produce more detailed and comprehensive responses.

Fallback models. Will be tried in order if the first one fails.

The number of most similar training table entries to consider when computing the dynamic weight.