Model Providers & Profiles

The Anthropic API Key used to authenticate requests

Selects the specific model that will be used to serve inference requests sent to this profile. See Anthropic's Model Information for details. This field must contain either the Claude API ID or Claude API alias of the model.

The maximum number of tokens that will be generated in response to an inference request to this profile. The minimum value for this parameter is 1, the maximum depends on the model chosen.

Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. If no value is provided, thinking will be disabled. See Extended Thinking for additional details.

Amount of randomness injected into the response.

Defaults to 1.0. Ranges from 0.0 to 1.0. Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks.

Note that even with temperature of 0.0, the results will not be fully deterministic.

Use nucleus sampling.

In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by Top P. You should either alter Temperature or Top P, but not both.

Recommended for advanced use cases only. You usually only need to use temperature.

Only sample from the top K options for each subsequent token.

Used to remove "long tail" low probability responses.

Recommended for advanced use cases only. You usually only need to use temperature.

The OpenAI API Key used to authenticate requests.

Selects the specific model that will be used to serve inference requests sent to this profile. See OpenAI's Model Information for details. This field must contain either a model identifier or a particular model snapshot identifier.

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

Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Note: The gpt-5-pro model defaults to (and only supports) high reasoning effort.

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

The Google Gemini API Key used to authenticate requests.

The GCP Project ID the service account to be used belongs to.

The GCP Location in which requests should be processed.

The JSON configuration file containing service account credentials.

Selects the specific model that will be used to serve inference requests sent to this profile. See Google's Model Information for details. This field must contain either a model identifier or a particular model snapshot identifier.

The maximum number of tokens to include in a response candidate.

Note: The default value varies by model.

Increase for reasoning tasks; disable if not needed.

Controls the randomness of the output.<br><br>Note: The default value varies by model.

Values can range from [0.0, 2.0].

The maximum cumulative probability of tokens to consider when sampling.

The model uses combined Top-k and Top-p (nucleus) sampling.

Tokens are sorted based on their assigned probabilities so that only the most likely tokens are considered. Top-k sampling directly limits the maximum number of tokens to consider, while Nucleus sampling limits the number of tokens based on the cumulative probability.

Note: The default value varies by Model. Some models do not support Top P sampling.

The maximum number of tokens to consider when sampling.

Gemini models use Top-p (nucleus) sampling or a combination of Top-k and nucleus sampling. Top-k sampling considers the set of topK most probable tokens. Models running with nucleus sampling don't allow topK setting.

Note: The default value varies by Model. Some models do not support Top K sampling.

The base URL of the model provider's API.

An API token to pass to the model provider. This will be included in a Bearer authorization header.

Selects the specific model that will be used to serve inference requests sent to this profile. The model identifiers available will be documented by the model provider.

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

Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.