Gemini

Configuration for the Gemini model provider.

The gemini sub-block configures the Google Gemini provider, which serves the Gemini family of models via the GenerateContent API.

Fields

Field	Type	Required	runtime()	Description
`models`	list	no	no	Allowlist of models for this provider. Each entry is a plain string or a config object with `name` and `params`. When omitted, no allowlist is enforced.
`config`	block	no		Connection configuration.
`config.api_key`	string	no	yes	Gemini API key. Wrap in `secret(runtime(...))` to keep it out of build artifacts.
`params`	block	no		Provider-level inference parameter defaults. Applied to every request unless overridden at the model level.

The config block is optional. When omitted, the client reads credentials from the GEMINI_API_KEY environment variable.

params

The params block sets inference parameter defaults for all models under this provider. All fields are optional and support runtime().

Field	Type	runtime()	Description
`max_tokens`	integer	yes	Maximum number of tokens to generate.
`temperature`	float	yes	Sampling temperature.
`top_p`	float	yes	Nucleus sampling probability.
`top_k`	integer	yes	Top-K sampling limit.
`stop_sequences`	list of strings	yes	Sequences that stop generation.
`seed`	integer	yes	Seed for deterministic sampling.
`provider_params`	object	yes	Provider-specific parameters passed directly to the API.

note

frequency_penalty and presence_penalty are not part of the Gemini API. Setting them has no effect and they will be ignored.

Known model identifiers

Model	Identifier
Gemini 2.5 Flash	`gemini-2.5-flash`
Gemini 2.5 Pro	`gemini-2.5-pro`
Gemini 2.0 Flash	`gemini-2.0-flash`
Gemini 1.5 Flash	`gemini-1.5-flash`
Gemini 1.5 Pro	`gemini-1.5-pro`

Example

agent.acl

providers {
  gemini {
    models = [
      "gemini-2.5-flash",
      {
        name = "gemini-2.5-pro"
        params {
          max_tokens  = 16384
          temperature = 0.4
        }
      }
    ]

    config {
      api_key = secret(runtime("GEMINI_API_KEY"))
    }

    params {
      max_tokens  = 4096
      temperature = 0.5
    }
  }
}

agent "assistant" {
  graph {
    type = "react"
  }

  model {
    provider = "gemini"
    name     = "gemini-2.5-flash"
  }
}

tip

Always wrap API keys in secret(runtime(...)). This prevents the key from appearing in build artifacts and the output of agentc inspect.

Gemini

Configuration for the Gemini model provider.

The gemini sub-block configures the Google Gemini provider, which serves the Gemini family of models via the GenerateContent API.

Fields

Field	Type	Required	runtime()	Description
`models`	list	no	no	Allowlist of models for this provider. Each entry is a plain string or a config object with `name` and `params`. When omitted, no allowlist is enforced.
`config`	block	no		Connection configuration.
`config.api_key`	string	no	yes	Gemini API key. Wrap in `secret(runtime(...))` to keep it out of build artifacts.
`params`	block	no		Provider-level inference parameter defaults. Applied to every request unless overridden at the model level.

The config block is optional. When omitted, the client reads credentials from the GEMINI_API_KEY environment variable.

params

The params block sets inference parameter defaults for all models under this provider. All fields are optional and support runtime().

Field	Type	runtime()	Description
`max_tokens`	integer	yes	Maximum number of tokens to generate.
`temperature`	float	yes	Sampling temperature.
`top_p`	float	yes	Nucleus sampling probability.
`top_k`	integer	yes	Top-K sampling limit.
`stop_sequences`	list of strings	yes	Sequences that stop generation.
`seed`	integer	yes	Seed for deterministic sampling.
`provider_params`	object	yes	Provider-specific parameters passed directly to the API.

note

frequency_penalty and presence_penalty are not part of the Gemini API. Setting them has no effect and they will be ignored.

Known model identifiers

Model	Identifier
Gemini 2.5 Flash	`gemini-2.5-flash`
Gemini 2.5 Pro	`gemini-2.5-pro`
Gemini 2.0 Flash	`gemini-2.0-flash`
Gemini 1.5 Flash	`gemini-1.5-flash`
Gemini 1.5 Pro	`gemini-1.5-pro`

Example

agent.acl

providers {
  gemini {
    models = [
      "gemini-2.5-flash",
      {
        name = "gemini-2.5-pro"
        params {
          max_tokens  = 16384
          temperature = 0.4
        }
      }
    ]

    config {
      api_key = secret(runtime("GEMINI_API_KEY"))
    }

    params {
      max_tokens  = 4096
      temperature = 0.5
    }
  }
}

agent "assistant" {
  graph {
    type = "react"
  }

  model {
    provider = "gemini"
    name     = "gemini-2.5-flash"
  }
}

tip

Always wrap API keys in secret(runtime(...)). This prevents the key from appearing in build artifacts and the output of agentc inspect.

Gemini

Fields

params

Known model identifiers

Example

Search docs

Gemini

Fields

params

Known model identifiers

Example

Search docs