Settings
Large language models (LLMs) typically provide settings to augment their output.
All AI SDK functions support the following common settings in addition to the model, the prompt, and additional provider-specific settings:
Some providers do not support all common settings. If you use a setting with a
provider that does not support it, a warning will be generated. You can check
the warnings property in the result object to see if any warnings were
generated.
Language Model Call Options
Language model call options (LanguageModelCallOptions) are settings that influence how the language model generates its response — token limits, sampling behavior, penalties, stop sequences, seed, and reasoning. They are forwarded to the underlying model.
maxOutputTokens
Maximum number of tokens to generate.
temperature
Temperature setting.
The value is passed through to the provider. The range depends on the provider and model.
For most providers, 0 means almost deterministic results, and higher values mean more randomness.
It is recommended to set either temperature or topP, but not both.
0 by default.topP
Nucleus sampling.
The value is passed through to the provider. The range depends on the provider and model. For most providers, nucleus sampling is a number between 0 and 1. E.g. 0.1 would mean that only tokens with the top 10% probability mass are considered.
It is recommended to set either temperature or topP, but not both.
topK
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.
presencePenalty
The presence penalty affects the likelihood of the model to repeat information that is already in the prompt.
The value is passed through to the provider. The range depends on the provider and model.
For most providers, 0 means no penalty.
frequencyPenalty
The frequency penalty affects the likelihood of the model to repeatedly use the same words or phrases.
The value is passed through to the provider. The range depends on the provider and model.
For most providers, 0 means no penalty.
stopSequences
The stop sequences to use for stopping the text generation.
If set, the model will stop generating text when one of the stop sequences is generated. Providers may have limits on the number of stop sequences.
seed
It is the seed (integer) to use for random sampling. If set and supported by the model, calls will generate deterministic results.
reasoning
Controls how much reasoning the model performs before generating a response.
| Value | Behavior |
|---|---|
'provider-default' | Use the provider's default reasoning behavior (default when omitted) |
'none' | Disable reasoning |
'minimal' | Bare-minimum reasoning |
'low' | Fast, concise reasoning |
'medium' | Balanced reasoning |
'high' | Thorough reasoning |
'xhigh' | Extra-high reasoning |
'max' | Maximum reasoning |
Provider-specific settings take precedence over the corresponding fields derived from reasoning. Partial configurations can still use portable reasoning to fill missing fields; summary and display options can be used alongside it. For example, Bedrock preserves an explicit thinking budget while deriving a missing enabled type from portable reasoning.
See the reasoning guide for details on per-provider mapping and migration from providerOptions.
Request Options
Request options (RequestOptions) are settings that affect transport, retries, cancellation, and timeouts — not model generation behavior. They control how the SDK communicates with the provider's API.
maxRetries
Maximum number of retries. Set to 0 to disable retries. Default: 2.
abortSignal
An optional abort signal that can be used to cancel the call.
The abort signal can e.g. be forwarded from a user interface to cancel the call,
or to define a timeout using AbortSignal.timeout.
Example: AbortSignal.timeout
timeout
An optional timeout in milliseconds. The call will be aborted if it takes longer than the specified duration.
This is a convenience parameter that creates an abort signal internally. It can be used alongside abortSignal - if both are provided, the call will abort when either condition is met.
You can specify the timeout either as a number (milliseconds) or as an object with the following properties:
totalMs: The total timeout for the entire call including all steps.stepMs: The timeout for each complete step, including model generation, retries, and local tool execution. The budget is cumulative across provider attempts within the step.firstChunkMs: The timeout until the first content-bearing output of each step (streaming only). Text deltas, reasoning deltas, tool-input deltas, generated files, and tool calls satisfy the timeout. Response metadata, stream starts, empty deltas, raw chunks, and transport activity do not satisfy or reset it.chunkMs: The timeout between meaningful model output chunks after output has started (streaming only). It starts with the first meaningful output; it does not limit the wait for that first output. Non-content chunks do not reset it. This is useful for detecting streams that stall after generation begins.toolMs: The default timeout for all tool executions. If a tool takes longer, it aborts and returns a tool-error so the model can respond or retry.tools: Per-tool timeout overrides using{toolName}Mskeys (e.g.weatherMs,slowApiMs). Takes precedence overtoolMs. Tool names are type-checked for autocomplete.
The firstChunkMs and chunkMs timers stop when the model response finishes, errors, closes, or is cancelled. Each provider retry or later model call gets fresh output timeout budgets. Retry backoff and local tool execution are outside these budgets. Provider-executed tools remain within the model response. The stepMs and totalMs budgets remain active across retries and local tool execution.
Example: 5 second timeout (number format)
Example: 5 second total timeout (object format)
Example: 10 second step timeout
Example: Combined total and step timeout
Example: Per-chunk timeout for streaming (streamText only)
Example: First-content timeout for streaming (streamText only)
Example: Tool execution timeout
Example: Per-tool timeout overrides
headers
Additional HTTP headers to be sent with the request. Only applicable for HTTP-based providers.
You can use the request headers to provide additional information to the provider,
depending on what the provider supports. For example, some observability providers support
headers such as Prompt-Id.
The headers setting is for request-specific headers. You can also set
headers in the provider configuration. These headers will be sent with every
request made by the provider.