new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

deepseek/options

4 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

DeepSeek provider configuration options

The DeepSeek provider supports the following optional configuration settings: baseURL (string) - Use a different URL prefix for API calls, defaults to https://api.deepseek.com. apiKey (string) - API key sent via Authorization header, defaults to DEEPSEEK_API_KEY environment variable. headers (Record<string,string>) - Custom headers to include in requests. fetch ((input: RequestInfo, init?: RequestInit) => Promise<Response>) - Custom fetch implementation.

DeepSeek thinking mode option

The thinking option (object) controls chain-of-thought reasoning. It can be enabled either by using the deepseek-reasoner model or by setting this option. The type field accepts 'adaptive', 'enabled', or 'disabled' to enable, disable, or let the model decide (adaptive) when to think. See DeepSeek's thinking mode docs at https://api-docs.deepseek.com/guides/thinking_mode.

DeepSeek reasoningEffort option

The reasoningEffort option (string) controls thinking strength for DeepSeek V4 reasoning models and accepts values: 'low', 'medium', 'high', 'xhigh', or 'max'. Per DeepSeek's docs, low and medium are mapped to high, and xhigh is mapped to max server-side for compatibility with other providers. When using the top-level reasoning setting, minimal is sent as low, and low, medium, high, and xhigh pass through to DeepSeek's native effort values.

DeepSeek thinking and reasoning example

Example using thinking and reasoning effort options: import { deepSeek, type DeepSeekLanguageModelChatOptions } from '@ai-sdk/deepseek'; import { generateText } from 'ai'; const { text, reasoning } = await generateText({ model: deepSeek('deepseek-chat'), prompt: 'How many "r"s are in the word "strawberry"?', providerOptions: { deepseek: { thinking: { type: 'enabled' }, reasoningEffort: 'high', } satisfies DeepSeekLanguageModelChatOptions, }, });

Give your agent this brain