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/models

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 language model creation example

Language models can be created using: import { deepSeek } from '@ai-sdk/deepseek'; import { generateText } from 'ai'; const { text } = await generateText({ model: deepSeek('deepseek-chat'), prompt: 'Write a vegetarian lasagna recipe for 4 people.', });

DeepSeek factory methods for model creation

Language models can also be created using the .chat() or .languageModel() factory methods: const model = deepSeek.chat('deepseek-chat'); or const model = deepSeek.languageModel('deepseek-chat');

DeepSeek available models note

For a full list of available DeepSeek models, see the DeepSeek docs at https://api-docs.deepseek.com/quick_start/pricing. Any available provider model ID can be passed as a string if needed.

DeepSeek model capabilities

DeepSeek models and their capabilities: | Model | Text Generation | Object Generation | Image Input | Tool Usage | Tool Streaming | | --- | --- | --- | --- | --- | --- | | deepseek-chat | Yes | Yes | No | Yes | Yes | | deepseek-reasoner | Yes | Yes | No | Yes | Yes | Both models support text generation, object generation, tool usage, and tool streaming. Neither model supports image input.

Give your agent this brain