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

cohere/capabilities

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

Cohere reasoning model with thinking option

Example of using Cohere reasoning model command-a-reasoning-08-2025 with thinking enabled: import { cohere, type CohereLanguageModelChatOptions } from '@ai-sdk/cohere'; import { generateText } from 'ai'; const { text, reasoning } = await generateText({ model: cohere('command-a-reasoning-08-2025'), prompt: "Alice has 3 brothers and she also has 2 sisters. How many sisters does Alice's brother have?", providerOptions: { cohere: { thinking: { type: 'enabled', tokenBudget: 100, }, } satisfies CohereLanguageModelChatOptions, }, }); console.log(reasoning); console.log(text);

Cohere language model capabilities table

Cohere language model capabilities: | Model | Image Input | Object Generation | Tool Usage | Tool Streaming | | command-a-03-2025 | No | Yes | Yes | Yes | | command-a-reasoning-08-2025 | No | Yes | Yes | Yes | | command-a-vision-07-2025 | Yes | Yes | Yes | Yes | | command-r7b-12-2024 | No | Yes | Yes | Yes | | command-r-plus-04-2024 | No | Yes | Yes | Yes | | command-r-plus | No | Yes | Yes | Yes | | command-r-08-2024 | No | Yes | Yes | Yes | | command-r-03-2024 | No | Yes | Yes | Yes | | command-r | No | Yes | Yes | Yes | | command | No | No | No | No | | command-nightly | No | No | No | No | | command-light | No | No | No | No | | command-light-nightly | No | No | No | No |

Cohere vision model image input example

Example of using Cohere vision models with image input: import { cohere } from '@ai-sdk/cohere'; import { generateText } from 'ai'; import { readFileSync } from 'node:fs'; const { text } = await generateText({ model: cohere('command-a-vision-07-2025'), messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe the image in detail.' }, { type: 'file', mediaType: 'image', data: readFileSync('./data/comic-cat.png'), }, ], }, ], });

Cohere supports streamText and Output for structured generation

Cohere language models support the streamText function and structured data generation with Output for AI SDK Core functionality.

Cohere embedding model capabilities table

Cohere embedding model capabilities: | Model | Embedding Dimensions | | embed-english-v3.0 | 1024 | | embed-multilingual-v3.0 | 1024 | | embed-english-light-v3.0 | 384 | | embed-multilingual-light-v3.0 | 384 | | embed-english-v2.0 | 4096 | | embed-english-light-v2.0 | 1024 | | embed-multilingual-v2.0 | 768 |

Cohere reranking model capabilities

Cohere reranking models available: rerank-v3.5, rerank-english-v3.0, rerank-multilingual-v3.0.

Cohere models support matrix

Cohere models and their capabilities: command-a-03-2025, command-a-reasoning-08-2025, command-r-plus, and command-r do not support Image Input but all support Object Generation, Tool Usage, and Tool Streaming.

Give your agent this brain