cerebras/capabilities

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

Cerebras reasoning models

Cerebras offers reasoning models including gpt-oss-120b, qwen-3-32b, and zai-glm-4.7 that generate intermediate thinking tokens before their final response. The reasoning output is streamed through standard AI SDK reasoning parts.

Cerebras reasoning example with streamText

Example code showing how to use Cerebras reasoning models with streamText: import { cerebras } from '@ai-sdk/cerebras'; import { streamText } from 'ai'; const result = streamText({ model: cerebras('gpt-oss-120b'), providerOptions: { cerebras: { reasoningEffort: 'medium', }, }, prompt: 'How many "r"s are in the word "strawberry"?', }); for await (const part of result.stream) { if (part.type === 'reasoning') { console.log('Reasoning:', part.text); } else if (part.type === 'text-delta') { process.stdout.write(part.textDelta); } }

Cerebras generateText example

Example code showing how to use Cerebras models with generateText: import { cerebras } from '@ai-sdk/cerebras'; import { generateText } from 'ai'; const { text } = await generateText({ model: cerebras('llama3.1-8b'), prompt: 'Write a vegetarian lasagna recipe for 4 people.', });

Cerebras models support matrix

Cerebras models and their capabilities: llama3.3-70b, gpt-oss-120b, and qwen-3-32b do not support Image Input but all support Object Generation, Tool Usage, and Tool Streaming.

Cerebras model capabilities

Cerebras model capabilities: - llama3.1-8b: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - llama3.1-70b: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - llama-3.3-70b: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - gpt-oss-120b: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Reasoning (yes), Image Input (no) - qwen-3-32b: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Reasoning (yes), Image Input (no) - qwen-3-235b-a22b-instruct-2507: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - qwen-3-235b-a22b-thinking-2507: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - zai-glm-4.6: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Image Input (no) - zai-glm-4.7: Object Generation (yes), Tool Usage (yes), Tool Streaming (yes), Reasoning (yes), Image Input (no) No Cerebras models support Image Input.

Give your agent this brain