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

model ids & availability

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

OpenAI GPT-4.1 vision model ID

The model ID for OpenAI's GPT-4 vision model in the AI SDK is 'openai/gpt-4.1'.

xAI Grok image model grok-imagine-image

xAI Grok provides the image model 'grok-imagine-image' which supports aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20, auto

OpenAI image models gpt-image-2 supported sizes

OpenAI's gpt-image-2 image model supports the following sizes: 1024x1024, 1536x1024, 1024x1536

Fal image models supported aspect ratios

Fal image models 'fal-ai/flux/dev', 'fal-ai/flux-lora', 'fal-ai/fast-sdxl', 'fal-ai/flux-pro/v1.1-ultra', 'fal-ai/ideogram/v2', 'fal-ai/recraft-v3', 'fal-ai/stable-diffusion-3.5-large', and 'fal-ai/hyper-sdxl' all support aspect ratios: 1:1, 3:4, 4:3, 9:16, 16:9, 9:21, 21:9

DeepInfra FLUX models supported sizes

DeepInfra FLUX models 'black-forest-labs/FLUX-1.1-pro', 'black-forest-labs/FLUX-1-schnell', 'black-forest-labs/FLUX-1-dev', and 'black-forest-labs/FLUX-pro' support sizes: 256-1440 (multiples of 32)

Replicate image model black-forest-labs/flux-schnell

Replicate's black-forest-labs/flux-schnell image model supports aspect ratios: 1:1, 2:3, 3:2, 4:5, 5:4, 16:9, 9:16, 9:21, 21:9

Replicate image model recraft-ai/recraft-v3

Replicate's recraft-ai/recraft-v3 image model supports sizes: 1024x1024, 1365x1024, 1024x1365, 1536x1024, 1024x1536, 1820x1024, 1024x1820, 1024x2048, 2048x1024, 1434x1024, 1024x1434, 1024x1280, 1280x1024, 1024x1707, 1707x1024

Google Vertex image models imagen-4.0 variants

Google Vertex provides three imagen-4.0 image models: 'imagen-4.0-generate-001', 'imagen-4.0-fast-generate-001', and 'imagen-4.0-ultra-generate-001'. All support aspect ratios: 1:1, 3:4, 4:3, 9:16, 16:9

Google Vertex image model imagen-3.0-fast-generate-001

Google Vertex's imagen-3.0-fast-generate-001 image model supports aspect ratios: 1:1, 3:4, 4:3, 9:16, 16:9

Fireworks FLUX image models supported aspect ratios

Fireworks FLUX image models 'accounts/fireworks/models/flux-1-dev-fp8' and 'accounts/fireworks/models/flux-1-schnell-fp8' support aspect ratios: 1:1, 2:3, 3:2, 4:5, 5:4, 16:9, 9:16, 9:21, 21:9

Fireworks playground image models supported sizes

Fireworks playground image models 'accounts/fireworks/models/playground-v2-5-1024px-aesthetic', 'accounts/fireworks/models/japanese-stable-diffusion-xl', 'accounts/fireworks/models/playground-v2-1024px-aesthetic', and 'accounts/fireworks/models/SSD-1B' all support sizes: 640x1536, 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768, 1536x640

Fireworks image model stable-diffusion-xl-1024-v1-0

Fireworks's stable-diffusion-xl-1024-v1-0 image model supports sizes: 640x1536, 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768, 1536x640

Luma image models photon variants

Luma provides two image models: 'photon-1' and 'photon-flash-1'. Both support aspect ratios: 1:1, 3:4, 4:3, 9:16, 16:9, 9:21, 21:9

Together.ai image model stabilityai/stable-diffusion-xl-base-1.0

Together.ai's stabilityai/stable-diffusion-xl-base-1.0 image model supports sizes: 512x512, 768x768, 1024x1024

Together.ai FLUX image models supported sizes

Together.ai FLUX image models 'black-forest-labs/FLUX.1-dev', 'black-forest-labs/FLUX.1-dev-lora', 'black-forest-labs/FLUX.1-schnell', 'black-forest-labs/FLUX.1-canny', 'black-forest-labs/FLUX.1-depth', 'black-forest-labs/FLUX.1-redux', 'black-forest-labs/FLUX.1.1-pro', 'black-forest-labs/FLUX.1-pro', and 'black-forest-labs/FLUX.1-schnell-Free' all support sizes: 512x512, 768x768, 1024x1024

OpenAI gpt-4o model identifier

The model identifier for OpenAI's GPT-4o model is 'openai/gpt-4o' when used with the Vercel AI SDK's generateText function.

OpenAI gpt-4.1 model supports vision with streamText

The model identifier 'openai/gpt-4.1' can be used with streamText to handle image prompts and streaming structured output. This model supports multimodal input combining text and images.

OpenAI GPT-4.1 supports vision with tool use

The model 'openai/gpt-4.1' supports vision capabilities and can process images as part of prompts while executing tools.

DeepInfra Stability AI image models supported aspect ratios

DeepInfra's Stability AI image models support the following aspect ratios: - stabilityai/sdxl-turbo - stabilityai/sd3.5-medium Supported aspect ratios: 1:1, 16:9, 1:9, 3:2, 2:3, 4:5, 5:4, 9:16, 9:21

Model capabilities table: xAI Grok models

xAI Grok models and their capabilities: grok-4.5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); grok-4 supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); grok-3 supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); grok-3-mini supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes).

Model capabilities table: OpenAI models

OpenAI models and their capabilities: gpt-5.6 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.6-luna supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.6-sol supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.6-terra supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.4-pro supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.4 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.4-mini supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.4-nano supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.3-chat-latest supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.2-pro supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.2-chat-latest supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.2 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5-mini supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5-nano supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.1-chat-latest supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.1-codex-mini supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.1-codex supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5.1 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5-codex supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gpt-5-chat-latest supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes).

Model capabilities table: Anthropic models

Anthropic models and their capabilities: claude-sonnet-5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-fable-5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-8 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-7 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-6 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-sonnet-4-6 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-5 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-1 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-opus-4-0 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); claude-sonnet-4-0 supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes).

Model capabilities table: Groq models

Groq models and their capabilities: meta-llama/llama-4-scout-17b-16e-instruct supports Image Input (yes), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); llama-3.3-70b-versatile supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); llama-3.1-8b-instant supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); mixtral-8x7b-32768 supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes); gemma2-9b-it supports Image Input (no), Object Generation (yes), Tool Usage (yes), Tool Streaming (yes).

OpenAI GPT-4o model ID in streamText

The OpenAI GPT-4o model is referenced using the model ID 'openai/gpt-4o' when calling streamText.

Black Forest Labs image models: flux-pro and flux-kontext variants

Black Forest Labs provides the following image models: Flux-pro variants: - flux-pro-1.1-ultra - flux-pro-1.1 - flux-pro-1.0-fill Flux-kontext variants: - flux-kontext-pro - flux-kontext-max All models support aspect ratios from 3:7 (portrait) to 7:3 (landscape).

Embedding model identifier openai/text-embedding-3-small

The model identifier 'openai/text-embedding-3-small' refers to OpenAI's text-embedding-3-small model, which is used in the AI SDK for creating text embeddings.

Language model identifier openai/gpt-4o

The model identifier 'openai/gpt-4o' refers to OpenAI's GPT-4 Omni model, which is used in the AI SDK for text generation tasks.

OpenAI image models supported sizes

OpenAI offers two image models with the following supported sizes: dall-e-2: 256x256, 512x512, 1024x1024 dall-e-3: 1024x1024, 1792x1024, 1024x1792

Give your agent this brain