Function
Encode representations
Convert an input into a representation suitable for a later operation.
Studio / Area
Computational Models
Explore identifiable models by the functions they are designed to provide.
What computational model could provide the required function?
In scope
- Model families, releases, variants, artifacts, offerings, and their documented capabilities
Boundary
- Frameworks, generic solvers, surrounding applications, and unsupported claims of autonomy
Start with the outcome
Functions
Function
Generate text
Produce text conditioned on an input or instruction.
Function
Simulate system behavior
Run a computational model to explore how a specified system evolves.
Function
Agent-based simulation
Model how local rules for individual agents can produce system-level behavior over time.
Function
NetLogo
Programmable environment for building and running multi-agent simulations.
Function
ShieldGemma 1
Google text safety moderation models in 2B, 9B, and 27B sizes, built on Gemma 2.
Function
IBM pos-egnn v1-6M
Predicts energy, per-atom forces and stress for atomic structures using a position-based graph neural network.
Function
Neuro-symbolic Robot Manipulation (ICRA 2023)
Research hybrid that grounds a natural-language instruction in an initial depth-image scene to produce a symbolic manipulation program and pose sub-goals.
Function
Recharging Robots (IPC 2023 PDDL domain)
A pinned engineered PDDL domain describing robots, battery use, guarding, and action transitions for IPC 2023 planning tasks.
Function
Llama 3.1 Instruct
Meta multilingual instruction-tuned Llama 3.1 text model release with size variants.
Function
Mixtral 8x22B Instruct v0.1
Mistral AI instruction-tuned sparse mixture-of-experts model for text responses.
Function
Voyage finance-2
Voyage AI text embedding model specialized for financial retrieval.
Function
Generate music
Create musical audio from a description, composition instructions, or supported reference audio.
Function
Generate sound effects
Create sound effects and ambient audio from descriptions of sounds or events.
Function
Converse in audio
Generate spoken responses to incoming speech and conversational context.
Function
Edit images
Transform supplied images according to text instructions or reference images.
Function
Claude Fable 5.1
Demanding reasoning and long-horizon agentic work with text responses.
Function
Claude Haiku 4.5
Fast text and image understanding with text responses for routine tasks.
Function
Claude Opus 5.5
Long-running agentic coding and knowledge work with text responses.
Function
Claude Sonnet 5.5
General reasoning, coding, and knowledge tasks with an emphasis on speed and capability.
Function
DeepSeek V4 Flash
Text reasoning, coding, and agent tasks in DeepSeek’s V4 Flash model.
Function
DeepSeek V4 Pro
Text reasoning, coding, and agent tasks in DeepSeek’s V4 Pro model.
Function
Gemini 3.1 Pro Preview
Multimodal reasoning and software engineering with text output through the Gemini API.
Function
Gemini 3.8 Flash
Fast multimodal text response generation for coding and agentic tasks.
Function
Llama 4 Maverick 17B-128E
Generate text from text and image prompts using Meta’s Maverick multimodal release.
Function
Llama 4 Scout 17B-16E
Generate text from text and image prompts using Meta’s Scout multimodal release.
Function
Mistral Large 3
General-purpose multimodal understanding and text generation with Mistral Large 3.
Function
Mistral Medium 3.5
Agentic and coding text tasks through Mistral’s current hosted API model.
Function
Mistral Small 4
Instruction following, reasoning, and coding in one hosted Mistral model.
Function
GPT-6.1 Sol
General reasoning, coding, and document work through a current OpenAI API model.
Function
GPT-6 Luna
Focused, high-volume reasoning and text generation through OpenAI API.
Function
Qwen3.5-397B-A17B
Vision-language reasoning and text generation with Qwen’s 397B-A17B release.
Function
Qwen3.5-9B
Vision-language reasoning and text generation with Qwen’s 9B release.
Function
GPT-Image-2.5 Sunburst
Generate images from text prompts and edit supplied images with an emphasis on precise edits.
Function
GPT-Image-2.5 Flare
Generate or edit images from text and image input for fast everyday visual work.
Function
Gemini 3.1 Flash Image
Generate and conversationally edit images from text, image, or video context.
Function
Gemini 3 Pro Image
Generate and edit professional visual assets from prompts and reference images.
Function
FLUX.2 [klein] 9B
Generate images from text and edit images with multiple references using FLUX.2 [klein] 9B.
Function
Gemini Omni Flash 1.1
Generate, edit, extend, and interpolate short videos from text, image, or video input.
Function
Veo 3.1 Preview
Generate short videos with natively generated audio from text or image direction.
Function
Runway Gen-4.5
Generate video clips from text prompts or image-plus-text direction.
Function
Wan2.2 T2V-A14B
Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
Function
GPT-Live 1
Hold full-duplex spoken conversations with simultaneous listening and speech output.
Function
GPT-Audio-1.5
Accept text or audio and produce spoken or text responses through Chat Completions.
Function
Voxtral TTS
Synthesize speech from text, including voice-conditioned delivery.
Function
Eleven v4
Generate expressive multilingual speech from text.
Function
Eleven Music v2.5
Generate music from text prompts or composition plans; the web interface also accepts an audio style reference.
Function
Eleven Text to Sound v2
Generate sound effects from text descriptions.
Function
Lyria 3.5
Generate songs and instrumentals from text or image direction.
Function
Stable Audio Open 1.0
Generate short stereo sound effects and instrumental audio from text prompts.
Function
Midjourney V8.2
Generate images from text and image prompts using Midjourney’s current V8.2 model.
Function
Kling Video 3.0
Generate and edit multi-shot video from prompts and visual references, with native audio.
Function
Seedance 2.5
Generate and extend up to 30-second audio-video clips from multimodal creative direction.
Function
Seedream 5.0 Pro
Generate text-rich and high-density images from creative prompts.
Function
Suno v6
Generate and edit songs from prompts or multimodal references using Suno’s v6 model.
Function
BGE Reranker v2 M3
Scores how relevant a candidate passage is to a query, supporting a second stage of text retrieval.
Function
SAM 2.1 Hiera Large
Segments prompted objects in images and follows their masks through video frames.
Function
Parakeet TDT 0.6B v2
Transcribes English speech audio into text with punctuation, capitalization, and timestamp support.
Function
Kokoro v1.0
Turns supplied text into synthesized speech using a downloadable v1.0 checkpoint.
Function
TimesFM 2.0 500M PyTorch
Forecasts future values of a univariate time series from its historical observations.
Function
TabPFN v2 Classifier
Predicts class labels from small tabular datasets using a pretrained tabular model.
Function
Stable Diffusion 3.5 Large
Generates images from text prompts under gated access and the Stability Community License.
Function
Wan2.1 T2V 1.3B
Generates short video from text prompts using a downloadable 1.3B checkpoint.
Function
Command A (03-2025)
Generates text through Cohere’s hosted chat service using the exact command-a-03-2025 model ID.
Function
OpenVLA 7B
Predicts robot manipulation actions from a camera image and an English-language instruction.
Function
NeuralGCM v1 1.4° Stochastic
Simulates atmospheric evolution using a released hybrid machine-learning and physics checkpoint.
Function
text-davinci-003
Historical OpenAI instruction-following text-completion model whose public API access ended in 2024.
Function
NormWear
Encodes multichannel physiological wearable sensor signals into reusable signal representations.
Function
SmolVLM Instruct
Answers visual questions and describes images in text with a compact vision-language model.
Function
GPT-6 Astra
Reasons over text and images and generates text through OpenAI's hosted API under the exact gpt-6-astra model ID.
Function
Gemma 3n E2B IT LiteRT preview
Produces text from text or images with a Google AI Edge preview checkpoint prepared for Android deployment.
Function
Classify content against a stated safety policy
Assess whether supplied text appears to violate a supplied safety policy.
Function
Produce a scene-grounded manipulation program
Turn a language instruction and perceived tabletop scene into symbolic manipulation steps and target sub-goals.
Function
Rerank candidates
Score candidate results against a query to reorder retrieval results.
Function
Segment images and video
Identify object regions in images or video frames.
Function
Transcribe speech
Convert spoken audio into written language.
Function
Synthesize speech
Generate spoken audio from text input.
Function
Forecast time series
Predict future values from observed time-indexed measurements.
Function
Classify tabular data
Assign categories to rows using structured feature columns.
Function
Generate images
Create image content from an input prompt or conditioning signal.
Function
Generate video
Create moving-image content from an input prompt or conditioning signal.
Function
Predict robot actions
Produce a robot-control action from visual observations and an instruction.
Function
Simulate atmospheric dynamics
Evolve an atmospheric state over time using a bounded simulation model.
Function
Predict material properties
Estimate physical properties of an atomic structure from its atoms and geometry.
Function
Encode sensor signals
Transform multichannel physiological sensor time series into representations for downstream analysis.
Function
Answer visual questions
Produce a text answer to a question grounded in one or more supplied images.
Function
BGE English v1.5
Produces numerical representations of English text for similarity-based applications.
Function
Cohere Embed v4.0
Produces embeddings from text, images, or mixed text and image inputs through a documented API.
Function
Gemma 2 instruction-tuned
Google instruction-tuned Gemma 2 text model line, with distinct size variants and gated artifacts.
Function
text-embedding-3-large
OpenAI API model that converts text to embedding vectors; the large model has its own published model identity.
Function
text-embedding-3-small
OpenAI API model that converts text to embedding vectors; the small model has its own published model identity.
Representative paths
Methods and options
model-release
ShieldGemma 1
Google text safety moderation models in 2B, 9B, and 27B sizes, built on Gemma 2.
model-release
Voyage finance-2
Voyage AI text embedding model specialized for financial retrieval.
model-release
Mixtral 8x22B Instruct v0.1
Mistral AI instruction-tuned sparse mixture-of-experts model for text responses.
model-release
Llama 3.1 Instruct
Meta multilingual instruction-tuned Llama 3.1 text model release with size variants.
model-release
Neuro-symbolic Robot Manipulation (ICRA 2023)
Research hybrid that grounds a natural-language instruction in an initial depth-image scene to produce a symbolic manipulation program and pose sub-goals.
model-release
Claude Fable 5.1
Demanding reasoning and long-horizon agentic work with text responses.
model-release
Claude Haiku 4.5
Fast text and image understanding with text responses for routine tasks.
model-release
Claude Opus 5.5
Long-running agentic coding and knowledge work with text responses.
model-release
Claude Sonnet 5.5
General reasoning, coding, and knowledge tasks with an emphasis on speed and capability.
model-release
DeepSeek V4 Flash
Text reasoning, coding, and agent tasks in DeepSeek’s V4 Flash model.
model-release
DeepSeek V4 Pro
Text reasoning, coding, and agent tasks in DeepSeek’s V4 Pro model.
model-release
Gemini 3.1 Pro Preview
Multimodal reasoning and software engineering with text output through the Gemini API.
model-release
Gemini 3.8 Flash
Fast multimodal text response generation for coding and agentic tasks.
model-release
Llama 4 Maverick 17B-128E
Generate text from text and image prompts using Meta’s Maverick multimodal release.
model-release
Llama 4 Scout 17B-16E
Generate text from text and image prompts using Meta’s Scout multimodal release.
model-release
Mistral Large 3
General-purpose multimodal understanding and text generation with Mistral Large 3.
model-release
Mistral Medium 3.5
Agentic and coding text tasks through Mistral’s current hosted API model.
model-release
Mistral Small 4
Instruction following, reasoning, and coding in one hosted Mistral model.
model-release
GPT-6.1 Sol
General reasoning, coding, and document work through a current OpenAI API model.
model-release
GPT-6 Luna
Focused, high-volume reasoning and text generation through OpenAI API.
model-release
Qwen3.5-397B-A17B
Vision-language reasoning and text generation with Qwen’s 397B-A17B release.
model-release
Qwen3.5-9B
Vision-language reasoning and text generation with Qwen’s 9B release.
model-release
GPT-Image-2.5 Sunburst
Generate images from text prompts and edit supplied images with an emphasis on precise edits.
model-release
GPT-Image-2.5 Flare
Generate or edit images from text and image input for fast everyday visual work.
model-release
Gemini 3.1 Flash Image
Generate and conversationally edit images from text, image, or video context.
model-release
Gemini 3 Pro Image
Generate and edit professional visual assets from prompts and reference images.
model-release
FLUX.2 [klein] 9B
Generate images from text and edit images with multiple references using FLUX.2 [klein] 9B.
model-release
Gemini Omni Flash 1.1
Generate, edit, extend, and interpolate short videos from text, image, or video input.
model-release
Veo 3.1 Preview
Generate short videos with natively generated audio from text or image direction.
model-release
Runway Gen-4.5
Generate video clips from text prompts or image-plus-text direction.
model-release
Wan2.2 T2V-A14B
Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
model-release
GPT-Live 1
Hold full-duplex spoken conversations with simultaneous listening and speech output.
model-release
GPT-Audio-1.5
Accept text or audio and produce spoken or text responses through Chat Completions.
model-release
Voxtral TTS
Synthesize speech from text, including voice-conditioned delivery.
model-release
Eleven v4
Generate expressive multilingual speech from text.
model-release
Eleven Music v2.5
Generate music from text prompts or composition plans; the web interface also accepts an audio style reference.
model-release
Eleven Text to Sound v2
Generate sound effects from text descriptions.
model-release
Lyria 3.5
Generate songs and instrumentals from text or image direction.
model-release
Stable Audio Open 1.0
Generate short stereo sound effects and instrumental audio from text prompts.
model-release
Midjourney V8.2
Generate images from text and image prompts using Midjourney’s current V8.2 model.
model-release
Kling Video 3.0
Generate and edit multi-shot video from prompts and visual references, with native audio.
model-release
Seedance 2.5
Generate and extend up to 30-second audio-video clips from multimodal creative direction.
model-release
Seedream 5.0 Pro
Generate text-rich and high-density images from creative prompts.
model-release
Suno v6
Generate and edit songs from prompts or multimodal references using Suno’s v6 model.
model-release
BGE Reranker v2 M3
Scores how relevant a candidate passage is to a query, supporting a second stage of text retrieval.
model-release
SAM 2.1 Hiera Large
Segments prompted objects in images and follows their masks through video frames.
model-release
Parakeet TDT 0.6B v2
Transcribes English speech audio into text with punctuation, capitalization, and timestamp support.
model-release
Kokoro v1.0
Turns supplied text into synthesized speech using a downloadable v1.0 checkpoint.
model-release
TimesFM 2.0 500M PyTorch
Forecasts future values of a univariate time series from its historical observations.
model-release
TabPFN v2 Classifier
Predicts class labels from small tabular datasets using a pretrained tabular model.
model-release
Stable Diffusion 3.5 Large
Generates images from text prompts under gated access and the Stability Community License.
model-release
Wan2.1 T2V 1.3B
Generates short video from text prompts using a downloadable 1.3B checkpoint.
model-release
Command A (03-2025)
Generates text through Cohere’s hosted chat service using the exact command-a-03-2025 model ID.
model-release
OpenVLA 7B
Predicts robot manipulation actions from a camera image and an English-language instruction.
model-release
NeuralGCM v1 1.4° Stochastic
Simulates atmospheric evolution using a released hybrid machine-learning and physics checkpoint.
model-release
text-davinci-003
Historical OpenAI instruction-following text-completion model whose public API access ended in 2024.
model-release
IBM pos-egnn v1-6M
Predicts energy, per-atom forces and stress for atomic structures using a position-based graph neural network.
model-release
NormWear
Encodes multichannel physiological wearable sensor signals into reusable signal representations.
model-release
SmolVLM Instruct
Answers visual questions and describes images in text with a compact vision-language model.
model-release
GPT-6 Astra
Reasons over text and images and generates text through OpenAI's hosted API under the exact gpt-6-astra model ID.
model-release
Gemma 3n E2B IT LiteRT preview
Produces text from text or images with a Google AI Edge preview checkpoint prepared for Android deployment.
approach
Agent-based simulation
Model how local rules for individual agents can produce system-level behavior over time.
implementation
NetLogo
Programmable environment for building and running multi-agent simulations.
model-release
BGE English v1.5
Produces numerical representations of English text for similarity-based applications.
model-release
Cohere Embed v4.0
Produces embeddings from text, images, or mixed text and image inputs through a documented API.
model-release
Gemma 2 instruction-tuned
Google instruction-tuned Gemma 2 text model line, with distinct size variants and gated artifacts.
model-release
text-embedding-3-large
OpenAI API model that converts text to embedding vectors; the large model has its own published model identity.
model-release
text-embedding-3-small
OpenAI API model that converts text to embedding vectors; the small model has its own published model identity.
Across the Studio
Governance connection
Model evidence, lifecycle, and availability are reviewed independently of vendor claims.
Related records
- In this areaEncode representations
- In this areaGenerate text
- In this areaSimulate system behavior
- In this areaAgent-based simulation
- In this areaNetLogo
- In this areaShieldGemma 1
- In this areaIBM pos-egnn v1-6M
- In this areaNeuro-symbolic Robot Manipulation (ICRA 2023)
- In this areaRecharging Robots (IPC 2023 PDDL domain)
- In this areaLlama 3.1 Instruct
- In this areaMixtral 8x22B Instruct v0.1
- In this areaVoyage finance-2
- In this areaGenerate music
- In this areaGenerate sound effects
- In this areaConverse in audio
- In this areaEdit images
- In this areaClaude Fable 5.1
- In this areaClaude Haiku 4.5
- In this areaClaude Opus 5.5
- In this areaClaude Sonnet 5.5
- In this areaDeepSeek V4 Flash
- In this areaDeepSeek V4 Pro
- In this areaGemini 3.1 Pro Preview
- In this areaGemini 3.8 Flash
- In this areaLlama 4 Maverick 17B-128E
- In this areaLlama 4 Scout 17B-16E
- In this areaMistral Large 3
- In this areaMistral Medium 3.5
- In this areaMistral Small 4
- In this areaGPT-6.1 Sol
- In this areaGPT-6 Luna
- In this areaQwen3.5-397B-A17B
- In this areaQwen3.5-9B
- In this areaGPT-Image-2.5 Sunburst
- In this areaGPT-Image-2.5 Flare
- In this areaGemini 3.1 Flash Image
- In this areaGemini 3 Pro Image
- In this areaFLUX.2 [klein] 9B
- In this areaGemini Omni Flash 1.1
- In this areaVeo 3.1 Preview
- In this areaRunway Gen-4.5
- In this areaWan2.2 T2V-A14B
- In this areaGPT-Live 1
- In this areaGPT-Audio-1.5
- In this areaVoxtral TTS
- In this areaEleven v4
- In this areaEleven Music v2.5
- In this areaEleven Text to Sound v2
- In this areaLyria 3.5
- In this areaStable Audio Open 1.0
- In this areaMidjourney V8.2
- In this areaKling Video 3.0
- In this areaSeedance 2.5
- In this areaSeedream 5.0 Pro
- In this areaSuno v6
- In this areaBGE Reranker v2 M3
- In this areaSAM 2.1 Hiera Large
- In this areaParakeet TDT 0.6B v2
- In this areaKokoro v1.0
- In this areaTimesFM 2.0 500M PyTorch
- In this areaTabPFN v2 Classifier
- In this areaStable Diffusion 3.5 Large
- In this areaWan2.1 T2V 1.3B
- In this areaCommand A (03-2025)
- In this areaOpenVLA 7B
- In this areaNeuralGCM v1 1.4° Stochastic
- In this areatext-davinci-003
- In this areaNormWear
- In this areaSmolVLM Instruct
- In this areaGPT-6 Astra
- In this areaGemma 3n E2B IT LiteRT preview
- In this areaClassify content against a stated safety policy
- In this areaProduce a scene-grounded manipulation program
- In this areaRerank candidates
- In this areaSegment images and video
- In this areaTranscribe speech
- In this areaSynthesize speech
- In this areaForecast time series
- In this areaClassify tabular data
- In this areaGenerate images
- In this areaGenerate video
- In this areaPredict robot actions
- In this areaSimulate atmospheric dynamics
- In this areaPredict material properties
- In this areaEncode sensor signals
- In this areaAnswer visual questions
- In this areaBGE English v1.5
- In this areaCohere Embed v4.0
- In this areaGemma 2 instruction-tuned
- In this areatext-embedding-3-large
- In this areatext-embedding-3-small
Sources
Last reviewed 2026-09-29