66 models with profiles. Classification describes capabilities, not a quality ranking.
NVIDIA model released on October 17, 2026 to turn page images into structured text, semantic classes, boxes and reading order. It combines C-RADIOv4-SO400M with a ten-layer mBART decoder and 630,800,496 unique parameters. It accepts an RGB image and a task prompt; PDFs must be converted into page images. It does not generate images or replace a general-purpose assistant.
OCR and documents · Open weights↗ Liquid AILiquid AI multimodal decision model released on October 15, 2026. It accepts text and images and returns probabilities for predefined choices, binary questions or scales. It uses the d1-ultra identifier in the decisions API; it does not generate free-form text.
Decisions · Paid proprietary↗ Black Forest LabsA 5.6-billion-parameter image model released on October 15, 2026. It generates and edits images from text and references, with bounding-box composition control. Distilled and Base are different checkpoints; neither should be confused with the full FLUX 3 Image model.
Image · Restricted weights↗ Black Forest LabsA 5.6-billion-parameter image model released on October 15, 2026. It generates and edits images from text and references, with bounding-box composition control. Distilled and Base are different checkpoints; neither should be confused with the full FLUX 3 Image model.
Image · Restricted weights↗ MetaMeta multimodal model released on October 15, 2026, with 816 billion total and 42 billion active parameters. It accepts text, images, audio and video and returns text. It has a combined one-million-token context and BF16 and NVFP4 variants.
Multimodal · Restricted weights↗ xAIProprietary voice model available since October 14, 2026 for bidirectional audio and text conversations. Its versioned identifier is grok-voice-3.0; grok-voice-latest is an alias already pointing to this version, not another model. It replaces the deprecated Grok Voice 2.0 without changing the endpoint, session parameters or events. Do not confuse it with Grok Voice Transcribe 2.0 or the separate text-to-speech service.
Voice and audio · Paid proprietary↗ GoogleGoogle model generally available since October 13, 2026. It accepts text, images, audio and video and generates text, including code; it does not generate images, audio or video. It uses a MoE architecture and a shared 1,048,576-token window. Robotics applications use this same model, not a separate endpoint.
Text and reasoning · Paid proprietary↗ MicrosoftMicrosoft's multimodal family turns content requirements and optional visual references into editable HTML/CSS documents. The 8B and 32B checkpoints derive from Qwen3-VL-8B-Instruct and Qwen3-VL-32B-Instruct respectively. They produce code, not raster images or video files. The reference provides composition and style, while the prompt remains the source of truth for text, figures and relationships. The verified public release is October 11, 2026; earlier repository creation is not its release date.
Code · Open weights↗ MicrosoftMicrosoft's multimodal family turns content requirements and optional visual references into editable HTML/CSS documents. The 8B and 32B checkpoints derive from Qwen3-VL-8B-Instruct and Qwen3-VL-32B-Instruct respectively. They produce code, not raster images or video files. The reference provides composition and style, while the prompt remains the source of truth for text, figures and relationships. The verified public release is October 11, 2026; earlier repository creation is not its release date.
Code · Open weights↗ Alibaba QwenImage generation and editing model published on October 9, 2026. The Qwen/Qwen-Image-2.1-Turbo checkpoint uses Qwen Image 2.1's 7-billion-parameter visual component, accelerated to eight denoising steps. Its API identifier is qwen-image-2.1-turbo. Both access paths are recorded in one profile, without confusing Turbo with Pro or duplicating entries by platform.
Image · Restricted weights and paid API↗ TencentTencent's 5-billion-parameter multimodal model, publicly released on Hugging Face on October 9, 2026. It analyzes pages, images, charts, diagrams, geometry, audio and video, producing structured text in an OmniSchema JSON envelope. It does not generate images, music or video. A shared encoder processes modalities before the decoder; the requested task determines the schema and extracted elements.
Multimodal · Restricted weights↗ GoogleProduction image model that combines generation, editing, and visual reasoning with a balance of quality, cost, and latency.
Image · Paid proprietary↗ GoogleGoogle model for image generation and conversational editing, generally available since October 6, 2026. It replaces Nano Banana 2 and should not be confused with Nano Banana Pro. It accepts text, images, video and PDF as context; it produces images and text, not video or audio. Google reports improvements in visuals, instruction following, text rendering and consistency across edits.
Image · Paid proprietary↗ Alibaba QwenImage generation and editing service added to Alibaba Cloud's international catalog on October 2, 2026. The Qwen Image 2.1 family combines text-based creation, localized editing and native transparency, with a visual component of 7 billion parameters. This profile identifies the Pro API variant, not the base model's downloadable weights.
Image · Paid proprietary↗ CohereEmbedding variant for interactive search, agent queries and high traffic. Accepts text, images and mixed documents in over one hundred languages. Shares Pro's vector space to query existing indexes at a lower text cost.
Embeddings · Paid proprietary↗ CohereEmbedding model for high-quality indexing of text, images and mixed documents. Supports over one hundred languages and shares a vector space with Embed 5 Fast, allowing documents to be indexed with Pro and queried with Fast without rebuilding the index.
Embeddings · Paid proprietary↗ OpenAIOpenAI model for complex coding, computer use and professional work with text and image inputs. The provider describes performance close to Astra at a lower cost; assess that trade-off on your own tasks.
Text and reasoning · Paid proprietary↗ ElevenLabsExpressive speech synthesis model for narration, characters, and dialogue in more than 90 languages.
Voice and audio · Paid proprietary↗
A workflow for recording how an image, video, or audio file is created, modified, and published—and for interpreting provenance credentials with care.
29 Sep 2026 ↗
A protocol for comparing Stable Audio 3.0 with licensed-library sound effects—without mistaking an impressive sample for a reliable workflow. Includes listening criteria, time, editing, and rights.
26 Sep 2026 ↗
A generated shot can be convincing on its own and still be unusable when edited with others. This guide proposes a protocol for evaluating visual, spatial, and narrative continuity in generative-video sequences, recording their traceability, and deciding which clips are approved, which require intervention, and which must be discarded.
23 Sep 2026 ↗
A generative edit that is useful in production is not validated merely because the requested change looks correct. This guide proposes treating every retouch as a preservation contract: define what may change, what must remain, how to measure it, and when to require human review.
23 Sep 2026 ↗
Using a synthetic voice responsibly requires more than a checkbox or a convincing demo. This guide proposes an operating system for linking each audio asset to a specific authorization, controlling the risk of resemblance to identifiable people, disclosing its nature where appropriate, and removing assets when the terms of use change.
22 Sep 2026 ↗
C2PA credentials can provide cryptographically verifiable evidence about provenance statements and transformations of a file. On their own, they do not prove that an image is true, may be legally reused, or depicts people who gave their consent. This guide sets out a method for assessing, preserving, and communicating that evidence without overstating its conclusions.
22 Sep 2026 ↗