Skip to main content

​
Release history

​
2026-09-25 — Isaac 0.1 and 0.2 retired

  • Removed: isaac-0.1, isaac-0.2-1b, and isaac-0.2-2b-preview from the Perceptron API. Requests for them return HTTP 404 with error code model_not_found, and they no longer appear in GET /v1/models or MCP. Migrate to perceptron-mk1.5.
  • Updated: Requests for any unknown model ID now return 404 model_not_found instead of 400.

​
2026-09-03 — Multilook chat completions

  • Added: /v1/chat/completions/multilook — send a shared context plus up to 16 independent prompts (and up to 8 completions per prompt) in one request. The context is prefilled once; reused prompt tokens are reported in usage.prompt_tokens_details.cached_tokens and billed at the cache-read rate ($0.0375/M).
  • Added: Multilook developer guide and API reference page.

​
2026-06-22 — Inline video frames

  • Added: video_frames content part for chat completions — pass pre-decoded video frames inline (each with an image_url and a timestamp_ms) as an alternative to a single video_url. Useful when you’ve already sampled frames client-side or need precise control over which frames the model sees.

​
2026-06-15 — Files API

  • Added: /v1/files endpoints (upload, list, retrieve, retrieve content, delete) for uploading images and video once and referencing them by id across requests.
  • Added: Files developer guide and OpenAI-compatible API reference pages.

​
2026-06-09 — Detect API

  • Added: /v1/detect endpoint for direct grounded object detection — return boxes or points from text categories, annotated exemplars, or exhaustive detection, without building a chat-completions prompt.
  • Added: Detect capability guide and API reference pages with full request/response schemas.

​
2026-05-12 — Perceptron Mk1 launch

  • Added: perceptron-mk1 — flagship VLM with image + video input, 32K context, and reasoning support.
  • Added: Video capability guides (Video Q&A, Video Clipping, ICL Video) plus matching cookbook notebooks.
  • Added: Models tab with per-model spec pages (modality, context, pricing).
  • Updated: Image capability guides rewritten for Perceptron Mk1 and the new SDK API surface.

​
2026-03-31 — Perceptron MCP launch

  • Added: Guide covering Perceptron MCP setup, Perceptron MCP tools, and tasks best suited for Isaac-powered agents.

​
2025-12-10 — Isaac 0.2 2B preview + Isaac 0.2 1B launch

  • Added: isaac-0.2-2b-preview and isaac-0.2-1b image VLMs (2B and 1B parameter, respectively).
  • Added: Guides covering thinking and tool calling flows.

​
2025-11-12 — Perceptron Platform launch

  • Added: Guidance on API creation via Perceptron’s first-party API.

​
2025-09-17 — Initial public launch

  • Added: isaac-0.1 image VLM (2B parameter).
  • Added: Perceptron SDK quickstart with first-run Python & CLI snippets.
  • Added: Guides covering captioning, VQA, detection, OCR, ICL, streaming, and edge deployment.
  • Added: Tutorials for manufacturing defects, OCR & Layout Extraction, and PDF document intake.
  • Added: Best practices playbooks for prompting, latency optimization, and security.
  • Added: API reference navigation with endpoint examples and CLI commands.