Overview
The platform now offers updatedisaac-0.2-2b-preview and isaac-0.2-1b models alongside Isaac 0.1 and a hosted Qwen3VL option.
| Feature | Isaac 0.2 2B Preview | Isaac 0.2 1B | Isaac 0.1 | Qwen3VL |
|---|---|---|---|---|
| Description / best for | Best-in-class image VLM with reasoning. | Best-in-class small image VLM; for local, low-latency perception. | Original image VLM for grounded perception. | Qwen’s 235B hosted VLM; for large, complex documents/scenes. |
| Model size | 2B parameters | 1B parameters | 2B parameters | 235B parameters |
| Model ID (API) | isaac-0.2-2b-preview | isaac-0.2-1b | isaac-0.1 | qwen3-vl-235b-a22b-thinking |
| Access / open source | Hosted API + open weights on Hugging Face. | Hosted API + open weights on Hugging Face. | Hosted API + open weights on Hugging Face. | Hosted API; open weights on Hugging Face. |
| Reasoning enabled | Yes | Yes | No | Yes (always on) |
| Comparative latency | Fast | Fastest | Fast | Slow |
| Context window | 8K tokens | 8K tokens | 8K tokens | 127K tokens |
| Max input + output | 8K tokens | 8K tokens | 8K tokens | 160K tokens |
| Pricing | $0.15 per million input tokens $1.25 per million output tokens | $0.15 per million input tokens $1.25 per million output tokens | $0.15 per million input tokens $1.25 per million output tokens | $0.40 per million input tokens $4.00 per million output tokens |
isaac-0.2-2b-preview
isaac-0.2-2b-preview is a 2B-parameter, best-in-class VLM with tool-calling-ready reasoning. It succeeds Isaac 0.1 with stronger perception and the same flexible deployment options. Highlights- Best-in-class perception + reasoning across VQA, OCR, detection, pointing, counting, and tool calls.
- Rapid response with sub-200 ms time-to-first-token and predictable latency.
- Focus capabilities to natively zoom, refocus, and reason over critical regions.
- Few-shot in-context learning so you can specialize with prompt-only examples.
- Python SDK: set
model="isaac-0.2-2b-preview"with the Perceptron SDK. - REST: hit
/v1/chat/completionswithmodel=isaac-0.2-2b-preview. - Self-hosting: download the open weights on Hugging Face; the repo includes the tokenizer, processor, and reference configs. Commercial uses require a commercial license - contact us for details.
isaac-0.2-1b
isaac-0.2-1b is a compact image VLM for grounded perception in local, memory-constrained or low-latency deployments. Highlights- Best in class perception + reasoning at small scale for detection, pointing, and VQA.
- Local-friendly footprint for CPU+GPU hybrids, Apple silicon laptops, Jetsons, and lightweight inference stacks.
- Python SDK: set
model="isaac-0.2-1b"with the Perceptron SDK. - REST: hit
/v1/chat/completionswithmodel=isaac-0.2-1b. - Self-hosting: download the open weights on Hugging Face; the repo includes the tokenizer, processor, and reference configs. Commercial uses require a commercial license - contact us for details.
Isaac 0.1
Isaac 0.1 is the prior 2B image VLM focused on grounded perception, still supported for customers who have integrated it. Access- Python SDK: set
model="isaac-0.1"with the Perceptron SDK. - REST: hit
/v1/chat/completionswithmodel=isaac-0.1. - Self-hosting: download the open weights on Hugging Face; the repo includes the tokenizer, processor, and reference configs. Commercial uses require a commercial license - contact us for details.
Qwen3VL
Perceptron hostsQwen3-VL-235B-A22B-Thinking to unlock additional capabilities for customers. Try it when:
- You need multi-step chain-of-thought over complex documents or scenes.
- Your workload tolerates higher latency/cost.
- You want one integration that spans efficient pointing and VQA models.
- SDK: set
model="qwen3-vl-235b-a22b-thinking"with the Perceptron SDK. - REST: hit
/v1/chat/completionswithmodel=qwen3-vl-235b-a22b-thinking.
Evaluation snapshots
Our latest public benchmarks forisaac-0.2-2b-preview and isaac-0.2-1b are shown below. Please reach out if you have questions.
