Step-3.7-Flash
by stepfun-ai
Apache-licensed multimodal MoE for image-text reasoning and fast visual QA
stepfun-ai/Step-3.7-Flashmixpeek://image_extractor@v1/stepfun_step37_flash_v1Overview
Step 3.7 Flash is a new multimodal Mixture-of-Experts model from StepFun with image-text-to-text support. It is notable because the model card ships with Transformers and vLLM usage, making it more practical for teams that want a deployable open VLM rather than an API-only model.
On Mixpeek, Step 3.7 Flash is a candidate for scene captioning, visual question answering, screenshot analysis, and agent perception tasks where a single model needs to reason over images plus instructions.
Architecture
Vision-language Mixture-of-Experts model exposed through custom Transformers code and vLLM. Supports image-text chat prompts with Apache 2.0 licensing.
Mixpeek SDK Integration
import { Mixpeek } from "mixpeek";
const mx = new Mixpeek({ apiKey: "API_KEY" });
// Managed: create a collection over a bucket; Mixpeek runs this model's extractor
const collection = await mx.collections.create({
namespace_id: "my-namespace",
collection_name: "my-collection",
source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
feature_extractor: {
feature_extractor_name: "scene_caption",
version: "v1",
parameters: { model_id: "stepfun-ai/Step-3.7-Flash" },
},
});Capabilities
- Image-text-to-text generation
- Vision-language reasoning over screenshots and natural images
- vLLM serving support
- Apache 2.0 license
Use Cases on Mixpeek
Performance
Use for reasoning or caption generation after cheaper retrieval stages
Common Pipeline Companions
Explore on Mixpeek
Compare alternatives in this category
Hand-picked tools & platforms compared
Deep-dive technical guide
See how Mixpeek runs models as extractors
Store & search embeddings at scale
Usage-based pricing for pipelines
Compare models, APIs & infrastructure
Specification
Research Paper
Step 3.7 Flash model card
arxiv.orgBuild a pipeline with Step-3.7-Flash
Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.
Run on your data, free