LLM Reference

Step-2

Released
2024-09-01
Last refreshed
2026-05-29
Status
Researched 22d ago
ProprietaryCommercial use with conditionsMultimodalRAGAgentsLong contextVisionJSON / Tool use

Step-2 is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 256k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Step
Released
2024-09-01
Context
256k
Parameters
1T (MoE)*
Architecture
Mixture of Experts
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use with conditions
Training
pretrained
Created by

One of China's leading AI 'Six Tigers'.

Shanghai, China
Founded 2023
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · StepFun

About

Step-2 is StepFun's Step model with multimodal text and image input. It offers a 256K-token context window.

Step-2 is a proprietary model in the Step family. The structured metadata tracks a 256k-token context window, multimodal input, and function calling. This page tracks provider routes through StepFun. No headline benchmark score is tracked for Step-2 yet.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
StepFun--
ServerlessPartial

Capabilities

VisionMultimodalFunction Calling

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.