StepFun: step3

Step3 is a cutting-edge multimodal reasoning model from StepFun. It is built on a Mixture-of-Experts (MoE) architecture with 321B total parameters and 38B active parameters. The model is designed end…

siliconFlow/stepfun-ai/step3

Step3 is a cutting-edge multimodal reasoning model from StepFun. It is built on a Mixture-of-Experts (MoE) architecture with 321B total parameters and 38B active parameters. The model is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision-language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators. During pretraining, Step3 processed over 20T text tokens and 4T image-text mixed tokens, spanning more than ten languages. The model has achieved state-of-the-art performance for open-source models on various benchmarks, including math, code, and multimodality

Specifications & capabilities

Input
text, image
Output
text
Max output · tokens
65536
Published model ID
step3
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput

Provider specifications & access

1–1 / 1

step3 ↗

source model id
stepfun-ai/step3
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
65536
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling

Source specification observations

1–2 / 2

siliconFlow ↗

field
context_length
value
66K
scope
source-model
source id
siliconFlow
confidence
1

siliconFlow ↗

field
max_output_tokens
value
66K
scope
source-model
source id
siliconFlow
confidence
1

Original sources

1–5 / 5

SiliconFlow · Model page ↗

Hugging Face · Model repository ↗

SiliconFlow · Playground ↗

SiliconFlow · API documentation ↗

SiliconFlow · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace