Step-3

by StepFunChat

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Context
65.5K tokens
Max output
64,000 tokens
Released
2025-07-31
Weights
Closed

stepfun/step-3

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-07-31
Weights
Closed
Input
Image, Text
Output
Text
Context window
65,536 max across endpoints
Max output
64,000
Providers
0 + 1 gateway, not counted as providers
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
2025-07-31
Knowledge cutoff
2025-01-01

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from StepFun

Newest StepFun models in the catalogue. All StepFun models

ModelReleasedContextListed price
Step 5 Preview2026-09-161Mfrom $0.959
Step 3.7 Flash2026-05-29256Kfrom $0.185
StepAudio 2.5 ASR2026-04-24—unpriced
StepAudio 2.5 TTS2026-04-16—unpriced
Step 3.5 Flash 26032026-04-02256Kfrom $0.10
Step TTS 22026-03-01—unpriced
Step 3.5 Flash2026-01-29256Kfrom $0.09
Gelab Zero 4b Preview2025-12-238.2Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model