Models.dev

An open-source database of AI models

Step 3.5 Flash

StepFun flash lane for quick multimodal reasoning and coding assistance

stepfun/step-3.5-flash
Lab
StepFun
Family
-
Providers
10
Context
256,000
Output limit
256,000
Knowledge
2025-01
Release
2026-01-29
Updated
2026-02-13
Weights
Open
Input
Output types
Capabilities
tools, reasoning, temperature

Providers

10
Provider Lab Model ID Context Output Price Reasoning Tool Call Structured Temperature
EmpirioLabs AIStepFunstep-3-5-flash256,000131,072$0.10 / $0.30YesYesYesYes
Hugging FaceStepFunstepfun-ai/Step-3.5-Flash262,144256,000$0.10 / $0.30YesYes-Yes
Kilo GatewayStepFunstepfun/step-3.5-flash256,000256,000$0.10 / $0.30YesYes-Yes
OpenRouterStepFunstepfun/step-3.5-flash262,14465,536$0.10 / $0.30YesYesNoYes
QiniuStepFunstepfun/step-3.5-flash64,0004,096-NoNoNoYes
StepFun (China)StepFunstep-3.5-flash256,000256,000$0.10 / $0.30YesYes-Yes
StepFun Step Plan (China)StepFunstep-3.5-flash256,000256,000-YesYes-Yes
StepFun Step Plan (Global)StepFunstep-3.5-flash256,000256,000-YesYes-Yes
Vercel AI GatewayStepFunstepfun/step-3.5-flash262,114262,114$0.09 / $0.30YesYes-Yes
ZenMuxStepFunstepfun/step-3.5-flash256,00064,000$0.10 / $0.30NoYes-Yes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

The homepage starts with provider-agnostic model metadata. Model pages list the providers serving that model; provider pages list every model available from that provider; lab pages group canonical models by author.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

SDK

Use the SDK to query the API from your app. It's type-safe and exports the latest snapshot for offline use.

Contribute

The data is stored in GitHub as TOML files organized by provider and canonical model.