Visitar URL original
StepFun models, providers, and specs | Models.dev

Models.dev

An open-source database of AI models

Labs

StepFun

StepFun's Step models target fast multimodal agents, pairing visual understanding, search, coding, and tool orchestration.

stepfun
Models
4
Providers
24
Updated
2026-09-20

Models

4
Model Providers Context Output Input Reasoning Tool Call Structured Temperature Weights Price Release Updated
Step 5 Previewstepfun/step-5-preview121,000,0001,000,000
YesYesYes-Closed$0.00 / $0.002026-09-162026-09-20
Step 3.7 Flashstepfun/step-3.7-flash24256,000256,000
YesYes-YesOpen$0.00 / $0.002026-05-292026-05-29
Step 3.5 Flash 2603stepfun/step-3.5-flash-26035256,000256,000
YesYes-YesOpen$0.10 / $0.302026-04-022026-04-02
Step 3.5 Flashstepfun/step-3.5-flash11256,000256,000
YesYes-YesOpen$0.09 / $0.302026-01-292026-02-13
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. Specialized model types are omitted by default; the site includes all model types.

curl https://models.dev/api.json?type=all
curl https://models.dev/models.json?type=all
curl https://models.dev/catalog.json?type=all

Logos

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

curl https://models.dev/logos/anthropic.svg

SDK

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

npm install @opencode-ai/models

Contribute

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

Edit on GitHubCreated by OpenCode