Step 3.7 Flash
StepFun128K context · — params · —
stepfun/step-3.7-flash
StepFun's efficient multimodal Flash model for agentic workflows with native vision understanding.
Reachability & verification
Live reachability
Target (StepFun): https://www.stepfun.com
Live reachability probe
Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.
Pricing across providers
1Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.
| Provider | Input /1M | Output /1M | Blended | Ctx | p50 latency | API | Verified |
|---|---|---|---|---|---|---|---|
| StepFunstep-3.7-flash | — | — | — | — | — | OAI | 46d ago |
Works with
Any OpenAI-compatible client works — point the base URL at the provider endpoint.
Capabilities
Languages: en, zh
Technical specs
Context
128K
Max output
—
Parameters
—
Release
—
Training cutoff
—
License
—
Similar models
Frequently asked questions
How much does Step 3.7 Flash cost?
No public pricing is tracked yet — request a brokerage quote for current rates.
Can I use Step 3.7 Flash from outside China?
Availability depends on the hosting provider. Use our Path Planner on the StepFun page to map a verified official-vs-brokered access path, including payment and KYC constraints.
Is Step 3.7 Flash open source?
No — Step 3.7 Flash is a proprietary hosted model, available only through APIs.
Is Step 3.7 Flash OpenAI-compatible?
Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.
What is the maximum context window?
Step 3.7 Flash supports up to 128K tokens of context with a maximum output of — tokens.
Need verified access to Step 3.7 Flash?
We broker vetted intros to StepFun — payment, KYC and endpoint verification handled.