Step 3.7 Flash

stepfun/step-3.7-flash

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

InputImageTextVideo
OutputText
Input / Outputclub$0.212 / $1.219per 1M tokens · USD
Context window262.1Ktoken
Maximum output230.4Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.212/ 1M token
Cache readUS$0.0424/ 1M token
OutputUS$1.219/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
ImageTextVideo
Output
Text
Context window
262,144 token
Maximum output
230,400 token
Reasoning
high · medium · low

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Step 3.7 Flash, and who develops it?

Step 3.7 Flash is a model from stepfun. Its model ID on Vecbase is stepfun/step-3.7-flash. Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

How much does Step 3.7 Flash cost on Vecbase?

For Step 3.7 Flash, the Club plan lists USD 0.212 per 1 million input tokens and USD 1.219 per 1 million output tokens, as of 10/22/2026, 10:14:07 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Step 3.7 Flash’s context window?

Step 3.7 Flash has a context window of 262,144 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Step 3.7 Flash?

Step 3.7 Flash can generate up to 230,400 tokens per response. Your API or request settings may set a lower limit.

Can Step 3.7 Flash call tools in an agent workflow?

Yes. Step 3.7 Flash supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Step 3.7 Flash support structured outputs?

Yes. Step 3.7 Flash supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Step 3.7 Flash support?

Step 3.7 Flash accepts Image, Text, and Video and produces Text.

Which providers make Step 3.7 Flash available through Vecbase?

Vecbase offers Step 3.7 Flash through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Step 3.7 Flash?

Use stepfun/step-3.7-flash as the model identifier for Step 3.7 Flash. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for Step 3.7 Flash?

Step 3.7 Flash supports these reasoning levels: high, medium, and low. Available options depend on your API.

What does an agent need to access Step 3.7 Flash through Vecbase?

To use Step 3.7 Flash, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Step 3.7 Flash?

We do not yet have a confirmed release date for Step 3.7 Flash.

Which models can I compare with Step 3.7 Flash on Vecbase?

You can compare Step 3.7 Flash with Vecbase Flash (vecbase-1.0-lite), Vecbase (vecbase-1.0), and Claude Haiku Latest (anthropic/claude-haiku-latest). Check their capabilities and prices to find the best fit for your task.