# StepFun API Models, Pricing and Capabilities Canonical HTML page: [StepFun API Models, Pricing and Capabilities]() Markdown alternative: [StepFun API Models, Pricing and Capabilities as Markdown]() StepFun builds multimodal foundation models, pairing open-weight sparse mixture-of-experts reasoning models with speech, vision and image generation. StepFun API and models: 2 models on Impossibl, including Step 5 Preview and Step 3.7 Flash. Compare pricing per million tokens, context windows, and capabilities between different StepFun models. Select two or three models to [compare specifications and API costs](). Model types and billing units are not interchangeable. ## At a glance - models: 2 - modalities: takes text and image in, gives text out - latest release: Step 5 Preview (Sep 20, 2026) ## Models ### [Step 3.7 Flash]() Step 3.7 Flash is StepFun's open-weight, high-speed multimodal reasoning model, a sparse mixture-of-experts with 198B total and 11B active parameters. It takes text and image input over a 256K context, reasons at a selectable effort level before answering, and is tuned for agent, coding and tool-calling workloads. Its published context window is 262,144 tokens. The advertised input rate is $0.20 per million input tokens. The advertised output rate is $1.15 per million output tokens. - API identifier: `stepfun/step-3.7-flash` - Creator: StepFun; model type: Text generation. - Context window: 262,144 tokens; tool calling: Not published. - Inputs: text, image; outputs: text. - Base API pricing (USD): $0.20 per million input tokens; $1.15 per million output tokens. - [Complete model facts, cache rates, context tiers, and FAQs as Markdown]() ### [Step 5 Preview]() Step 5 Preview is StepFun's flagship model for agentic work, aimed at software engineering and professional knowledge work with particular strength in finance. It takes text and image input over a context of about one million tokens, reasons at a selectable effort level before answering, and supports tool calling and structured output. Its published context window is 1,024,000 tokens. The advertised input rate is $1.00 per million input tokens. The advertised output rate is $2.70 per million output tokens. - API identifier: `stepfun/step-5-preview` - Creator: StepFun; model type: Text generation. - Context window: 1,024,000 tokens; tool calling: Not published. - Inputs: text, image; outputs: text. - Base API pricing (USD): $1.00 per million input tokens; $2.70 per million output tokens. - [Complete model facts, cache rates, context tiers, and FAQs as Markdown]() ## Compare StepFun models - [Step 3.7 Flash vs Step 5 Preview](); [Markdown comparison]() ## Frequently asked questions ### Which Step models are available through Impossibl? The directory lists 2 models from StepFun available through the Impossibl API, including Step 5 Preview and Step 3.7 Flash. Open each model page for its API identifier, capabilities, and current pricing. ### How much do Step models cost? StepFun model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.20 per million input tokens. Published output rates start at $1.15 per million output tokens. Input and output minima may refer to different models. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid. ### What is the cheapest Step model? By published input rate, the cheapest Step text generation model on Impossibl is Step 3.7 Flash (stepfun/step-3.7-flash) at $0.20 per million input tokens and $1.15 per million output tokens. Cheapest by input rate is not always cheapest for a workload; output-heavy or cached requests can favor another model. ### Does Impossibl add a markup to StepFun pricing? No. Usage is charged at the provider's list price with 0% usage markup. Prepaid credit purchases include a 5% platform fee, and there is no subscription. The rates on this page are StepFun's published base rates, and usage comes off your balance when the request finishes. ### What context windows do Step models support? Among StepFun models with a published limit on Impossibl, the largest context window is 1,024,000 tokens, listed for Step 5 Preview. Context limits vary by model and are separate from maximum output limits. ### What inputs and capabilities do Step models support? Available model types include text generation. Published input support includes image and text; support varies by model. Tool-calling support is unspecified for 2 models. ### How do I use Step models through an API? Use the exact model identifier from the model page with the Impossibl API. For example, select stepfun/step-5-preview with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request. ## Sources and related links Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs. - [Public Impossibl model catalog]() - [Full model directory as JSON]() - [Model directory as Markdown]() - [API quickstart]() - [Model documentation]()