# 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. - Model identifier: ` stepfun/step-3.7-flash ` - Creator: StepFun - Providers: StepFun - Model type: Text generation - Canonical model page: [Step 3.7 Flash]() - API availability: Listed as serving through Impossibl. - Creator release date: 2026-05-29 ## Providers StepFun hosts Step 3.7 Flash. Impossibl routes your request intelligently and handles failover automatically when a provider is down. | Provider | Endpoint location | Routes | Verified context window | Tool calling | | --- | --- | --- | --- | --- | | StepFun | Not specified | 1 | Not verified | Not verified | The model price applies whichever provider serves the request. Endpoint locations do not guarantee inference residency. ## Specs and Capabilities - Context window: 262,144 tokens - Maximum output tokens: Not published in the public catalog; this is separate from the context window. - Inputs: text, image - Outputs: text - Tool calling: Not published ## API access Use ` stepfun/step-3.7-flash ` as the model identifier through the Impossibl API. Published API endpoints: - ` /v1/chat/completions ` [API quickstart]() · [Models and billing documentation]() ## Published API prices All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid. | Usage | Published base rate | Billing unit | | --- | --- | --- | | Input | $0.20 | per million input tokens | | Output | $1.15 | per million output tokens | | Cache read | $0.04 | per million cached input tokens | | Cache write (default retention) | Not published | per million tokens | | Cache write (one-hour retention) | Not published | per million tokens | | Audio input | Not published | per million audio input tokens | ## Benchmarks Last checked: 2026-10-14T17:57:48.915Z. Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted. ### Step 3.7 Flash Source: [Evaluation source]() | Benchmark | Score | | --- | --- | | Intelligence Index | 19.48 | | Omniscience Index | -37.28 | | GPQA | 80.91% | | Humanity’s Last Exam | 21.41% | | SciCode | 43.87% | | CritPt | 2.29% | | Terminal-Bench Hard | 35.61% | | AA-LCR | 73.67% | | GDPval Elo | 855.95 | | MMMU-Pro | 75.32% | | IFBench | 67.28% | | Tau2 | 98.54% | | Tau Banking | 11.96% | | APEX-Agents | 14.82% | | ITBench | 30.27% | Full benchmark data and breakdowns: [Complete benchmark snapshot](). ## Availability and retirement The model is listed as serving. No retirement is announced in the current public catalog. ## Frequently asked questions ### What is 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. Sources: [Step 3.7 Flash model page](); [Step 3.7 Flash on Hugging Face]() ### How much does Step 3.7 Flash cost? Step 3.7 Flash costs $0.20 per million input tokens and $1.15 per million output tokens through the Impossibl API. Cache reads cost $0.04 per million tokens. All rates are in USD. ### What is the context length of Step 3.7 Flash? Step 3.7 Flash has a 262,144-token context window through the Impossibl API. ### What inputs and outputs does Step 3.7 Flash support? Step 3.7 Flash accepts text and image as input. Step 3.7 Flash returns text. ### How do I use Step 3.7 Flash through an API? Step 3.7 Flash is available through the Impossibl API. Use stepfun/step-3.7-flash as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request. ### When was Step 3.7 Flash released? StepFun released Step 3.7 Flash on May 29, 2026. Sources: [Creator release announcement]() ## Sources and related links Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering. - [Public Impossibl model catalog]() - [Full model directory as JSON]() - [Step 3.7 Flash: model details and pricing]() - [Model directory]() - [Step 3.7 Flash model page]() - [Step 3.7 Flash on Hugging Face]()