StepFun model product
7 Flash is a StepFun large language model for agents, coding, and multimodal prompts.
Updated Oct 23, 2026. Default version: Step 3.7 Flash
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Step 3.7 Flash.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGDPval | Score45.80% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools, text-only) | Score47.20% | Rank08 | Participants10 | Percentile22.22% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score59.50% | Rank38 | Participants48 | Percentile21.28% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score56.30% | Rank39 | Participants63 | Percentile38.71% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score43.87% | Rank51 | Participants89 | Percentile43.18% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score67.28% | Rank60 | Participants168 | Percentile64.67% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score73.67% | Rank71 | Participants193 | Percentile63.54% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score2.29% | Rank72 | Participants200 | Percentile64.32% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score25.78% | Rank80 | Participants201 | Percentile60.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score21.41% | Rank85 | Participants200 | Percentile57.79% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score80.91% | Rank95 | Participants199 | Percentile52.53% | EvidenceB | EvaluatedN/A |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderUnoRouter | Provider model IDstep-3.7-flash:free | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context256K | Updated |
| ProviderAmbient | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.19 | Output / 1M$1.14 | Context262.1K | Updated |
| ProviderDeep Infra | Provider model IDstepfun-ai/Step-3.7-Flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDstepfun-ai/Step-3.7-Flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderStepFun (Global) | Provider model IDstep-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderZenMux | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderRequesty | Provider model IDstep-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderEmpirioLabs AI | Provider model IDstep-3-7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderVercel AI Gateway | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderKilo Gateway | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDstep-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderNovita AI | Provider model IDstepfun/step-3.7-flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context262.1K | Updated |
| ProviderCommandCode | Provider model IDstepfun/Step-3.7-Flash | Regionglobal | Input / 1M$0.20 | Output / 1M$1.15 | Context256K | Updated |
| ProviderStepFun (China) | Provider model IDstep-3.7-flash | Regionglobal | Input / 1M$0.2018 | Output / 1M$1.21 | Context256K | Updated |
| ProviderAIHubMix | Provider model IDstep-3.7-flash | Regionglobal | Input / 1M$0.22 | Output / 1M$1.32 | Context256K | Updated |
| ProviderKenari | Provider model IDstep-3-7-flash | Regionglobal | Input / 1M$0.24 | Output / 1M$1.37 | Context256K | Updated |
Provider-specific output speed and catalog latency for Step 3.7 Flash. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionStep 3.7 Flash | Released | LLMBoard49.27 | Parameters198B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Step 3.7 Flash and its available data.
7 Flash is a newer StepFun flash model designed for agents, coding, and multimodal prompts.
Data as of 2026-10-22.
Common questions about Step 3.7 Flash.
Step 3.7 Flash's default version was released on Jun 10, 2026.
Step 3.7 Flash's official API price is $0.20 per million input tokens and $1.15 per million output tokens via StepFun (Global). The lowest tracked third-party offer starts at $0.19 input and $1.14 output via Ambient.
Step 3.7 Flash was created by StepFun.
The default version has a 262.1K token context window.
Yes. The default version is marked as open weight under Apache 2.0.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
19 provider offerings are linked to the default version.