StepFun · Official-source model record
Step-3.7-Flash
Step · Version Step-3.7-Flash
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about Step-3.7-Flash
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which Step-3.7-Flash does this page describe?
Step-3.7-Flash is a model record from StepFun in the Step family. Source
The recorded model identifier or checkpoint is Step-3.7-Flash. Use that exact identifier when checking documentation or a provider listing. Source
How can you access Step-3.7-Flash?
The catalog documents API and Open weights access for Step-3.7-Flash. Source 1 · Source 2
As of the catalog check, this version was listed as available. Source
For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.
What are Step-3.7-Flash's context and output limits?
The documented context window is 256,000 tokens. Source
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What can Step-3.7-Flash receive and generate?
Documented inputs: text, image, and video. Source
Documented outputs: text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for Step-3.7-Flash?
The recorded license label is apache-2.0. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What is documented about the Step-3.7-Flash checkpoint?
This evidence refers to stepfun-ai/Step-3.7-Flash at recorded revision 5f6244077ac62e04eec3f320501ff8c2b293373a, checked October 23, 2026. Repository metadata
Safetensors metadata records 201,365,316,160 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: Step3p7ForConditionalGeneration. Repository metadata
Repository task tag: image-text-to-text. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata
Repository language labels: en. These labels are not independent evaluations of language quality. Repository metadata
Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
What the configuration file says
The pinned config.json section text_config contains these values. Pinned configuration
max_position_embeddings- 262,144
rope_scaling- {"rope_type":"llama3","factor":2,"original_max_position_embeddings":131072,"low_freq_factor":1,"high_freq_factor":32}
sliding_window- 512
torch_dtype- bfloat16
num_attention_heads- 64
num_hidden_layers- 45
hidden_size- 4,096
Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other Step models from StepFun.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
step-1o-turbo-vision
API · 32,000 context tokens
Step-3.5-Flash
API · Open weights · 256,000 context tokens
step-3.5-flash-2603
API · 256,000 context tokens
Step-3.5-Flash-Base
Open weights
Step-3.5-Flash-Base-Midtrain
Open weights
Step-Audio-2-mini
Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- StepFunSource ↗
- Family
- StepSource ↗
- Version
- Step-3.7-FlashSource ↗
- Availability
- AvailableSource ↗
- Access
- API · Open weightsSource 1 ↗Source 2 ↗
- Inputs
- Text · Image · VideoSource ↗
- Outputs
- TextSource ↗
- Context window
- 256,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Not documented
- License
- apache-2.0Source ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official publisher weight listing; availability refers to this distribution, not a guaranteed hosted API. Base, SFT and research variants are identified by their exact published names. Official quantization/runtime variants are retained as aliases. Official context K/M display values normalized as decimal tokens. Publisher repository evidence (2026-10-23): Publisher task label: image-text-to-text. Published architecture metadata: Step3p7ForConditionalGeneration. Repository library label: transformers. Model-card language labels: en; these labels are not evaluated proficiency scores. Published safetensors metadata counts 201,365,316,160 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published text_config configuration: max_position_embeddings=262144; sliding_window=512; dtype=bfloat16; 45 hidden layers. The configuration includes explicit RoPE scaling ({"rope_type":"llama3","factor":2,"original_max_position_embeddings":131072,"low_freq_factor":1,"high_freq_factor":32}); no effective context extension is inferred. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Model identifiers and aliases 5
step-3.7-flashstepfun-ai/Step-3.7-Flashstepfun-ai/Step-3.7-Flash-FP8stepfun-ai/Step-3.7-Flash-GGUFstepfun-ai/Step-3.7-Flash-NVFP4
Follow the evidence
Official sources.
- Step-3.7-Flash official model card ↗huggingface.co
- list — official StepFun documentation ↗platform.stepfun.com
- Step-3.7-Flash: official publisher repository metadata ↗huggingface.co
- Step-3.7-Flash: publisher model card at revision 5f6244077ac6 ↗huggingface.co
- Step-3.7-Flash: published checkpoint configuration at revision 5f6244077ac6 ↗huggingface.co