Step 3.7 Flash
StepFun · released May 23, 2026 · stepfun-ai/Step-3.7-Flash
- Type
- Open weightsApache License 2.0
- Params
- 201B
- Context
- 262K
about 197K words of context
Our take
Written Aug 2, 2026Step 3.7 Flash is a 201.4-billion-parameter downloadable model from StepFun that accepts text, images and video. It carries a permissive Apache licence and a 262,144-token request limit, though no benchmark scores are available to judge its quality.
Pick this for large-context multimodal workloads where a permissive open licence matters, or when you want predictable costs without hunting across providers. Skip it if you need measured quality data to compare against alternatives, or if you want to optimise price by switching hosts.
The case for it
- Apache License 2.0 allows commercial use, fine-tuning and redistribution.
- 262,144-token request limit is among the longest we track for downloadable models.
- Throughput varies nearly threefold across measured hosts, from 49 to 144 tokens per second, so you can choose speed over convenience.
The case against it
- No benchmark scores in our data — no chat, coding or reasoning scores to judge quality.
- 201.4 billion total parameters with no disclosed active count or efficiency architecture; self-hosting demands are unclear.
- All six tracked offers are identically priced, so there is no cost arbitrage between providers.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Step 3.7 Flash — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M2 Ultra (76-core GPU) · 192 GB
Borderline fit on an estimated size. It leaves 11.5 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 6 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.20 in / $1.15 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.20 / $1.15 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInframodelopt | $0.20 / $1.15 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfra | $0.20 / $1.15 | 262K | 163 tok/s | No | No | Confirmed |
| Novita AIfp8 | $0.20 / $1.15 | 262K | 94 tok/s | No | No | Confirmed |
| Novita AI | $0.20 / $1.15 | 262K | not measured | Unknown | Unknown | Unknown |
| StepFunfp8 | $0.20 / $1.15 | 256K | 48 tok/s | No | Yesunknown period | Unknown |
DeepInfra
Novita AIAcross the 6 listings we hold: 3 say they do not train on prompts, 0 say they do and 3 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| DeepInframodelopt | |||
| DeepInfra | ✓ | ✗ | ✗ |
| Novita AIfp8 | ✓ | ✗ | ✓ |
| Novita AI | |||
| StepFunfp8 | ✓ | ✓ | ✓ |
Tool calling: 4 of 6 listings say yes, 2 publish no parameter list. JSON output: 2 of 6 listings say yes, 2 say no, 2 publish no parameter list. Strict schema: 3 of 6 listings say yes, 1 says no, 2 publish no parameter list.
Models people weigh against Step 3.7 Flash
When we formed this view
Dates behind this page
Prices last checked 4d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No board we watch has turned up a score, so we hold no quality figures at all.
- 2 of 6 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 3 of 6 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- stepfun-ai/Step-3.7-Flash
- Architecture
- Mixture of experts
- Modality record
- text+image+video->text
- Catalogue slug
- stepfun-step-3-7-flash