Step 3.5 Flash
StepFun · released Feb 1, 2026 · stepfun-ai/Step-3.5-Flash
- Type
- Open weightsApache License 2.0
- Params
- 199B
- Context
- 262K
about 197K words of context
Our take
Written Aug 3, 2026Step 3.5 Flash is a 199.4-billion-parameter text model from StepFun with a permissive Apache licence and a 262,144-token request limit. Its measured coding score is the highest of its tracked categories, while its creative-writing score sits more than a hundred points lower.
Pick this for coding tasks where its headline measured strength lies, or for long-context text work with a licence that allows commercial use and redistribution. It is also a viable choice when you want identical pricing across the two tracked providers. Skip it if creative writing is the main workload, or if you need throughput guarantees from every host.
The case for it
- Arena Coding Elo of 1450.4 — the highest of its six measured categories, and 105.8 points above its own creative-writing score.
- Apache 2.0 licence permits commercial use, fine-tuning and redistribution without restriction.
- 262,144-token request limit, large for a downloadable model.
- Same pricing on both tracked providers, so switching host does not change cost.
The case against it
- Creative writing is a clear weak spot: its Arena score there is 105.8 points below its coding score.
- No disclosed active-parameter count for its 199.4 billion total parameters.
- Throughput data is thin: only one of two providers lists a speed figure.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)81st of 143 · 1394.6
CodingWriting and fixing code on its own
Arena Coding73rd of 143 · 1450.4
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Step 3.5 Flash for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Step 3.5 Flash placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
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 12.8 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 2 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
- $0.10 in / $0.30 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.10 / $0.30 | 262K | not measured | Unknown | Unknown | Unknown |
| SiliconFlowfp8 | $0.10 / $0.30 | 262K | 67 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 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 | ✓ | ✗ | ✗ |
| SiliconFlowfp8 | ✓ | ✗ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
Models people weigh against Step 3.5 Flash
When we formed this view
Dates behind this page
Prices last checked 3d 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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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-3.5-Flash
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- stepfun-step-3-5-flash