Catalog Changes · 2026-10-14 00:05:18.741142

StepFun: Step 3.7 Flash · 2026-10-14 00:05:18.741142 UTC

OpenRouter

6 Changed Fields

Field / Array Position	Previous Value	Observed Value
Benchmarks · Design Arena[0] · Rank	75	76
Benchmarks · Design Arena[1] · Elo	1153	1154
Benchmarks · Design Arena[4] · Win Rate	38.8	38.7
Benchmarks · Design Arena[6] · Elo	1183	1182
Benchmarks · Design Arena[6] · Rank	63	62
Benchmarks · Design Arena[6] · Win Rate	42.2	42.1

← Back To Results

StepFun: Step 3.7 Flash

stepfun/step-3.7-flash

OpenRouter Catalog Changes

Last Observed: 2026-10-14 12:02:50.732034 UTC

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

Find A Field

Architecture And Modalities · 3

Architecture · Instruct Type API Details /architecture/instruct_type Explicit Null	Explicit Null
Architecture · Modality API Details /architecture/modality text+image+video->text	text+image+video->text
Architecture · Tokenizer API Details /architecture/tokenizer Other	Other

Benchmarks · 3

Benchmarks · Artificial Analysis · Agentic Index API Details /benchmarks/artificial_analysis/agentic_index Explicit Null	Explicit Null
Benchmarks · Artificial Analysis · Coding Index API Details /benchmarks/artificial_analysis/coding_index 39.6	39.6
Benchmarks · Artificial Analysis · Intelligence Index API Details /benchmarks/artificial_analysis/intelligence_index 19.5	19.5

Catalog Identity And Metadata · 11

Canonical Slug API Details /canonical_slug stepfun/step-3.7-flash-20260528	stepfun/step-3.7-flash-20260528
Context Tokens API Details /context_length 262144	262,144
Created API Details /created 1779985069	2026-05-28 16:17:49 UTC
Description API Details /description Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...	Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Expiration Date API Details /expiration_date Explicit Null	Explicit Null
Hugging Face Id API Details /hugging_face_id stepfun-ai/Step-3.7-Flash	stepfun-ai/Step-3.7-Flash
Id API Details /id stepfun/step-3.7-flash	stepfun/step-3.7-flash
Knowledge Cutoff API Details /knowledge_cutoff Explicit Null	Explicit Null
Links · Details API Details /links/details /api/v1/models/stepfun/step-3.7-flash-20260528/endpoints	/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints
Name API Details /name StepFun: Step 3.7 Flash	StepFun: Step 3.7 Flash
Supported Voices API Details /supported_voices Explicit Null	Explicit Null

Default Parameters · 6

Default Parameters · Frequency Penalty API Details /default_parameters/frequency_penalty Explicit Null	Explicit Null
Default Parameters · Presence Penalty API Details /default_parameters/presence_penalty Explicit Null	Explicit Null
Default Parameters · Repetition Penalty API Details /default_parameters/repetition_penalty Explicit Null	Explicit Null
Default Parameters · Temperature API Details /default_parameters/temperature Explicit Null	Explicit Null
Default Parameters · Top K API Details /default_parameters/top_k Explicit Null	Explicit Null
Default Parameters · Top P API Details /default_parameters/top_p Explicit Null	Explicit Null

Request Limits · 1

Per Request Limits API Details /per_request_limits Explicit Null	Explicit Null

Pricing · 3

Output Price · USD/Token API Details /pricing/completion 0.00000115	0.00000115
Pricing · Input Cache Read API Details /pricing/input_cache_read 0.00000004	0.00000004
Input Price · USD/Token API Details /pricing/prompt 0.0000002	0.0000002

Reasoning · 2

Reasoning · Default Effort API Details /reasoning/default_effort medium	medium
Reasoning · Mandatory API Details /reasoning/mandatory True	True

Provider Limits · 3

Top Provider · Context Length API Details /top_provider/context_length 256000	256,000
Top Provider · Is Moderated API Details /top_provider/is_moderated False	False
Top Provider · Max Completion Tokens API Details /top_provider/max_completion_tokens 230400	230,400

API Structure And Container Types

Architecture API Details /architecture Object · See Fields	Object · See Fields
Architecture · Input Modalities API Details /architecture/input_modalities Array · See Items	Array · See Items
Architecture · Output Modalities API Details /architecture/output_modalities Array · See Items	Array · See Items
Benchmarks API Details /benchmarks Object · See Fields	Object · See Fields
Benchmarks · Artificial Analysis API Details /benchmarks/artificial_analysis Object · See Fields	Object · See Fields
Benchmarks · Design Arena API Details /benchmarks/design_arena Array · See Items	Array · See Items
Default Parameters API Details /default_parameters Object · See Fields	Object · See Fields
Links API Details /links Object · See Fields	Object · See Fields
Pricing API Details /pricing Object · See Fields	Object · See Fields
Reasoning API Details /reasoning Object · See Fields	Object · See Fields
Reasoning · Supported Efforts API Details /reasoning/supported_efforts Array · See Items	Array · See Items
Supported Parameters API Details /supported_parameters Array · See Items	Array · See Items
Top Provider API Details /top_provider Object · See Fields	Object · See Fields

Architecture · Input Modalities

3 items · source order preserved

text
image
video

API Details

Item	/architecture/input_modalities/*
1	text
2	image
3	video

Architecture · Output Modalities

1 items · source order preserved

text

API Details

Item	/architecture/output_modalities/*
1	text

Supported Parameters

18 items · source order preserved

frequency_penalty
include_reasoning
logprobs
max_tokens
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

API Details

Item	/supported_parameters/*
1	frequency_penalty
2	include_reasoning
3	logprobs
4	max_tokens
5	presence_penalty
6	reasoning
7	reasoning_effort
8	repetition_penalty
9	response_format
10	seed
11	stop
12	structured_outputs
13	temperature
14	tool_choice
15	tools
16	top_k
17	top_logprobs
18	top_p

Benchmarks · Design Arena

8 items · source order preserved

Item	Arena	Category	Elo	Rank	Win Rate
1	models	3d	1130	76	40.5
2	models	asciiart	1154	42	44.9
3	models	codecategories	1185	63	42.5
4	models	dataviz	1174	67	42.9
5	models	gamedev	1163	68	38.7
6	models	svg	1083	64	37.3
7	models	uicomponent	1182	62	42.1
8	models	website	1198	61	44

API Details

Item	/benchmarks/design_arena/*/arena	/benchmarks/design_arena/*/category	/benchmarks/design_arena/*/elo	/benchmarks/design_arena/*/rank	/benchmarks/design_arena/*/win_rate
1	models	3d	1130	76	40.5
2	models	asciiart	1154	42	44.9
3	models	codecategories	1185	63	42.5
4	models	dataviz	1174	67	42.9
5	models	gamedev	1163	68	38.7
6	models	svg	1083	64	37.3
7	models	uicomponent	1182	62	42.1
8	models	website	1198	61	44

Reasoning · Supported Efforts

3 items · source order preserved

high
medium
low

API Details

Item	/reasoning/supported_efforts/*
1	high
2	medium
3	low