AiCostCompare

Step 3.7 Flash

by Stepfun · stepfun/step-3.7-flash · #113 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

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...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.20

per 1M tokens

Output

$1.15

per 1M tokens

Blended (3:1)

$0.438

3 input : 1 output

Cache read

$0.04

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Step 3.7 Flash with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.438$0.0215
50%$0.377$0.0135−37%
90%$0.329$0.00715−67%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000445$0.445
Document summary8,0001,000$0.00275$2.75
Codebase question (RAG)30,0002,000$0.0083$8.30
Long-context analysis150,0005,000$0.0357$35.75

Performance

Intelligence Index

30.3

AA composite quality

Coding Index

39.6

Math Index

Agentic Index

21.5

Output speed

401 tok/s

median

Time to first token

0.72s

median

Time to first answer

5.71s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
GPQA Diamond80.9%
Humanity's Last Exam19.9%
SciCode40.0%
IFBench67.3%
AA-LCR (Long Context Reasoning)63.7%
Terminal-Bench Hard35.6%
Terminal-Bench 2.139.3%
τ²-Bench (Telecom)98.5%
τ³-Bench Banking11.3%

Design Arena Elo

CategoryElo
Website1,210
UI components1,201
Data viz1,200
SVG1,121
3D1,178
Game dev1,200
Code categories1,201
ASCII art1,204

Specs

Context window

262K

tokens

Max output

256K

tokens

Input modalities

text, image, video

Tokenizer

Other