Step 3.7 Flash
by Stepfun · stepfun/step-3.7-flash · #154 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:42 PM UTC · refreshed nightly
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 rate | Effective blended $/1M | Example 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
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000445 | $0.445 |
| Document summary | 8,000 | 1,000 | $0.00275 | $2.75 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0083 | $8.30 |
| Long-context analysis | 150,000 | 5,000 | $0.0357 | $35.75 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
39.6
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,186 |
| UI components | 1,165 |
| Data viz | 1,171 |
| SVG | 1,073 |
| 3D | 1,108 |
| Game dev | 1,143 |
| Code categories | 1,169 |
| ASCII art | 1,132 |
| 1,116 |
Specs
Context window
262K
tokens
Max output
230K
tokens
Input modalities
text, image, video
Tokenizer
Other