Model specification · StepFun
Step 3.7 Flash
stepfun/step-3.7-flash
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...
SpecificationsReported values
- Context window
- 262K
- Maximum output
- 256K
- Architecture
- text+image+video->text
- Tokenizer
- Other
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text image video
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.200 / M |
| Output | $1.15 / M |
Benchmark indexesReported indexes
- Intelligence
- 30.3
- Coding
- 39.6
- Agentic
- 21.5
- Design Arena Elo
- 1189
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00315 |
| Long analysis | 100K / 4K × 1 | 50% | $0.017 |
| Workday | 20K / 2K × 1,000 | 30% | $5.34 |