Stepfun
99.98%Context256K
Max output256K
p50 latency7,002 ms
Throughput106.0 t/s
Input price$0.2
Output price$1.15
Caching
Model directory
Baseer model profileLanguage model
stepfun/step-3.7-flash
Step 3.7 Flash
StepFun’s flagship multimodal reasoning model. Powered by a 198B-parameter / 11B-activation sparse MoE architecture, with native support for image and video understanding.
Input / 1M tokens$0.2
Output / 1M tokens$1.15
Maximum context256K
Inference providers1
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Stepfun | 256K | 256K | 7,002 ms | 106.0 t/s | 99.978% | $0.2 | $1.15 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningAutomatic cachingTool useVisionTools
Reasoning options
LowMediumHigh
Technical profile
- Model type
- Language model
- Release date
- May 28, 2026
- Knowledge cutoff
- 2026-03-01
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
stepfun/step-3.7-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.