Step 3.7 Flash
StepFun · Open weights · Released May 28, 2026 · stepfun/step-3.7-flash
262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 3 providersUSD / MTOK · VERIFIED 13 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| STStepFun1ST PARTY | $0.20 | $1.15 | $0.04 | 256K | fp8 | 3.7s | 102 tok/s | 99.6% |
 DeepInfra | $0.20 | $1.15 | $0.04 | 262K | — | 0.55s | 148 tok/s | 100.0% |
 Novita | $0.20 | $1.15 | $0.04 | 262K | fp8 | 4.1s | 149 tok/s | 97.8% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.20 / $1.15
per MTok in / out
CACHE READ $0.04
About
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...
Specifications
Context window262,144
Max output256,000
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedMay 28, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/stepfun/step-3.7-flash)Sources
OpenRouter API13 minutes ago
AGGREGATORHugging Face13 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 13 minutes ago · list prices, not negotiated rates.