Step 3.5 Flash
DeprecatedStep 3.5 Flash is StepFun's language model with a 262K context window and up to 66K output tokens, starting at $0.1 / 1M input and $0.3 / 1M output. An open-source Mixture-of-Experts reasoning model from StepFun with 196B total parameters (11B active), featuring a 256K context window and tool-calling support.
| Benchmarks | |
|---|---|
| Intelligence Index | #200 |
| GPQA | #127 |
| HLE | #121 |
| IFBench | #89 |
| Time to First Token | #530 |
| SciCode | #164 |
| LCR | #193 |
| TerminalBench Hard | #87 |
| TAU2 | #34 |
| Output TPS | #79 |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.1 | $0.3 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Step 3.5 Flash, ranked by cheapest on-demand price. The model needs about 479 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| p4de.24xlarge |  AWS | 8× A100 | 640 GB | $27.45/hr | ||
| Standard_ND96amsr_A100_v4 |  Azure | 8× NVIDIA A100 (80GB) | 640 GB | $32.77/hr | ||
| g7e.48xlarge | AWS | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | ||