Step 3 VL 10B
Step 3 VL 10B is StepFun's language model. A 10B-parameter vision-language model from StepFun capable of understanding and reasoning over both images and text.
| Benchmarks | |
|---|---|
| Intelligence Index | #397 |
| GPQA | #279 |
| HLE | #235 |
| IFBench | #183 |
| Time to First Token | #310 |
| SciCode | #313 |
| LCR | #488 |
| TerminalBench Hard | #272 |
| TAU2 | #359 |
| Output TPS | #543 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
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·
Cheapest Instances to Run It
Cloud GPU instances that can host Step 3 VL 10B, ranked by cheapest on-demand price. The model needs about 24 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 | |
|---|---|---|---|---|---|---|
| g2-standard-4 |  GCP | nvidia-l4 | 24 GB | $0.705/hr | ||
| g2-standard-8 | GCP | nvidia-l4 | 24 GB | $0.851/hr | ||
| Standard_NV16as_v4 |  Azure | AMD Radeon Instinct MI25 | 32 GB | $0.932/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Step 5 Preview | 1.0M | $1.00 | $2.70 | Available | |
| Step 5 Preview | — | — | — | — | Available |
| Step 3.7 Flash | 262K | $0.200 | $1.15 | Available | |
| Step 3 VL 10B | — | — | — | — | Current |
| Step Image Edit 2 | — | — | — | — | Available |
| Step 1X Edit 1.2 | — | — | — | — | Available |
| Step 1X Edit | — | — | — | — | Available |