Step-3.7-Flash
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding. Engineered for high-frequency production workloads, it activates approximately 11B parameters per token and delivers a throughput of up to 400 tokens per second. Step 3.7 Flash supports a 256k context window and o...
Params
201.4 B
Context
—
Downloads 30d
17 K
Likes
463
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)17 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 402.7 GB | 473.7 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.20
input / 1M
$1.15
output / 1M
$0.04
cached input / 1M
$1.35
1M in + 1M out
- Context window
- 256,000 tokens
- Max output
- 230,400 tokens
- Providers
- 2
- Cheapest provider
- Novita · $0.20 / $1.15
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 19.5 / 39.6 / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Step3p7ForConditionalGeneration
- Parameters
- 201.4 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-05-23
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model