Step 3.7 Flash Pricing, Benchmarks & Channels
Step 3.7 Flash is a 2026-05-29 model from StepFun featuring a 256K context window and extended reasoning capabilities. Lowest rate on OpenRouter ($0.2 in / $1.15 out per 1M tokens).
Input Price / 1M
$0.20175
Output Price / 1M
$1.21052
Cache Read / 1M
$0.04035
Context Window
256K
Generation Speed
191 TPS
Access Grade
A · CN Direct
F.A.R.E. Four-Dimension Score Breakdown
Scenario Capability Breakdown (0–100):
💻 Coding
70/100
✍️ Writing
70/100
📚 Long-Doc RAG
76/100
👁️ Vision OCR
74/100
F.A.R.E. CAPABILITY RADAR
Step 3.7 Flash Multi-Platform Price Comparison (3 Verified Channels)
All prices are in USD per 1M tokens. Domestic developers can prioritize channels marked "Direct in CN" for compliant access and local billing.
| Platform / Gateway | Network Access | Input ($/1M) | Output ($/1M) | Cache Hit ($/1M) | Billing & Notes | Link |
|---|---|---|---|---|---|---|
| OpenRouter Lowest Price | Direct in CN | $0.2 | $1.15 | $0.04 | Direct CN access · RMB billing | Visit Official → |
| DeepInfra | Global Network | $0.2 | $1.15 | $0.04 | Global cloud billing | Visit Official → |
| StepFun Official (CN) | Direct in CN | $0.2018 | $1.2105 | $0.0403 | Direct CN access · RMB billing | Visit Official → |
✅ Core Strengths & Ideal Workloads
- Fast generation speed (~191 tokens/sec)
- Direct access in mainland China with RMB enterprise billing
- Open weights available for private self-hosting (~20GB VRAM at INT4)
⚠️ Limitations & Practical Caveats
- Domestic Chinese frontier lab specializing in multimodal reasoning and fast flash models.
- Extended thinking generates internal reasoning tokens (~1.8x output multiplier)