All models
Stepfun
Step 3.5 Flash fastruns locally
stepfun/step-3-5-flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
Input / 1M
$0.10
USD per million tokens
Output / 1M
$0.30
USD per million tokens
Est. cost / token
$0.00000015
$0.15 per 1M, 3:1 mix
Context window
262K
max output 66K
Major features
Open weightsReasoningTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 92.4 GB |
| Q3_K_M | fair | 107 GB |
| Q4_K_Mrecommended | good | 133 GB |
| Q5_K_M | very good | 154 GB |
| Q6_K | excellent | 176 GB |
| Q8_0 | near-lossless | 227 GB |
| F16 | lossless | 423 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.10 | $0.30 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.10
- Output
- $0.30
- Blended (3:1)
- $0.15
Details
- Company
- Stepfun
- Version
- 3.5
- Family
- Step
- Released
- 2026-01-29
- Parameters
- 199.4B
- Max output
- 66K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago