← Model list
Step 3.5 Flash
stepfun·stepfun/step-3.5-flash-2·GA·Open weights
StepFun flash lane for quick multimodal reasoning and coding assistance
At a glance
Official price$0.10 / $0.30 per 1M
Cache read $0.02 · StepFun (Global)
Lowest paid$0.09 / $0.30
Eden AI Gateway · 1.1× spread
1 more $0 channels
Context256,000
⚠ Providers report 256,000–262,144; the table below is authoritative
Output limit256,000
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-01
Released / updated2026-01-29 / 2026-02-13
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence26
Value182
Coding—
Agentic—
Output speed224 tok/s
TTFT1.08 s
Value formulaIQ 26 ÷ min blended $0.142 = 182
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 12 providers9 with public prices · 1 free · 2 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia stepfun-ai/step-3.5-flash | First-party | Free | — | — | 256,000 | 16,384 | ||
| Eden AI deepinfra/stepfun-ai/Step-3.5-Flash | Gateway | $0.09 | $0.30 | $0.02 | — | 262,144 ⚠ | 256,000 | |
| NanoGPT stepfun-ai/step-3.5-flash | Gateway | $0.10 | $0.30 | $0.05 | — | 256,000 | 256,000 | |
| Hugging Face stepfun-ai/Step-3.5-Flash | Cloud | $0.10 | $0.30 | — | — | 262,144 ⚠ | 256,000 | |
| OpenRouter stepfun/step-3.5-flash | Gateway | $0.10 | $0.30 | — | — | 262,144 ⚠ | 65,536 | |
| StepFun (Global)Official step-3.5-flash | First-party | $0.10 | $0.30 | $0.02 | — | 256,000 | 256,000 | |
| StepFun (China)Official step-3.5-flash | First-party | $0.10 | $0.30 | $0.02 | — | 256,000 | 256,000 | |
| ZenMux stepfun/step-3.5-flash | Gateway | $0.10 | $0.30 | — | — | 256,000 | 64,000 | |
| EmpirioLabs AI step-3-5-flash | Gateway | $0.10 | $0.30 | $0.02 | — | 256,000 | 131,072 | |
| Kilo Gateway stepfun/step-3.5-flash | Gateway | $0.10 | $0.30 | — | — | 262,144 ⚠ | 65,536 | |
| StepFun Step Plan (China) step-3.5-flash | Gateway | — | — | — | — | 256,000 | 256,000 | hostTable.undisclosed |
| StepFun Step Plan (Global) step-3.5-flash | Gateway | — | — | — | — | 256,000 | 256,000 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Eden AI$24.60
2StepFun (Global) · Official$25.40
3StepFun (China) · Official$25.40
4EmpirioLabs AI$25.40
5NanoGPT$29.00
6Hugging Face$35.00
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to Eden AI to save $0.80/mo (3%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 31.6 | index | Source ↗ |
| SciCode | — | 40.4 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 27.3 | success rate | Source ↗ |
| SWE-Bench Verified | — | 74.4 | resolved | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = loweffort = mediumeffort = high
3 / 12 providers expose no reasoning control (reasoning_options: []).
Related models
GLM-4.7-Flashcheaper alternative$0 / $0Hy3cheaper alternative$0 / $0Nemotron 3 Nano 30B A3Bcheaper alternative$0 / $0Qwen3.7 Flashcheaper alternative$0.03 / $0.118
Price historyone sample accumulated per data sync
Input listOutput listMin blended