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....
Updated 24 min ago · first seen 11 Sept 2026
model_01M294WW5QV0E1S0GS8B5HA1CP
- Context
- 256K tokens
- T2 · 24 min ago
- Released
- 29 Jan 2026
- T2 · 2 h ago
Specification
- Release date
- 29 Jan 2026
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Status
- deprecated
Source:Artificial AnalysisT2observed 24 min agomedium
- Openness
- open-weights
Source:Artificial AnalysisT2observed 24 min agomedium
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 24 min agomedium
- Max output
- 65.5K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Hugging Face repo
- stepfun-ai/Step-3.5-Flash
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Aa median output tokens per second
- 205.1
Source:Artificial AnalysisT2observed 24 min agomedium
- Openrouter id
- stepfun/step-3.5-flash
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, max_tokens, reasoning, temperature, tool_choice, tools, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
16
Source tiers
T216
Freshest observation
24 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
No
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 24 min agomedium
- Max output
- 65.5K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 94.44% | pass^1 | aa_slug=step-3-5-flash-0202 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 16.62 | index | aa_slug=step-3-5-flash-0202 · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 83.13% | accuracy | aa_slug=step-3-5-flash-0202 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 21.13% | accuracy | aa_slug=step-3-5-flash-0202 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 64.56% | accuracy | aa_slug=step-3-5-flash-0202 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 27.27% | accuracy | aa_slug=step-3-5-flash-0202 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterstepfun/step-3.5-flash | $0.10 | $0.30 | — | — | 262.1K | 29 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
No hardware estimate available
Ancestors 0
None recorded.
This model
Step 3.5 Flash
Quantizations 0
None recorded.
Descendants 2
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Max output
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 65.5K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Step 3.5 Flash scores 27.27% on Terminal-Bench
artificial_analysisStep 3.5 Flash scores 94.44% on τ²-bench
artificial_analysisStep 3.5 Flash scores 64.56% on IFBench
artificial_analysisStep 3.5 Flash scores 21.13% on Humanity's Last Exam
artificial_analysisStep 3.5 Flash scores 16.62 on Artificial Analysis Intelligence Index
artificial_analysisStep 3.5 Flash: context length changed from 262144 to 256000
Context window262.1K tokens→256K tokensartificial_analysisOpenRouter lists Step 3.5 Flash at $0.1 in / $0.3 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 24 min ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 29 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/cerebras/Step-3.5-Flash-REAP-149B-A11B | model_page | T2· Quality secondary | 2 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/cerebras/Step-3.5-Flash-REAP-121B-A11B | model_page | T2· Quality secondary | 2 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.