Step 3.5 Flash
StepFun • llm
Grande modelo de linguagem (llm) desenvolvido pela StepFun — Intelligence Index 38/100 no Artificial Analysis; US$ 0.100/1M tokens de entrada; 153 tokens/s de velocidade.
Specifications
Context Window
—
Input Price/1M
$0.10
Output Price/1M
$0.30
Parameters
—
Speed
202 tok/s
Latency (TTFT)
838ms
Benchmarks
Step 3.5 Flash results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 33.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SciCode | 40.0 | 100.0 | — |
| AA Coding Index | 31.6 | 100.0 | Artificial Analysis official API |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 54.0 | 100.0 | — |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 26.0 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 83.0 | 100.0 | Artificial Analysis official API |
| IFBench | 67.0 | 100.0 | — |
| HLE | 23.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 94.0 | 100.0 | — |
Information
- Release date
- February 02, 2026
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: Step 3.5 Flash
What is Step 3.5 Flash?
Step 3.5 Flash is an AI model developed by StepFun, classified as a llm model. It focuses on text processing and natural language generation. As a proprietary model, it is available via StepFun's cloud API.
Pricing & Costs in 2026
Step 3.5 Flash is usage-based, priced at $0.1/1M input tokens and $0.3/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Benchmarks & Performance
Step 3.5 Flash was evaluated on 9 different benchmarks, covering categories like Agentic, Coding, Long Context, overall, Reasoning, Tool Use. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Step 3.5 Flash is suitable for a wide range of AI applications: high-volume chatbots and automated support, text generation, summarization, translation, and general assistance.
Comparison with Alternatives
In the 2026 AI model ecosystem, Step 3.5 Flash competes directly with similarly capable models. StepFun competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Step 3.5 Flash?
Step 3.5 Flash is an AI model developed by StepFun. It is a llm model.
How much does Step 3.5 Flash cost?
Step 3.5 Flash costs $0.1/1M input tokens and $0.3/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Step 3.5 Flash compare with other models?
In available benchmarks, Step 3.5 Flash scored: Terminal-Bench Hard: 33/100, SciCode: 40/100, AA Coding Index: 31.6/100. See the full table above for a detailed comparison.
Is Step 3.5 Flash open source?
No, Step 3.5 Flash is a proprietary model from StepFun. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Step 3.5 Flash best for?
Step 3.5 Flash excels at general-purpose language tasks.
Last updated: June 22, 2026 • View methodology →