# Step 3.5 Flash

> Step 3.5 Flash is an open-weight language model from StepFun, released on 29 Jan 2026. It accepts text and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.09 per million input tokens and $0.30 per million output tokens (Vercel AI Gateway), across 4 providers we track.

Source page: https://www.aimodel.directory/models/step-3-5-flash
Last verified: 4 Oct 2026

## Specifications

- **Developer:** StepFun
- **Release date:** 29 Jan 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/stepfun-ai/Step-3.5-Flash)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/stepfun-ai/Step-3.5-Flash)
- **Parameters:** 199B (source: Hugging Face, https://huggingface.co/stepfun-ai/Step-3.5-Flash)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/stepfun/step-3.5-flash.toml)
- **Hugging Face:** stepfun-ai/Step-3.5-Flash (source: Hugging Face, https://huggingface.co/stepfun-ai/Step-3.5-Flash)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Vercel AI Gateway | $0.09 | $0.30 | $0.02 | 262K |
| SiliconFlow | $0.10 | $0.30 | – | 262K |
| Hugging Face Inference Providers | $0.10 | $0.30 | – | 262K |
| OpenRouter | $0.10 | $0.30 | – | 262K |

## FAQ

### What is the context window of Step 3.5 Flash?

Step 3.5 Flash has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.

### How much does the Step 3.5 Flash API cost?

Step 3.5 Flash is listed from $0.09 per million input tokens and $0.30 per million output tokens (Vercel AI Gateway). Prices last verified 4 Oct 2026.

### Is Step 3.5 Flash open source?

Step 3.5 Flash is an open-weight model: its weights are published on Hugging Face as stepfun-ai/Step-3.5-Flash under the apache-2.0 license. Check the license terms before commercial use.

### When was Step 3.5 Flash released?

StepFun released Step 3.5 Flash on 29 Jan 2026, according to models.dev.

### Which providers offer Step 3.5 Flash?

We track Step 3.5 Flash on 4 providers: Vercel AI Gateway, SiliconFlow, Hugging Face Inference Providers, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Step 3.5 Flash", https://www.aimodel.directory/models/step-3-5-flash