# Step 3.7 Flash

> StepFun's fast flash tier. 256K context, multimodal input, tool calling. Cheap throughput.

Human version: https://kymaapi.com/models/step-3.7-flash
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `step-3.7-flash` — pass this as `model` in the request body
- **Creator**: StepFun
- **Released**: 2026-05-28
- **Context window**: 256K tokens
- **Max output**: 8K tokens per response — a hard ceiling, not a default
- **Price**: $0.27 in / $1.553 out per 1M, cached input 10%
- **Capabilities**: tools, vision, reasoning, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "step-3.7-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

Step 3.7 Flash is a fast, low-cost model optimized for high-throughput chat and bulk processing. Reach for it when you need to handle text, image, or video inputs at scale with tool calling and reasoning enabled.

## About

Created by stepfun, it supports a 256,000-token context window and accepts text, image, and video inputs while returning text. It includes native support for tool calling, reasoning, and structured outputs.

On Kyma, requests are routed through an OpenAI-compatible endpoint with automatic failover if a serving path degrades. Prompt prefixes are cached at 10% of the standard input rate.

The model caps output at 8,192 tokens, making it suitable for conversational and extraction workflows rather than long-form generation.

## Use cases

- **Bulk Chat Processing** — Route high-volume conversational workloads with low latency and minimal overhead.
- **Multimodal Input Analysis** — Extract information from text, images, and video streams in a single request.
- **Tool-Driven Workflows** — Execute function calls and structured data extraction for automated pipelines.
- **Long-Context Summarization** — Process documents up to 256K tokens while maintaining fast response times.

## Not ideal for

It is not suited for tasks requiring outputs longer than 8,192 tokens or heavy creative writing where maximum reasoning depth is prioritized over speed and cost.

## Pick something else when

- You need deeper reasoning or longer outputs → `qwen-3.7-max`, `gpt-5.6-terra`
- You need specialized code generation → `qwen-3-coder`, `kimi-k3`
- You need higher-tier multimodal reasoning → `gemini-3.5-flash-lite`, `gemini-3.6-flash`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by StepFun: https://kymaapi.com/models?q=StepFun