AI Recommendation
Should you use step-3.7-flash?
step-3.7-flash is listed for chat workloads and supports a 262K context window.
Use it when Kilo Code's free tier is enough for evaluation, demos, or light production traffic.
step-3.7-flash Free API on Kilo Code
Free APINewer StepFun flash model for faster agents, coding, and multimodal prompts
Free APIOpenAI compatibleReasoningTool callingTextImageVideo
API Details
Copy-ready connection details
Base URL
https://api.kilo.ai/api/gateway Model ID
stepfun/step-3.7-flash:free API format OpenAI-style
Technical Details
step-3.7-flash specifications
Context window 262K
Max output 262K
Status Online
Knowledge cutoff 2026-03-01
Released May 29, 2026
Last updated Aug 6, 2026
Free listing since May 29, 2026
Input text, image, video
Output text
Capabilities reasoning, tool calling, file attachments, temperature control
Open weights Yes
Weights Hugging Face
External benchmark references
| Benchmark | Score | Metric | Date |
|---|---|---|---|
| SWE-Bench Pro | 56.3 | resolve rate | 2026-05-29 |
| SWE-Bench Verified | 76.5 | resolved | 2026-05-29 |
| Terminal-Bench | 59.6 | success rate | 2026-05-29 |
| Humanity's Last Exam | 47.2 | accuracy | 2026-05-29 |
Best for
- Chat
Strengths & Weaknesses
Strengths
- Long context window
- Reasoning mode listed
- Tool calling support
- Open weights available
Watch outs
- Free-tier rate limits apply
Benchmark Overview
Benchmark signals for step-3.7-flash
Intelligence General reasoning and instruction following
30.3/100 Coding Programming and code generation
39.6/100 Agentic Tool use and multi-step tasks
21.5/100 Speed Observed generation speed
364 tok/s Context Maximum listed context window
262K Pricing
step-3.7-flash pricing per 1M tokens
Input $0.2 per 1M tokens
Output $1.15 per 1M tokens
Free access Available Kilo Code
Rate limit ~200 req/hr provider policy
Availability
step-3.7-flash availability by provider
We only found this step-3.7-flash listing on Kilo Code in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | stepfun/step-3.7-flash:free | Free tier | 262K | OpenAI-style | ~200 req/hr |
Compare
step-3.7-flash alternatives to consider
| Model | Provider | Context | Access |
|---|---|---|---|
| nvidia/nemotron-3-ultra-550b-a55b:free | Kilo Code | 1.0M | Free tier |
| nvidia/nemotron-3-super-120b-a12b:free | Kilo Code | 262K | Free tier |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Kilo Code | 256K | Free tier |
| inclusionai/ling-3.0-flash:free | Kilo Code | 262K | Free tier |
| poolside/laguna-s-2.1:free | Kilo Code | 262K | Free tier |
Typical Use Cases
step-3.7-flash use cases
Chat
step-3.7-flash is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
FAQ
step-3.7-flash free API FAQ
Is step-3.7-flash free to use?
step-3.7-flash is listed with free API access on Kilo Code, subject to the provider's quota and account policy.
What is the step-3.7-flash model ID?
The model ID shown in this catalog is stepfun/step-3.7-flash:free.
What are the step-3.7-flash free tier rate limits on Kilo Code?
The listed free tier limit is ~200 req/hr. Limits can change per account tier, so confirm against the provider dashboard.
What context window does step-3.7-flash support?
The listed context window is 262K tokens with up to 262K output tokens.
More about step-3.7-flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.
For API keys, setup steps, and provider-level limits, see the Kilo Code provider page.