StepFun: Step 3.7 Flash
Step 3.7 Flash is a reasoning model from StepFun released on May 29, 2026. It reads text, images and video and writes text, with a 256K token context window and up to 256K tokens per reply.
Show moreShow less
It costs $0.185 per million input tokens and $1.11 per million output tokens. Cached input bills at $0.037, 80% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
19 providers serve it, including Hugging Face, Novita AI and Vercel AI Gateway.
- Modalities
- In / out price
- $0.185 / $1.11 per 1M
- Context
- 256K
- Max output
- 256K
- Released
- May 29, 2026
- Knowledge cutoff
- Mar 2026
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Step 3.7 Flash pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.185 / 1M tokens | |
|---|---|---|
| Output | $1.11 / 1M tokens | |
| Cached input (read) | $0.037 / 1M tokens | 80% off input |
Step 3.7 Flash providers
19 providers serve it, including Hugging Face, Novita AI and Vercel AI Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| StepFun (China) First party | $0.185 | $1.11 | $0.037 | 256K | 256K |
| Hugging Face | $0.20 | $1.15 | – | 262K | 256K |
| Novita AI | $0.20 | $1.15 | $0.04 | 262K | 256K |
| Vercel AI Gateway | $0.20 | $1.15 | $0.04 | 256K | 256K |
| StepFun (Global) | $0.185 | $1.11 | $0.037 | 256K | 256K |
| Ambient | $0.19 | $1.14 | $0.03 | 262K | 262K |
| DevPass (LLM Gateway) | $0.20 | $1.15 | $0.04 | 262K | 256K |
| Eden AI | $0.20 | $1.15 | $0.04 | 262K | 256K |
| EmpirioLabs AI | $0.20 | $1.15 | $0.04 | 256K | 131K |
| Kilo Gateway | $0.20 | $1.15 | $0.04 | 256K | 230K |
| LLM Gateway | $0.20 | $1.15 | $0.04 | 262K | 256K |
| NanoGPT | $0.20 | $1.15 | $0.04 | 262K | 256K |
Showing 12 of 19 providers: the lab first, then the major clouds, then the cheapest resellers.
What Step 3.7 Flash costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Step 3.7 Flash through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Step 3.7 Flash
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 41.8
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 65 providers.
by z-aiAug 21, 20261M context$0.15/M input tokens$0.50/M output tokens65 providers
- Index 39.8
Reads text, images and video. Tool calling, structured output, reasoning. Served by 23 providers.
by qwenAug 26, 20261M context$0.15/M input tokens$0.47/M output tokens23 providers
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 5 providers.
by qwenAug 27, 2026$0.20/M input tokens$0.50/M output tokens5 providers
- Index 29.2
Reads text, images and video. Tool calling, structured output, reasoning. Served by 42 providers.
by minimaxMay 31, 20261M context$0.30/M input tokens$1.20/M output tokens42 providers
- Index 37.9
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 17 providers.
by xiaomiSep 22, 20261.05M context$0.14/M input tokens$0.28/M output tokens17 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 23 providers.
by googleJun 17, 2025$0.10/M input tokens$0.40/M output tokens23 providers
More from StepFun
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 11 providers.
by stepfunSep 16, 2026$0.959/M input tokens$2.74/M output tokens11 providers
StepAudio 2.5 ASR
TranscriptionTurns speech into text. Served by 2 providers.
by stepfunApr 24, 20262 providers
StepAudio 2.5 TTS
SpeechTurns text into spoken audio. Served by 2 providers.
by stepfunApr 16, 20262 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 6 providers.
by stepfunApr 2, 2026$0.10/M input tokens$0.30/M output tokens6 providers
Step TTS 2
SpeechTurns text into spoken audio. Served by 2 providers.
by stepfunMar 1, 20262 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 13 providers.
by stepfunJan 29, 2026$0.10/M input tokens$0.30/M output tokens13 providers
Step 3.7 Flash questions
How much does the Step 3.7 Flash API cost?
$0.185 per million input tokens and $1.11 per million output tokens, with cached input at $0.037. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Step 3.7 Flash?
256,000 tokens of input, and it can write up to 256,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Step 3.7 Flash?
19 providers serve it, including Hugging Face, Novita AI and Vercel AI Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Step 3.7 Flash support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Step 3.7 Flash open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Step 3.7 Flash released?
May 29, 2026, with training data up to Mar 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Step 3.7 Flash?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting