---
title: "Step 3.7 Flash API pricing: 3 providers compared | BroadRouter"
description: "Step 3.7 Flash API price per token from 3 providers: lowest listed USD 0.20 input and USD 1.15 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/step-3.7-flash/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Step 3.7 Flash API pricing

Updated 2026-11-15

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 tie for the lowest blended standard price for Step 3.7 Flash; Featherless charges USD 0.20 per 1M input tokens and USD 1.15 per 1M output tokens. The median across 3 standard prices is USD 0.20 / USD 1.15. Each price is read from the provider's own pricing page.

StepFun · slug `step-3.7-flash` · up to 262,144 tokens of context · 3 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/).

## Does StepFun sell Step 3.7 Flash directly?

StepFun publishes no price for Step 3.7 Flash on its own API that we could find, so this page compares hosts only.

## Step 3.7 Flash model facts

Facts from StepFun's model card for [`stepfun-ai/Step-3.7-Flash`](https://huggingface.co/stepfun-ai/Step-3.7-Flash) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Step 3.7 Flash: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes. The weights are in a public Hugging Face repository (stepfun-ai/Step-3.7-Flash) with no access gate. | [Hugging Face model API](https://huggingface.co/api/models/stepfun-ai/Step-3.7-Flash), checked 2026-11-16 · Quote: “"private": false, "gated": false, 26 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | [StepFun model card metadata](https://huggingface.co/stepfun-ai/Step-3.7-Flash), checked 2026-11-16 · Quote: “license: apache-2.0” |
| Total parameters | 198B (196B language backbone + 1.8B vision encoder) | [StepFun model card](https://huggingface.co/stepfun-ai/Step-3.7-Flash), checked 2026-11-16 · Quote: “Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder” |
| Context length | Not found on StepFun's model card when we read it; see the context column in the price table | checked 2026-11-16 |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | [StepFun model card metadata](https://huggingface.co/stepfun-ai/Step-3.7-Flash), checked 2026-11-16 · Quote: “pipeline_tag: image-text-to-text” |
| Tool calling | Not found on StepFun's model card when we read it | checked 2026-11-16 |
| First published on Hugging Face (not necessarily the release date) | 2026-05-23 | [Hugging Face model API](https://huggingface.co/api/models/stepfun-ai/Step-3.7-Flash), checked 2026-11-16 · Quote: “"createdAt": "2026-05-23T02:13:46.000Z"” |

## Step 3.7 Flash price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest.

Step 3.7 Flash API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[Featherless](https://broadrouter.com/llm-api-pricing/providers/featherless/)** tied cheapest · `stepfun-ai/Step-3.7-Flash` · Note: Developer plan (per-token billing, from 50 USD a month in credits). Quote: “PRICING: INPUT $0.2 / CACHED $0.04 / OUTPUT $1.15” | USD 0.20 | USD 0.04 | USD 1.15 | USD 0.4375 | 262,144 | FP8 | [Featherless page](https://featherless.ai/models/stepfun-ai/Step-3.7-Flash) · checked 2026-11-15 · re-checked 2026-11-16 |
| 2 | **[GMI Cloud](https://broadrouter.com/llm-api-pricing/providers/gmi-cloud/)** tied cheapest · `stepfun-ai/Step-3.7-Flash` · Quote: “Price (per 1M tokens) Input $0.20 Output $1.15 Cache Read $0.04 Cache Write -” | USD 0.20 | USD 0.04 | USD 1.15 | USD 0.4375 | 256,000 | BF16 | [GMI Cloud page](https://console.gmicloud.ai/model/llm/stepfun-step-3-7-flash/824d96ea-74f3-42c1-aa61-c7a21c1e1449) · checked 2026-11-15 · re-checked 2026-11-16 |
| 3 | **[Novita AI](https://broadrouter.com/llm-api-pricing/providers/novita/)** tied cheapest · `stepfun/step-3.7-flash` · Quote: “Step 3.7 Flash 256K $0.2 /Mt · Cache Read $0.04 /Mt $1.15 /Mt” | USD 0.20 | USD 0.04 | USD 1.15 | USD 0.4375 | 262,144 | not stated | [Novita AI page](https://novita.ai/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Step%203.7%20Flash%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fstep-3.7-flash%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does Step 3.7 Flash cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=step-3.7-flash). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on Step 3.7 Flash, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **Featherless** | USD 30.06 | USD 53.73 | USD 218.70 |
| **GMI Cloud** | USD 30.06 | USD 53.73 | USD 218.70 |
| **Novita AI** | USD 30.06 | USD 53.73 | USD 218.70 |

For the support chatbot, the cheapest price (Featherless and 2 others, tied, USD 30.06 a month) saves USD 0 against the median (USD 30.06). For the coding agent the gap is USD 0 a month.

## Which Step 3.7 Flash provider is cheapest for your traffic?

All 3 providers charge the same standard price, USD 0.20 input and USD 1.15 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

Step 3.7 Flash: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **Featherless** | USD 0.4375 cheapest | USD 0.3775 cheapest | USD 0.3295 cheapest |
| **GMI Cloud** | USD 0.4375 cheapest | USD 0.3775 cheapest | USD 0.3295 cheapest |
| **Novita AI** | USD 0.4375 cheapest | USD 0.3775 cheapest | USD 0.3295 cheapest |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

All 3 providers publish a cached-input price below the input price: Featherless (80% off), GMI Cloud (80% off), Novita AI (80% off).

Context windows differ: 262,144 tokens at Featherless and Novita AI; 256,000 tokens at GMI Cloud. The cheapest row is not always the one that fits a long prompt.

## Estimate your own bill

-   [LLM API cost calculator with Step 3.7 Flash preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=step-3.7-flash): your traffic and cache rate, against any of 428 models.
-   [Token counter](https://broadrouter.com/tools/token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does Step 3.7 Flash compare with other StepFun models?

The StepFun models whose cheapest standard price is closest to Step 3.7 Flash's (USD 0.4375 blended):

StepFun models priced closest to Step 3.7 Flash
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [Step-3.5-Flash](https://broadrouter.com/llm-api-pricing/step-3.5-flash/) | USD 0.10 | USD 0.30 | 262,144 | 2 |
| [Step 5 Preview](https://broadrouter.com/llm-api-pricing/step-5-preview/) | USD 1 | USD 2.70 | 1,048,576 | 4 |

Priced closest from other makers: [DeepSeek V3](https://broadrouter.com/llm-api-pricing/deepseek-chat/) (DeepSeek, USD 0.4375) · [Qwen3 Coder 480B A35B](https://broadrouter.com/llm-api-pricing/qwen3-coder/) (Qwen, USD 0.4375) · [MiniMax M2.5](https://broadrouter.com/llm-api-pricing/minimax-m2.5/) (MiniMax, USD 0.44).

## Compare Step 3.7 Flash with

-   [Qwen3.8 27B vs Step 3.7 Flash](https://broadrouter.com/llm-api-pricing/compare/qwen3.8-27b-vs-step-3.7-flash/): API price side by side
-   [Step 3.7 Flash vs Step-3.5-Flash](https://broadrouter.com/llm-api-pricing/compare/step-3.7-flash-vs-step-3.5-flash/): API price side by side

Also compared: [vs Qwen3.8 27B](https://broadrouter.com/llm-api-pricing/compare/qwen3.8-27b-vs-step-3.7-flash/) · [vs Step-3.5-Flash](https://broadrouter.com/llm-api-pricing/compare/step-3.7-flash-vs-step-3.5-flash/).

[Every Step 3.7 Flash price comparison](https://broadrouter.com/llm-api-pricing/compare/#m-step-3.7-flash) · [All model-vs-model price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

[All 428 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the Step 3.7 Flash API cost per token?

From USD 0.20 per 1M input tokens (USD 0.0000002 per token) and USD 1.15 per 1M output tokens (USD 0.00000115 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.20 input and USD 1.15 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for Step 3.7 Flash?

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 are tied for the lowest price: Featherless, GMI Cloud and Novita AI, each USD 0.4375 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.20 (Featherless and 2 others, tied); for output alone, USD 1.15 (Featherless and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does StepFun sell Step 3.7 Flash on its own API?

StepFun publishes no price for Step 3.7 Flash on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Featherless at USD 0.20 / USD 1.15 per 1M tokens.

### Does Step 3.7 Flash have cached input pricing?

All 3 standard prices include one. The lowest is USD 0.04 per 1M at Featherless; the median is USD 0.04. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

### What is the Step 3.7 Flash context window?

Up to 262,144 tokens. 1 standard price comes with less, down to 256,000 tokens (GMI Cloud). Check the context column before you pick the cheapest row for long prompts. [Context window calculator](https://broadrouter.com/tools/context-window-calculator/).

### How much does a coding agent cost per month on Step 3.7 Flash?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 218.70 a month at Featherless, USD 218.70 at the median price and USD 218.70 at Novita AI. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=step-3.7-flash).

### Is Step 3.7 Flash free to use through an API?

No provider in our data lists a free price for Step 3.7 Flash as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is Step 3.7 Flash open source, with open weights, and what is its licence?

StepFun publishes the weights on Hugging Face as [`stepfun-ai/Step-3.7-Flash`](https://huggingface.co/stepfun-ai/Step-3.7-Flash), in a public repository with no access gate. The licence, as the [StepFun model card metadata](https://huggingface.co/stepfun-ai/Step-3.7-Flash) states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from StepFun's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does Step 3.7 Flash have?

Total parameters, as the [StepFun model card](https://huggingface.co/stepfun-ai/Step-3.7-Flash) states them: 198B (196B language backbone + 1.8B vision encoder). (checked 2026-11-16; BroadNet did not verify these figures.)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-step-3.7-flash&utm_content=page-cta) ·

**Sources**

-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/stepfun-ai/Step-3.7-Flash)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://console.gmicloud.ai/model/llm/stepfun-step-3-7-flash/824d96ea-74f3-42c1-aa61-c7a21c1e1449)
-   [Novita AI: pricing (checked 2026-11-14)](https://novita.ai/pricing)
