AIHubMixAIHubMix

StepFun Models

4 modelsGeneral models from $0.11/M inputUp to 256K context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

489M

Requests

2.7K

Models in use

4 of 4

Tokens per day

063.2M126M07-1307-2007-2708-0308-102026-07-13 — 6,167,990 tokens2026-07-14 — 49,816,400 tokens2026-07-15 — 35,905,675 tokens2026-07-16 — 508,620 tokens2026-07-17 — 4,793,185 tokens2026-07-18 — 90,625 tokens2026-07-19 — 873,905 tokens2026-07-20 — 49,615 tokens2026-07-21 — 26,060 tokens2026-07-22 — 3,688,905 tokens2026-07-23 — 8,890,865 tokens2026-07-24 — 671,600 tokens2026-07-25 — 85,902,555 tokens2026-07-26 — 26,016,605 tokens2026-07-27 — 58,426,120 tokens2026-07-28 — 40,326,005 tokens2026-07-29 — 15,170 tokens2026-07-30 — 378,045 tokens2026-07-31 — 33,323,045 tokens2026-08-01 — 3,755 tokens2026-08-02 — 7,065 tokens2026-08-03 — 1,984,110 tokens2026-08-04 — 97,650 tokens2026-08-05 — 126,332,130 tokens2026-08-06 — 3,639,110 tokens2026-08-07 — 170,945 tokens2026-08-08 — 190,815 tokens2026-08-09 — 1,355 tokens2026-08-10 — 14,225 tokens2026-08-11 — 198,685 tokens

Which models that traffic went to

  1. step-3.5-flash63.0%308M
  2. step-3.7-flash37.0%181M

Share of 489M tokens. 2 models with traffic report no token counts and cannot be ranked here, including step-2-16k and stepfun-ai/step3 — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 4 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 4 StepFun Models

Open in model list
StepFun models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
step-3.5-flashTakes text, vision, returns text.256K$0.11$0.33/M—
step-3.7-flashTakes text, vision, returns text.256K$0.22$1.32/M$0.04/M
stepfun-ai/step3—$1.10$2.75/M—
step-2-16k—$2.00$2.00/M—

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

step-3.5-flash vs step-3.7-flashqwen3.8-max-preview vs step-3.5-flashkimi-k3 vs step-3.5-flashglm-5.2 vs step-3.5-flashgrok-4.5 vs step-3.5-flash

StepFun on AIHubMix

Which StepFun model should I start with?

step-3.5-flash at $0.11/M input — the cheapest entry here that declares a token price, and it carries a 256K context. Move up to step-2-16k when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (stepfun-ai/…), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example step-3.7-flash bills cache hits at 20% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate StepFun account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 models

Start calling StepFun in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect