step-5-preview
StepFun/Open weights/1 provider
Step 5 Preview is StepFun's flagship model for agentic work, a sparse Mixture-of-Experts model with 600B total and 27B active parameters, a 1M token context window, and text and image input. It is built for software engineering, long horizon agentic execution with repeated tool calls, and professional knowledge work, with particular strength in finance.MoreLess
Which id to call
step-5-previewRequesty routes this id across every provider serving step-5-preview, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
From /1M input
$1.00
DeepInfra Inc.
Context
1.0M
66K output
Endpoints
1
1 region
Regions
1
chat
Capabilities 5/8
1 endpoint / 1 region
Providers serving step-5-preview
Provider prices, per 1M tokens. Pay as you go adds 5%, or 0% on your own keys.
| Rank | Privacy | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  DeepInfra Inc. | Global | 1.0M | $1.00 | $2.70 | $0.05 | zdr |
A column is blank where no qualifying sample exists, and every row links to that provider's endpoint page.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
step-5-previewRequesty routes this id across every provider serving step-5-preview, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="step-5-preview", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Artificial Analysis
Benchmark scores
Artificial Analysis Intelligence Index: a composite of multiple evaluations measuring overall model capability.
Scores from artificialanalysis.ai. They measure the model, not the provider, so they are the same on every endpoint above.
1
More from StepFun
Reference
step-5-preview questions
Which providers serve step-5-preview?
step-5-preview is available from 1 provider through Requesty: DeepInfra Inc.. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does step-5-preview cost?
Pricing starts at $1.00 per million input tokens and $2.70 per million output tokens on DeepInfra Inc., the cheapest endpoint. Prices vary by provider and region; the table above shows every endpoint. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
Is step-5-preview open weights?
Yes. step-5-preview is an open-weights model from StepFun, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of step-5-preview?
step-5-preview supports up to 1.0M tokens of context, with up to 66K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
How do I use step-5-preview with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "step-5-preview" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call step-5-preview by its managed id or a provider id?
Use the managed id, "step-5-preview". Requesty picks which of the 1 provider serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. Send a provider id like "deepinfra/step-5-preview" only when you need one specific deployment and want no failover.
Route step-5-preview through one endpoint
One key for 1 provider on this model and 600+ others. No markup on provider prices, automatic failover, caching built in.