Built for agents
Repeated tool calls, running and checking code, and revising over long tasks, with the whole context in view.
StepFun
Operational· checked every few minutesStep 5 Preview API
The Step 5 Preview API: StepFun's flagship for agentic work, 75% below StepFun's list price
Price per 1M tokens75%off
- Input
- $0.25
$1.00 - Output
- $0.68
$2.70 - Cached input
- $0.025
Model ID
step-5-previewchat.py
from openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)stream = client.chat.completions.create( model="step-5-preview", messages=[{"role": "user", "content": "Explain quicksort in two sentences."}], stream=True,)for chunk in stream: if chunk.choices: print(chunk.choices[0].delta.content or "", end="")Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs
- Context window
- 1M tokens
- Max output
- 64K tokens
- Reasoning
- low · medium · high
- Input
- Text, Image
- Released
- Sep 20, 2026
- Status
- Operational
Pricing
Step 5 Preview API pricing. A fraction of the list price.
Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.
| Rate | Zurelay | StepFun list | You save |
|---|---|---|---|
Input per 1M tokens | $0.25 | 75%off | |
Output per 1M tokens | $0.68 | 75%off | |
Cached input per 1M tokens | $0.025 | — | — |
One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.
Savings calculator
Move the sliders to your monthly usage.
Input tokens per month50M
Output tokens per month10M
Zurelay
$19.30
StepFun list price
$77.00
You save every month$57.70
$692.40 a year
Overview
What is Step 5 Preview?
Step 5 Preview is StepFun's flagship model for agentic work: software engineering, long tool-calling tasks and professional knowledge work, with particular strength in finance. The Zurelay Step 5 Preview API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 75% below StepFun's list price.
StepFun released Step 5 Preview on September 20, 2026, and published its open weights on October 15 under the StepFun Model License. It is a sparse mixture-of-experts model with 600B total parameters, 27B of them active per token, and a context window of up to 1M tokens. On Zurelay the model ID is step-5-preview, and it costs $0.25 per 1M input tokens and $0.68 per 1M output tokens.
StepFun built it for long agentic runs: repository-level coding across many files, frontend and visual work, and tasks that repeat tool calls, run and check their results, and revise. It also reads long documents, charts and screenshots for research and reports, and StepFun singles out finance, where quantitative reasoning meets financial data.
On StepFun's own tests at high effort it scores 93.5% on GPQA Diamond, 67.7% on DeepSWE v1.1 (GLM-5.3: 66.9%, Kimi K3: 67.5%) and 66.4% on FrontierFinance, ahead of GPT-6 Astra's 55.0% and behind Claude Opus 5's 69.7%. StepFun notes a gap to the frontier models on its longest coding tasks, and these are its own numbers, not independent ones.
Reasoning is always on. Set reasoning_effort to low, medium or high; StepFun recommends medium for most tasks, and temperature 1.0 with top_p 0.95. The model calls tools, follows a JSON schema in response_format and streams. On Zurelay it reads text and images and writes up to 64K tokens per answer. You pay $0.25 per 1M input tokens and $0.68 per 1M output tokens, against StepFun's list price of $1.00 and $2.70, with cached input at $0.025.
Strengths
Where Step 5 Preview shines. And what teams build with it.
Strong in finance
StepFun reports 66.4% on FrontierFinance, ahead of GPT-6 Astra and GLM-5.3, for analysis over financial data and documents.
Long context
A 1M-token window and up to 64K output tokens per answer. In our tests it found one fact buried in a 327K-token prompt.
Open weights
StepFun published the weights in October 2026, so prompts you build on Zurelay carry over to a self-hosted copy later.
Use cases
Coding agents
Repository-level changes across many files, with tool calls to run, test and fix the code.
Financial analysis
Models, reports and research over filings, tables and charts, where numbers have to add up.
Long documents
Contracts, codebases and research papers read whole in one request, up to 1M tokens.
Screenshots and charts
Read interfaces, charts and scanned pages from images alongside your text.
Get started
Call Step 5 Preview in three steps.
No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.
- 1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
- 2
Point your SDK at Zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1 - 3
Use step-5-preview
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
step-5-preview
Works with the tools you already use
Compare
Similar models. All on the same key.
73%off
GLM-5.3
$0.38 / $1.21 per 1M tokens
Pick GLM-5.3, Z.ai's flagship, for coding and terminal work: it scores 41.9% on Terminal-Bench v4 against Step 5 Preview's 33.3%.
GLM-5.3 API84%off
DeepSeek V4 Pro 0813
$0.23 / $0.62 per 1M tokens
Pick DeepSeek V4 Pro 0813 for text-only coding and agent work at a similar price.
DeepSeek V4 Pro 0813 API60%off
Kimi K3.1 Pro
$0.80 / $4.00 per 1M tokens
Pick Kimi K3.1 Pro, Moonshot's newest flagship, for the hardest coding, 3D and financial research work, at a higher price.
Kimi K3.1 Pro APIHow much does the Step 5 Preview API cost?
Step 5 Preview costs $0.25 per 1M input tokens and $0.68 per 1M output tokens on Zurelay, with cached input at $0.025. StepFun's list price is $1.00 input and $2.70 output, so you save 75%. One rate applies at every prompt length, and reasoning tokens count as output, as on StepFun's own API.
How do I call the Step 5 Preview API with the OpenAI SDK?
Install the official OpenAI SDK, set the base URL to https://api.zurelay.com/v1 and use your Zurelay API key. Then pass model "step-5-preview" to chat.completions.create. StepFun recommends temperature 1.0 and top_p 0.95, and a reasoning_effort of medium for most tasks.
What is the Step 5 Preview context window?
Step 5 Preview has a 1M-token context window and writes up to 64K output tokens per answer, reasoning included. On Zurelay it takes text and images and returns text.
Can Step 5 Preview read images, video or PDFs on Zurelay?
Images, yes: send them as https links or base64 data URLs in image_url parts. StepFun's own API also takes video, but Zurelay doesn't serve video or PDFs for Step 5 Preview yet, and a request that includes one is turned away with a clear error before anything is billed.
Can I turn reasoning off on Step 5 Preview?
No. Step 5 Preview always reasons before it answers. Set reasoning_effort to low for the quickest answers; a request for none runs at low.
Does Step 5 Preview support tool calling and tool_choice?
Yes, it calls tools, but StepFun's API ignores tool_choice. On Zurelay a tool forced by name is still called, and tool_choice "none" is kept, with the tools left out of that request. "required" without a tool name can't be enforced, so name the tool you need instead.
Does Step 5 Preview support JSON mode and structured outputs?
Yes. Send response_format with json_schema or json_object and the answer comes back as the JSON alone. Zurelay also passes your schema to the model in words, so the answer follows it on every route.
Is Step 5 Preview on Zurelay the same model StepFun serves?
Yes. Requests go to step-5-preview itself; Zurelay doesn't swap in a smaller or substitute model. Only smart routing, which you turn on yourself, can answer with another model when Step 5 Preview is down, and the x-zurelay-model header names the model that answered. Output is sampled, so wording varies from run to run, as it does on StepFun's own API. Zurelay is an independent service and is not affiliated with StepFun.
More models on Zurelay
All models- Zurelay Auto APIfrom $0.025 / $0.12 per 1M tokensAuto
- Claude Opus 5.5 API$1.40 / $7.00 per 1M tokens−65%
- GPT-6 Astra API$2.50 / $12.50 per 1M tokens−75%
- Nano Banana 2.1 APIfrom $0.03 per image−11%
- Nano Banana Pro APIfrom $0.035 per image−74%
- Nano Banana 2 APIfrom $0.025 per image−63%
- Nano Banana 2 Lite API$0.016 per image−52%
- Claude Sonnet 5.5 API$0.79 / $3.95 per 1M tokens−61%
- Claude Haiku 5.5 API$0.04 / $0.20 per 1M tokens−60%
- GPT-6.1 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6.1 Terra API$0.25 / $1.25 per 1M tokens−75%
- GPT-6 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Luna API$0.025 / $0.125 per 1M tokens−75%
- Grok 4.7 API$0.70 / $2.10 per 1M tokens−65%
- Muse Wonder API$1.20 / $6.00 per 1M tokens−70%
- MiMo V2.6 Pro API$0.32 / $0.64 per 1M tokens−26%
- MiMo V2.6 Flash API$0.075 / $0.15 per 1M tokens−46%
- DeepSeek V4.1 Flash 1017 API$0.03 / $0.12 per 1M tokens−90%
- DeepSeek V4.1 Flash API$0.03 / $0.12 per 1M tokens−90%
- DeepSeek V4 Flash API$0.03 / $0.12 per 1M tokens−90%
- DeepSeek V4 Flash 0731 API$0.029 / $0.087 per 1M tokens−69%
- DeepSeek V4 Pro 0813 API$0.23 / $0.62 per 1M tokens−84%
- Claude Fable 5.1 API$3.50 / $17.50 per 1M tokens−65%
- Claude Fable 5 API$3.50 / $17.50 per 1M tokens−65%
- Claude Opus 5 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.8 API$2.40 / $12.00 per 1M tokens−52%
- Claude Opus 4.7 API$1.78 / $8.93 per 1M tokens−64%
- Claude Opus 4.6 API$2.40 / $12.00 per 1M tokens−52%
- Claude Haiku 4.5 API$0.54 / $2.70 per 1M tokens−46%
- GPT-5.6 Sol API$1.14 / $5.70 per 1M tokens−72%
- GPT-5.6 Terra API$0.54 / $3.26 per 1M tokens−73%
- GPT-5.6 Luna API$0.08 / $0.49 per 1M tokens−59%
- Gemini 4 Argon API$0.80 / $4.00 per 1M tokens−60%
- Gemini 3.1 Pro API$0.50 / $3.45 per 1M tokens−71%
- Gemini 3.8 Flash API$0.22 / $1.10 per 1M tokens−71%
- Gemini 3.7 Flash API$0.32 / $1.59 per 1M tokens−58%
- Gemini 3.5 Flash-Lite API$0.12 / $1.04 per 1M tokens−58%
- Gemini 3.1 Flash-Lite API$0.10 / $0.59 per 1M tokens−61%
- GLM-5.3 API$0.38 / $1.21 per 1M tokens−73%
- GLM-5.2 API$0.38 / $1.21 per 1M tokens−73%
- GLM-5.3 Flash API$0.058 / $0.19 per 1M tokens−62%
- GLM-5.3 FlashX API$0.12 / $0.40 per 1M tokens−68%
- Kimi K3.1 Pro API$0.80 / $4.00 per 1M tokens−60%
- Kimi K3.1 Pro Highspeed API$3.30 / $16.50 per 1M tokens−18%
- Kimi K3 API$1.27 / $6.37 per 1M tokens−58%
- Qwen 3.8 Max API$1.20 / $3.60 per 1M tokens−40%
- Qwen 3.8 Flash API$0.07 / $0.22 per 1M tokens−53%
- MiniMax M3.1 Flash API$0.06 / $0.24 per 1M tokens−60%
- Qwen 3.8 Omni Flash API$0.075 / $0.235 per 1M tokens−50%
- HY4 Preview API$0.40 / $1.20 per 1M tokens−52%
- MiniMax M3 API$0.13 / $0.51 per 1M tokens−57%
- GPT Image 2.5 Flare APIfrom $0.028 per image−47%
- GPT Image 2.5 Sunburst APIfrom $0.026 per image−51%
- GPT Image 2 API$0.02 per image−62%
- Grok Imagine Image 2.0 APIfrom $0.045 per image−25%
- FLUX 3 Image APIfrom $0.04 per image−17%
- Seedance 2.5 APIfrom $0.135 per secondVideo
- Seedance 2.0 APIfrom $0.097 per secondVideo
- Seedance 2.0 Fast APIfrom $0.074 per secondVideo
- Kling 4.0 APIfrom $0.15 per secondVideo
- Seedance 2.0 Mini APIfrom $0.047 per secondVideo
- Kling 3.0 APIfrom $0.125 per secondVideo
- Gemini Omni Flash APIfrom $0.042 per secondVideo
- Wan 3.0 APIfrom $0.039 per secondVideo
- Veo 3.1 Fast APIfrom $0.025 per secondVideo
- Grok Imagine Video 1.5 APIfrom $0.071 per secondVideo
- Vidu Q3 Turbo APIfrom $0.03 per secondVideo
- PixVerse V6 APIfrom $0.019 per secondVideo
- MiniMax H3 APIfrom $0.039 per secondVideo
- Gemini 3.8 Flash TTS API$0.30 / $5.40 per 1M tokens−40%
- Gemini 3.1 Flash TTS API$0.60 / $12.00 per 1M tokens−40%
- Gemini 2.5 Pro TTS API$0.60 / $12.00 per 1M tokens−40%
- Gemini 2.5 Flash TTS API$0.30 / $6.00 per 1M tokens−40%
- Jev 1.14 API$0.024 per 1M input tokens−43%
- Jev 1.13 API$0.035 per 1M input tokens−17%
Stop paying list price.
Start saving today.
Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.