What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat Labby Stepfun·Released 28 May 2026
Step 3.7 Flash reads text, pictures and video and writes text, keeping about 260 pages in mind at once. You pick a high, medium or low thinking level to trade speed and cost against depth. StepFun designs it for coding, long jobs that use connected tools, filling in the exact tables you specify, and long-document work.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 66,57 DA | 382,76 DA |
| Cached tokens read | 13,31 DA |
per 1M tokens
Two companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| 66,57 DA | 382,76 DA | 13,31 DA | … | … | … | |
| 66,57 DA | 382,76 DA | 13,31 DA | … | … | … |
You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="stepfun/step-3.7-flash",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoningreasoning_effortinclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceAbout 0,26 DA per message. ↑ 66,57 DA · ↓ 382,76 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Step 3.7 Flash reads text, pictures and video and writes text, keeping about 260 pages in mind at once. You pick a high, medium or low thinking level to trade speed and cost against depth. StepFun designs it for coding, long jobs that use connected tools, filling in the exact tables you specify, and long-document work.
Deposit dinars with your Edahabia or CIB card. Every model, Step 3.7 Flash included, is paid from that balance. No foreign card, no conversion.
StepFun tags the model card English. Arabic, French and Darja are not named.
It reads text, images and video. Up to 262K tokens in one request, about 260 pages. It writes up to 173 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
Stepfun. Released 28 May 2026.
Step 5 Preview reads text, pictures and video and writes text, keeping about 1,000 pages in mind at once. StepFun calls it its flagship for long tasks: it does well at building software and at expert office work, finance above all, across big codebases and document sets, where it uses tools and refines its result step by step.
Step 3.5 Flash reads and writes text, thinks before it answers, and keeps about 260 pages in mind at once while staying fast on long inputs. StepFun calls it its most capable open model, released under the Apache 2.0 licence so you can download it and run it yourself, and it supports connected tools for agent work.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights
The model's weights are public.
Read a long spec with diagrams and list open questions
Images
Summarise a product demo video
Video
Run an agent with your tools
Uses your tools · Thinks first