Step 3.5 Flash with Jev
Step 3.5 Flash is a model from StepFun, released 2026-01-29. It costs $0.100 per million input tokens and $0.300 per million output tokens, reads up to 262K tokens of context, and writes up to 65,536 tokens in one reply. Through llm11, set model to stepfun/step-3.5-flash.
- Input price
- $0.100 / 1M
- Output price
- $0.300 / 1M
- Context window
- 262K tokens
- Max output
- 66K tokens
- Released
- 2026-01-29
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 82% of the 332 priced models we can call cost more.
Using Step 3.5 Flash with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Step 3.5 Flash does the answering when Jev sends it work, or when you name it yourself. At list price Step 3.5 Flash falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass stepfun/step-3.5-flash as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Step 3.5 Flash with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00011 | $0.110 |
| Question over retrieved documents | 4,000 / 500 | $0.00055 | $0.550 |
| Long document summary | 30,000 / 1,000 | $0.00330 | $3.30 |
Cheaper models to try
The catalogue has no benchmark score for Step 3.5 Flash, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Google Gemma 4 26B A4B | $0.090 | $0.300 | 262K | |
| OpenAI GPT-5 Nano | $0.050 | $0.400 | 400K | |
| Mistral Mistral Small 3.2 24B | $0.094 | $0.250 | 256K | |
| OpenAI gpt-oss-safeguard-20b | $0.075 | $0.300 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="stepfun/step-3.5-flash",
messages=[{"role": "user", "content": "Hello"}],
)More from StepFun
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Step 3.7 Flash | $0.200 | $1.15 | 262K |
Questions
- What is Step 3.5 Flash with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Step 3.5 Flash does the answering when Jev sends it work, or when you name it yourself. At list price Step 3.5 Flash falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass stepfun/step-3.5-flash as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Step 3.5 Flash a System One model?
- No. Step 3.5 Flash answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Step 3.5 Flash cost?
- $0.100 per million input tokens and $0.300 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00055, so a thousand of them is about $0.550. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Step 3.5 Flash context window?
- 262,144 tokens, with up to 65,536 tokens in a single reply.
- Does Step 3.5 Flash support tool calling and structured output?
- The catalogue lists tool calling and reasoning controls, but it does not list structured output.
- Can I use Step 3.5 Flash through llm11?
- Yes. Set model to stepfun/step-3.5-flash on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Step 3.5 Flash?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Step 3.5 Flash falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass stepfun/step-3.5-flash as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Step 3.5 Flash?
- Nearest in price and below it: Google Gemma 4 26B A4B at $0.090 in and $0.300 out, OpenAI GPT-5 Nano at $0.050 in and $0.400 out and Mistral Mistral Small 3.2 24B at $0.094 in and $0.250 out. The catalogue has no benchmark score for Step 3.5 Flash, so this is a price ordering. It does not claim these answer as well.