StepfunFreeOperational
Step 3.5 Flash
API model name: step-3.5-flash:free
Step 3.5 Flash is Stepfun's chat model, served on the Api.Airforce unified API. It has a 128K-token context window. It is available on the free tier at no per-token cost. Knowledge cutoff: 2025-05. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.
Pricing
Specifications
- Provider
- Stepfun
- Type
- chat model
- Context window
- 128K tokens
- Max output
- 8K tokens
- Knowledge cutoff
- 2025-05
- Input
- text
- Output
- text
Capabilities
Streaming
Benchmarks
Independent evaluations and measured speed from Artificial Analysis.
Intelligence Index
37.8/100
Coding Index
31.6/100
GPQA Diamond83%
Humanity's Last Exam19%
Output speed182.4 tok/s
Time to first token1.12 s
Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)
What is Step 3.5 Flash used for?
- Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
- Real-time experiences — stream tokens for responsive chat and apps.
Step 3.5 Flash vs. similar models
| Model | Intelligence | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Step 3.5 Flash | 37.8 | 128K | Free | Free |
| Gpt 5.1 | — | 400K | $0.27 | $2.13 |
| Gpt 5.1 Chat | — | — | $0.27 | $2.13 |
| Gpt 5.1 Codex Mini | 38.6 | — | $0.18 | $1.48 |
Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.
Related models
Gpt 5.1OpenAI · $0.27 / 1MGpt 5.1 ChatOpenAI · $0.27 / 1MGpt 5.1 Codex MiniOpenAI · $0.18 / 1MGpt 5.2OpenAI · $0.36 / 1MGpt 5.2 ChatOpenAI · $0.36 / 1MGpt 5.2 CodexOpenAI · $0.03 / 1MGpt 5.3 ChatOpenAI · $0.36 / 1MGpt 5.3 CodexOpenAI · $0.50 / 1MGpt 5.4OpenAI · $0.75 / 1MGpt 5.4 MiniOpenAI · $0.20 / 1MGpt 5.4 NanoOpenAI · $0.10 / 1MGpt 5.4 ProOpenAI · $13.28 / 1M
Step 3.5 Flash — frequently asked questions
- How much does Step 3.5 Flash cost?
- Step 3.5 Flash is available on the free tier at no token cost — create an API key and start building. Paid plans add higher rate limits.
- What is the context window of Step 3.5 Flash?
- Step 3.5 Flash supports a context window of up to 128K tokens. It can return up to 8K tokens in a single response.
- What can Step 3.5 Flash do?
- Step 3.5 Flash is Stepfun's chat model, accessible through the Api.Airforce API.
- Is Step 3.5 Flash free to use?
- Yes — Step 3.5 Flash is on the free tier. You can use it with an Api.Airforce API key at no cost.
- How do I use Step 3.5 Flash via the API?
- Step 3.5 Flash is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID step-3.5-flash:free with your Api.Airforce API key.
- Who makes Step 3.5 Flash?
- Step 3.5 Flash is Stepfun's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.
Loading live metrics…
Loading live metrics…
Loading live metrics…
Use Step 3.5 Flash via the API
OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass step-3.5-flash:free as the model.
cURL
curl https://api.airforce/v1/chat/completions \
-H "Authorization: Bearer $AIRFORCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "step-3.5-flash:free",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Python
from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
model="step-3.5-flash:free",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
model: "step-3.5-flash:free",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);