Stepfun model
Step 5 Preview API cost calculator
Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens on the Stepfun API, with a 1M-token context window. A typical request (2K input, 500 output tokens) costs $0.0034 — about $101/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Step 5 Preview
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0013 | $1.31 |
| RAG query with context | 4,000 / 500 | $0.0053 | $5.35 |
| Document summarization | 20,000 / 1,000 | $0.02 | $22.70 |
| Agent coding session | 100,000 / 5,000 | $0.11 | $114 |
Step 5 Preview vs other Stepfun models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Step 5 Preview | $1 | $2.70 | 1M |
| Step 3.7 Flash | $0.20 | $1.15 | 262K |
| Step 3.5 Flash | $0.10 | $0.30 | 262K |
Frequently asked questions
How much does Step 5 Preview cost per 1M tokens?
According to current pricing data, Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens. Processing 1M tokens each way costs $3.70.
What does a typical API request to Step 5 Preview cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0034. At 1,000 requests per day that is $3.35 daily, or about $101 per month.
What is Step 5 Preview's context window?
Step 5 Preview supports a 1M-token context window (1,000,000 tokens).
Does Step 5 Preview support prompt caching?
Yes. Cached input tokens cost $0.05 per 1M — a 95% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Step 5 Preview?
DeepSeek Flash Latest from ~deepseek is currently the cheapest comparable option at $0.00 per 1M input tokens versus $1 for Step 5 Preview — roughly 10000x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Step 5 Preview vs DeepSeek Flash Latest pricing, or run Step 5 Preview head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.