Step 3.5 Flash 2603 API Pricing
StepFun · released Apr 2, 2026 · 256K context · API model ID step-3.5-flash-2603
Step 3.5 Flash 2603 by StepFun API pricing: $0.10 per 1M input tokens and $0.30 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $0.10 |
| Output | $0.30 |
| Cache read | $0.02 |
| Cache write | Not published |
StepFun's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$75.00
per month
- per day
- $2.50
- per request
- $0.00025
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $75.00/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $142.50/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $72.00/mo |
Context and capabilities
- Context
- 256,000 tokens
- Max output
- 256,000 tokens
- Input
- text
- Output
- text
- Knowledge cutoff
- January 2025
- Open weights
- Yes
- Tool calling
- Yes
- Reasoning
- Yes
- Structured outputs
- No
Capabilities and limits as listed by models.dev.
Similarly priced models
- Claude Haiku 5.5 · $0.10 in / $0.50 out
- GPT-6 Luna · $0.10 in / $0.50 out
- Qwen3.8 Flash · $0.15 in / $0.47 out
- DeepSeek V4.1 Flash · $0.30 in / $1.20 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does Step 3.5 Flash 2603 cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Step 3.5 Flash 2603 costs about $75.00 per month at StepFun's list prices ($0.10 per 1M input tokens, $0.30 per 1M output tokens).
- Does Step 3.5 Flash 2603 support prompt caching?
- Yes. Cached input costs $0.02 per 1M tokens, compared with $0.10 for regular input.
- How long is Step 3.5 Flash 2603's context window?
- Step 3.5 Flash 2603 accepts up to 256,000 tokens (256K) of context and returns up to 256,000 tokens per response.