Step 5 Preview
by StepFun · stepfun/step-5-preview
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
- Input / 1M tokens
- $1.00
- Output / 1M tokens
- $2.70
- Context
- 1.05M
Specs
| Input price | $1.00 / 1M tokens |
|---|---|
| Output price | $2.70 / 1M tokens |
| Cached input | $0.10 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 64K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Oct 8, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
3 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Featherless | fp4 | 262K | 32.8K | $1.00 | $2.70 | $0.10 | 100% | 3.08 s | 28 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 944K | $1.00 | $2.70 | $0.10 | 0% | 952 ms | 141 tok/s | Code -5 | |
| StepFun | fp8 | 1M | 64K | $1.00 | $2.70 | $0.10 | 100% | 3.51 s | 103 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#7
by tokens, Oct 29, 2026
1.18T
tokens that day · 7 days +266%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- StepFun
Step 3.7 Flash
- Input
- $0.20
- Output
- $1.15
- Context
- 262K
- StepFun
Step 3.5 Flash
- Input
- $0.10
- Output
- $0.30
- Context
- 262K
- OpenAI
GPT-6.1 Terra
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M
- OpenAI
GPT-6.1 Terra Pro
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M
- Google
Gemini 4 Argon (batch)
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M
- OpenAI
GPT-6.1 Sol Pro (batch)
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M