AI model comparison
Step 5 Preview vs Claude Sonnet 4.6
Side by side comparison of Step 5 Preview and Claude Sonnet 4.6 on pricing, benchmark scores, context window, and more.
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).
- Input / 1M
- $1
- Output / 1M
- $2.70
- Context
- 1M
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
- Input / 1M
- $3
- Output / 1M
- $15
- Context
- 1M
Comparing image generators? Compare image models
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Step 5 Preview
4.0x cheaper for a typical chat
Higher intelligence score
Claude Sonnet 4.6
30.1 vs 28.5 on Artificial Analysis
Larger context window
Tie
1M vs 1M tokens
Newer release
Step 5 Preview
Released October 8, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
Step 5 Preview vs Claude Sonnet 4.6 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $1 | $3 |
| Output tokensPer 1M tokens | $2.70 | $15 |
| Cached input (read)Per 1M tokens | $0.10 | $0.30 |
| Cache writePer 1M tokens | Not available | $3.75 |
| Web searchPer request | Not available | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Coding task
30K in, 4K out
Long document summary
150K in, 2K out
Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | ||
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Max output | 64K tokens | 128K tokens |
| Input types | Image, Text, Video | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low | Max, High, Medium, Low, None |
| Default reasoning effort | Medium | Medium |
| Release date | October 8, 2026 | February 17, 2026 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Not supported | Supported |
Our take
Step 5 Preview is 4.0x cheaper for a typical chat. Claude Sonnet 4.6 scores higher on the Artificial Analysis Intelligence Index (30.1 vs 28.5). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Step 5 Preview or Claude Sonnet 4.6 cheaper?
Step 5 Preview is cheaper for a typical chat (2K input tokens and 500 output tokens). Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens, while Claude Sonnet 4.6 costs $3 per 1M input tokens and $15 per 1M output tokens.
Which has a bigger context window, Step 5 Preview or Claude Sonnet 4.6?
Step 5 Preview supports up to 1M tokens of context, compared with 1M for Claude Sonnet 4.6.
Is Step 5 Preview smarter than Claude Sonnet 4.6?
On the Artificial Analysis Intelligence Index, Step 5 Preview scores 28.5 and Claude Sonnet 4.6 scores 30.1, putting Claude Sonnet 4.6 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Step 5 Preview and Claude Sonnet 4.6 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Step 5 Preview and Claude Sonnet 4.6 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Step 5 Preview and Claude Sonnet 4.6 at the same time. Compare the answers side by side and keep the best one.