AI model comparison
Step 5 Preview vs Claude Haiku 4.5
Side by side comparison of Step 5 Preview and Claude Haiku 4.5 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
- 1.05M
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.
- Input / 1M
- $1
- Output / 1M
- $5
- Context
- 200K
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
1.3x cheaper for a typical chat
Higher intelligence score
Not available
Not enough benchmark data
Larger context window
Step 5 Preview
1.05M vs 200K tokens
Newer release
Step 5 Preview
Released October 8, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Claude Haiku 4.5Not availableCoding index
Claude Haiku 4.543.9Agentic index
Claude Haiku 4.58Pricing
Step 5 Preview vs Claude Haiku 4.5 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Claude Haiku 4.5 | |
|---|---|---|
| Input tokensPer 1M tokens | $1 | $1 |
| Output tokensPer 1M tokens | $2.70 | $5 |
| Cached input (read)Per 1M tokens | $0.10 | $0.10 |
| Cache writePer 1M tokens | Not available | $1.25 |
| 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
Claude Haiku 4.5$4.50Coding task
30K in, 4K out
Claude Haiku 4.5$50$23 cachedLong document summary
150K in, 2K out
Claude Haiku 4.5$160$25 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Claude Haiku 4.5 | |
|---|---|---|
| Context window | 1.05M tokens | 200K tokens |
| Max output | 64K tokens | 64K tokens |
| Input types | Image, Text, Video | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low | Not available |
| Default reasoning effort | Medium | Not available |
| Release date | October 8, 2026 | October 15, 2025 |
Features
Supported features
API features available for each model.
| Metric | Claude Haiku 4.5 | |
|---|---|---|
| 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 | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
- Step 5 Preview vs DeepSeek V4.1 Flash 1017
- Step 5 Preview vs DeepSeek V4.1 Flash
- Step 5 Preview vs GLM 5.3 Flash
- Step 5 Preview vs Hy4 preview
- Step 5 Preview vs GPT-6 Luna
- Step 5 Preview vs Claude Opus 5.5
- Step 5 Preview vs GLM 5.3
- Step 5 Preview vs MiMo-V2.6-Flash
- Step 5 Preview vs DeepSeek V4 Flash 0731
- Step 5 Preview vs Hy3
- Step 5 Preview vs GPT-6.1 Sol
- Step 5 Preview vs MiniMax M3.1 Flash
- Step 5 Preview vs Muse Spark 1.3
- Step 5 Preview vs Grok 4.7
- Step 5 Preview vs Qwen3.8 Max (0902)
- Step 5 Preview vs Gemini 3.8 Flash
- Step 5 Preview vs MiMo-V2.6-Pro
- Step 5 Preview vs MiniMax M3
- Step 5 Preview vs Solar Pro 4
- Step 5 Preview vs GLM 5.2
- Step 5 Preview vs DeepSeek V4 Pro 0813
- Step 5 Preview vs Mistral Large 4
- Step 5 Preview vs Qwen3.8 27B
- Step 5 Preview vs Gemini 3 Flash Preview
- Step 5 Preview vs DeepSeek V4 Pro 0423
- Step 5 Preview vs Gemini 3.1 Flash Lite
- Step 5 Preview vs Gemini 3.7 Flash
- Step 5 Preview vs Step 3.7 Flash
- Step 5 Preview vs Gemini 2.5 Flash
- Step 5 Preview vs GLM 5.3 FlashX
- Step 5 Preview vs Grok 4.6
- Step 5 Preview vs MiMo-V2.5
- Step 5 Preview vs MiMo-V2.5-Pro
Claude Haiku 4.5View full model details- Claude Haiku 4.5 vs DeepSeek V4.1 Flash 1017
- Claude Haiku 4.5 vs Hy4 preview
- Claude Haiku 4.5 vs Claude Opus 5.5
- Claude Haiku 4.5 vs GPT-6.1 Sol
- Claude Haiku 4.5 vs Claude Sonnet 5.5
- Claude Haiku 4.5 vs Gemini 3.8 Flash
- Claude Haiku 4.5 vs GLM 5.2
- Claude Haiku 4.5 vs Claude Sonnet 5
- Claude Haiku 4.5 vs Grok 4.7
Our take
Step 5 Preview is 1.3x cheaper for a typical chat. Step 5 Preview has the larger context window (1.05M vs 200K tokens). 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 Haiku 4.5 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 Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens.
Which has a bigger context window, Step 5 Preview or Claude Haiku 4.5?
Step 5 Preview supports up to 1.05M tokens of context, compared with 200K for Claude Haiku 4.5.
Can I use Step 5 Preview and Claude Haiku 4.5 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Step 5 Preview and Claude Haiku 4.5 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Step 5 Preview and Claude Haiku 4.5 at the same time. Compare the answers side by side and keep the best one.