AI model comparison
Step 5 Preview vs Claude Haiku 5.5
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
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).
- Input / 1M
- $1
- Output / 1M
- $2.70
- Context
- 1.05M
Anthropic
Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Claude Haiku 5.5
7.4x cheaper for a typical chat
Higher intelligence score
Step 5 Preview
43.7 vs 43.4 on Artificial Analysis
Larger context window
Step 5 Preview
1.05M 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
Claude Haiku 5.543.4Coding index
Claude Haiku 5.5Not availableAgentic index
Claude Haiku 5.5Not availablePricing
Step 5 Preview vs Claude Haiku 5.5 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Claude Haiku 5.5 | |
|---|---|---|
| Input tokensPer 1M tokens | $1 | $0.10 |
| Output tokensPer 1M tokens | $2.70 | $0.50 |
| Cached input (read)Per 1M tokens | $0.05 | $0.01 |
| Cache writePer 1M tokens | Not available | $0.13 |
| Long-context pricingPer 1M tokens, for very long prompts | Same rate at any length | $0.50 in / $2.50 out above 100K |
| 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 5.5$0.45Coding task
30K in, 4K out
Claude Haiku 5.5$5$2.30 cachedLong document summary
150K in, 2K out
Claude Haiku 5.5$16$2.50 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 5.5 | |
|---|---|---|
| Context window | 1.05M 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, Extra high, High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | October 8, 2026 | October 7, 2026 |
Features
Supported features
API features available for each model.
| Metric | Claude Haiku 5.5 | |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Not supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Not supported | 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
- Step 5 Preview vs GLM 5.3 Flash
- Step 5 Preview vs MiMo-V2.6-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 DeepSeek V4 Flash 0731
- Step 5 Preview vs GLM 5.3
- Step 5 Preview vs Hy3
- Step 5 Preview vs DeepSeek V4 Flash 0423
- Step 5 Preview vs Muse Spark 1.3 Contributor
- Step 5 Preview vs Claude Sonnet 5.5
- Step 5 Preview vs Kimi K3
- Step 5 Preview vs GPT-6.1 Sol
- Step 5 Preview vs Claude Fable 5.1
- Step 5 Preview vs Gemini 3.8 Flash
- Step 5 Preview vs GPT-6 Astra
- Step 5 Preview vs GPT-5.6 Luna
- Step 5 Preview vs Gemini 4 Argon
- Step 5 Preview vs MiMo-V2.6-Pro
- Step 5 Preview vs DeepSeek V4 Pro 0813
- Step 5 Preview vs Muse Spark 1.3
- Step 5 Preview vs GPT-6 Sol
- Step 5 Preview vs GPT-5.6 Sol
- Step 5 Preview vs Grok 4.7
- Step 5 Preview vs Qwen3.8 Max (0902)
- Step 5 Preview vs Grok 4.6
- Step 5 Preview vs Claude Sonnet 5
- Step 5 Preview vs GPT-5.6 Terra
- Step 5 Preview vs Claude Opus 4.8
- Step 5 Preview vs Ling 3.1 Flash
- Step 5 Preview vs Claude Opus 4.7
- Step 5 Preview vs Qwen3.8 2.4T A95B
- Step 5 Preview vs Gemini 3.7 Flash
- Step 5 Preview vs Muse Spark 1.2
- Step 5 Preview vs Grok 4.5
- Step 5 Preview vs Qwen3.8 27B
- Step 5 Preview vs Mistral Large 4
- Step 5 Preview vs Muse Spark 1.1
- Step 5 Preview vs GLM 5.3 FlashX
- Step 5 Preview vs GPT-5.6 Luna Pro
Claude Haiku 5.5View full model details- Claude Haiku 5.5 vs DeepSeek V4.1 Flash
- Claude Haiku 5.5 vs GLM 5.3 Flash
- Claude Haiku 5.5 vs MiMo-V2.6-Flash
- Claude Haiku 5.5 vs GPT-6 Luna
- Claude Haiku 5.5 vs DeepSeek V4 Flash 0731
- Claude Haiku 5.5 vs GLM 5.3
- Claude Haiku 5.5 vs MiMo-V2.6-Pro
- Claude Haiku 5.5 vs GPT-5.6 Luna
- Claude Haiku 5.5 vs Ling 3.1 Flash
- Claude Haiku 5.5 vs Qwen3.8 Flash
- Claude Haiku 5.5 vs GPT-6 Luna Pro
Our take
Claude Haiku 5.5 is 7.4x cheaper for a typical chat. Step 5 Preview scores higher on the Artificial Analysis Intelligence Index (43.7 vs 43.4). Step 5 Preview has the larger context window (1.05M vs 1M 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 5.5 cheaper?
Claude Haiku 5.5 is cheaper for a typical chat (2K input tokens and 500 output tokens). Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, while Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens.
Which has a bigger context window, Step 5 Preview or Claude Haiku 5.5?
Step 5 Preview supports up to 1.05M tokens of context, compared with 1M for Claude Haiku 5.5.
Is Step 5 Preview smarter than Claude Haiku 5.5?
On the Artificial Analysis Intelligence Index, Step 5 Preview scores 43.7 and Claude Haiku 5.5 scores 43.4, putting Step 5 Preview 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 Haiku 5.5 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 5.5 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Step 5 Preview and Claude Haiku 5.5 at the same time. Compare the answers side by side and keep the best one.