Step 5 Preview
Step 5 PreviewRankingin thinking mode?
Alternatives?
CheaperClaude Haiku 5.5max+54%-79%$0.21Remove sampling parameters+5
BetterGPT-6 Lunamax+25%-93%$0.068Function calling only with none · Chat Completions+3
OpenGLM 5.3max+11%+95%$2.01Memory (4-bit): 363 GB → 452 GB+5CheaperGPT-6.1 Solmax+43%-29%$0.72Remove unsupported parameters+5
CheaperMiMo v2.6 ProthinkingOpen+7%-87%$0.13Memory (4-bit): 363 GB → 615 GB+4Claude Haiku 5.5max+54%-79%$0.21Remove sampling parameters+5GPT-6.1 Solmax+43%-29%$0.72Remove unsupported parameters+5GPT-6 Lunamax+25%-93%$0.068Function calling only with none · Chat Completions+3MiMo v2.6 ProthinkingOpen+7%-87%$0.13Memory (4-bit): 363 GB → 615 GB+4
Grok 4.5highsame-26%$0.76Context: 1M → 500KGPT-6 Lunamax+25%-93%$0.068Function calling only with none · Chat Completions+3MiMo v2.6 ProthinkingOpen+7%-87%$0.13Memory (4-bit): 363 GB → 615 GB+4Claude Haiku 5.5max+54%-79%$0.21Remove sampling parameters+5GPT-6.1 Solmax+43%-29%$0.72Remove unsupported parameters+5
Gemini 3.1 Pro Previewthinking+18%+40%$1.44Cannot use both thinking controlsGLM 5.3maxOpen+11%+95%$2.01Memory (4-bit): 363 GB → 452 GB+5MiMo v2.6 ProthinkingOpen+7%-87%$0.13Memory (4-bit): 363 GB → 615 GB+4TInkling SmallthinkingOpen-21%-91%$0.089Context: 1M → 256K+1GLM 5.3 FlashmaxOpen-29%-72%$0.28Defaults to max · Self-hosted+4TInklingxhighOpen-32%-42%$0.60Context: 1M → 256K+2Run it yourself
estimateBenchmarks
all categoriesWatch out 3
web_search not available · Chat Completions›
Built-in Chat Completions web_search is unavailable; integrate external search through a function tool and return the results. Source ↗
Output includes reasoning›
Output billing includes the reasoning process as well as the final answer. Source ↗
LRU eviction during peak traffic›
LRU eviction removes unused cache entries more aggressively during peak traffic, so cached prefixes may not survive. Source ↗
FAQ
How much does Step 5 Preview cost?›
$1 per 1M input tokens and $2.70 per 1M output tokens; cached input $0.10 per 1M. A typical benchmark task costs about $1.03 at default effort.
Is Step 5 Preview free to use?›
There is no free API; the cheapest paid price is $1 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Step 5 Preview, and what is it best at?›
#20 of 336 in Chat & Knowledge, #19 of 134 in Coding, #36 of 135 in Agents & Tool Use, #53 of 197 in Writing & Language, #41 of 125 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Reasoning, Long context, Knowledge.
Is Step 5 Preview better than MiMo v2.6 Pro?›
On AA Analyst Agent, Step 5 Preview scores 35 vs 37.5 — lower. It is 670% more expensive per task.
How can I use Step 5 Preview?›
Through the API of DeepInfra, Featherless, InferenceNet, Novita, StepFun.
What is the context window of Step 5 Preview?›
1M tokens, with up to 64K output tokens.
When was Step 5 Preview released? Is there a newer version?›
Released 2026-09-16. It is the current version in its line.
Is Step 5 Preview open source?›
Yes, the weights are open.
Can I run Step 5 Preview locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Step 5 Preview read images?›
It accepts text and images, video as input.
What is Step 5 Preview?›
Step 5 Preview is an open-weights language model from StepFun, released Sep 2026.
What are the best alternatives to Step 5 Preview?›
Claude Haiku 5.5 (cheaper), GPT-6 Luna (better), GLM 5.3 (open weights).