Step-3
zenmux/step-3제공: zenmux · 출시 2025-07-31 · 지식 컷오프: 2025-01-01
⚠ 이 모델은 커뮤니티 파인튜닝 / 파생본으로, 벤더 공식 릴리스가 아닙니다.
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
기능
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding51
- Tool calling40/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)0/20
- Provider availability1/10
Agents66
- Tool calling35/35
- Structured output0/25
- Reasoning15/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output48
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume18/20
Cost efficiency65
- Headline price (log-scaled)65/95
- Has prompt-cache pricing0/5
Long context0
- Context ≥ 100K0/100
Vision73
- Accepts image input50/50
- Context window (10K → 1M)12/30
- Has published price10/10
- Provider availability1/10
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $1.33 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $2.67 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.70 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $2.25 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $2.86 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
가격 상세
추천 가격 제공자: zenmux · stepfun/step-3
1곳 제공사에서 이용 가능
| 제공자 | 제공자 모델 ID | 입력 / 1M | 출력 / 1M | 컨텍스트 | 출시일 |
|---|---|---|---|---|---|
| ZenMux zenmux | stepfun/step-3 | $0.210 | $0.570 | 66K | 2025-07-31 |
Frequently asked questions
How much does Step-3 cost?
Step-3 costs $0.210 per 1M input tokens and $0.570 per 1M output tokens, sourced from zenmux. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Step-3?
Step-3 has a context window of 66K tokens, with a max output of 64K tokens per reply. This is the total combined size of prompt + completion.
Does Step-3 support tool calling?
Yes. Step-3 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Step-3 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Step-3 in our data source. Verify with zenmux's official documentation before relying on it in production.
Can Step-3 accept image input?
Yes. Step-3 accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check zenmux's docs for the exact rule.
Is Step-3 open-weight?
No. Step-3 is a proprietary model — only zenmux (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Step-3?
If Step-3 doesn't fit, consider Ring-1T, Ling-1T, KAT-Coder-Pro-V2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More zenmux models
- Ring-1T$0.56 in / $2.24 out
- Ling-1T$0.56 in / $2.24 out
- KAT-Coder-Pro-V2$0.30 in / $1.20 out
- Agnes 1.5 Lite$0.12 in / $0.60 out
- Agnes 1.5 Pro$0.16 in / $0.80 out
Capability lists this model is in
마지막 업데이트:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.