Step 5 Preview
stepfun/step-5-previewPor StepFun · lançado 2026-09-16
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacidades
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.
Coding93
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability3/10
Agents93
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability3/10
JSON / structured output83
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control0/10
- Price-friendly for high-volume13/20
Cost efficiency53
- Headline price (log-scaled)48/95
- Has prompt-cache pricing5/5
Long context90
- Context window (100K → 2M)80/90
- Has published price for full window10/10
Vision93
- Accepts image input50/50
- Context window (10K → 1M)30/30
- Has published price10/10
- Provider availability3/10
Production-readiness73
- Number of independent providers15/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers8/10
- Official model (not derivative)15/15
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 | $6.17 < $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 | $12.33 < $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 | $3.29 < $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 | $10.41 $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 | $13.15 $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Detalhes de preço
Preço recomendado de stepfun · step-5-preview
Disponível em 3 provedores
| Provedor | ID do modelo do provedor | Entrada / 1M | Saída / 1M | Contexto | Lançado |
|---|---|---|---|---|---|
| StepFun (China) stepfun | step-5-preview | $0.959 | $2.74 | 1M | 2026-09-16 |
| Vercel AI Gateway vercel | stepfun/step-5-preview | $1.00 | $2.70 | 1M | 2026-09-16 |
| NanoGPT nano-gpt | stepfun/step-5-preview | $1.00 | $2.70 | 1M | 2026-09-16 |
Inconsistências de dados entre provedores
- modalities varies across offerings
Os provedores reportam valores diferentes para este modelo. Os dados rápidos acima usam um provedor representativo; consulte a tabela para detalhes por provedor.
Frequently asked questions
How much does Step 5 Preview cost?
Step 5 Preview costs $0.959 per 1M input tokens and $2.74 per 1M output tokens, sourced from stepfun. 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 5 Preview?
Step 5 Preview has a context window of 1M tokens, with a max output of 66K tokens per reply. This is the total combined size of prompt + completion.
Does Step 5 Preview support tool calling?
Yes. Step 5 Preview 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 5 Preview support structured output / JSON mode?
Yes. Step 5 Preview supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Step 5 Preview accept image input?
Yes. Step 5 Preview accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check StepFun's docs for the exact rule.
Is Step 5 Preview open-weight?
No. Step 5 Preview is a proprietary model — only StepFun (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Step 5 Preview?
If Step 5 Preview doesn't fit, consider Step 3.5 Flash, Step 3.7 Flash, Step 3.5 Flash 2603. 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 are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More StepFun models
- Step 3.5 Flash$0.10 in / $0.30 out
- Step 3.7 Flash$0.18 in / $1.11 out
- Step 3.5 Flash 2603$0.10 in / $0.30 out
- Step 1 (32K)$2.05 in / $9.59 out
- Step TTS 2Unknown pricing
Capability lists this model is in
Última atualização:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.