# StepFun API (slim)

> The StepFun API is StepFun's paid model API for its Step language, vision and speech models, including the flagship Step 5 Preview, through OpenAI-style Chat Completions and Responses endpoints and an Anthropic-style Messages endpoint.

- Full: https://www.anchorterminal.com/tools/stepfun-api.md (~6,150 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/stepfun-api.json · canonical https://www.anchorterminal.com/tools/stepfun-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-12

**E · 44.4/100 · rank #889 of 965 · #18 in Model APIs & inference · not agent-ready · confidence medium**


Assessment: StepFun's API serves Step 5 Preview with a 1M-token context, video input, strict JSON Schema output and published per-token prices, documented in Markdown with an llms.txt. The model is a preview with no release date found, there's no free allowance or SLA, and the terms and privacy policy leave room to train on customer data.

## Facts

- Kind: Model API · vendor: StepFun · category: Model APIs & inference · legal entity: STEPFUN TECHNOLOGY (HK) LIMITED · provenance 65/100
- Endpoint: `https://api.stepfun.ai/v1` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law).
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The international StepFun Open Platform API at api.stepfun.ai, read from its docs, pricing, terms and privacy policy on 12 October 2026, with Step 5 Preview as the model in question. No authenticated call was made. An unauthenticated `GET /v1/models` answered 401.
- Step 5 Preview: Model ID step-5-preview. 1M-token context and input, 64k output. Text, images (URL or base64, up to 60 a request) and video (URL, base64 or a Files API reference, MP4 under 128 MB). Reasoning effort low, medium or high.
- Endpoints: Chat Completions, Responses and Messages for chat, plus speech synthesis and recognition, realtime voice, files, models, token count and account details.
- Rate limits: By cumulative cash top-up for individuals, from V0 (under $15, 5 concurrent, 100 RPM, 500,000 TPM) to V4 ($1,500 and above, 130 concurrent, 2,600 RPM, 13,000,000 TPM). Enterprise tiers through sales.
- Errors: 400 invalid parameters, 401 invalid key, 402 insufficient balance, 404 wrong path, 429 rate limit, 451 content failed review, 500 and 503 server or overload, each with a suggested fix.
- Data handling: Privacy policy effective 7 August 2026. Servers in the United States, IP addresses kept three years. Data may be used for training and fine-tuning where law and program terms permit. A DPA with general authorisation for subprocessors.
- Two platforms: platform.stepfun.ai (international, dollars, api.stepfun.ai) and platform.stepfun.com (China, yuan, api.stepfun.com), with separate docs.
- Prices: Step 5 Preview input, cache miss $1 per 1M tokens; Step 5 Preview input, cache hit $0.10 per 1M tokens; Step 5 Preview output $2.70 per 1M tokens

- Scores: Reliability 28, Performance pending, Schema & documentation 53, Agent ergonomics 68, Security & auth 41, Payments & pricing 20, Task success pending, Maintenance & community 50, Transparency & trust 58 · total over the 7 assessed categories
- Why: Reliability, No status page read. · Schema & documentation, No OpenAPI or similar machine-readable contract found. · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). · Security & auth, Model reading. · Payments & pricing, No machine payment protocol (0). · Maintenance & community, Model reading. · Transparency & trust, Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees.
- Sources: 15, open questions: 6, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/stepfun-api.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/stepfun-api.svg` or a link to https://www.anchorterminal.com/tools/stepfun-api from a page on stepfun.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set `max_tokens` yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output
2. Use `response_format` with `type: json_schema` and `strict: true` when the shape matters. JSON Mode alone isn't schema-checked
3. Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule
4. Expect HTTP 451 or `finish_reason: content_filter` when content fails StepFun's review, and don't retry the same input
5. Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing

## Connect

```bash
curl https://api.stepfun.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $STEPFUN_API_KEY" \
  -d '{"model":"step-5-preview","messages":[{"role":"user","content":"Hello"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI API | A | 83.3 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| Claude API | BB | 77.3 | inference.llm | https://www.anchorterminal.com/tools/anthropic-api.min.md |
| GroqCloud | BB | 75.6 | inference.llm | https://www.anchorterminal.com/tools/groq.min.md |
| BlockRun.AI | BB | 72.4 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |
| Mistral AI API | BB | 71.2 | inference.llm | https://www.anchorterminal.com/tools/mistral-api.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)