{ "data": { "similar": [ { "grade": "A", "json": "https://www.anchorterminal.com/tools/openai-api.json", "name": "OpenAI API", "score": 83.3, "shared": [ "inference.llm" ], "slug": "openai-api" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/anthropic-api.json", "name": "Claude API", "score": 77.3, "shared": [ "inference.llm" ], "slug": "anthropic-api" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/groq.json", "name": "GroqCloud", "score": 75.6, "shared": [ "inference.llm" ], "slug": "groq" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/blockrun-ai.json", "name": "BlockRun.AI", "score": 72.4, "shared": [ "inference.llm" ], "slug": "blockrun-ai" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/mistral-api.json", "name": "Mistral AI API", "score": 71.2, "shared": [ "inference.llm" ], "slug": "mistral-api" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/openrouter.json", "name": "OpenRouter", "score": 68.5, "shared": [ "inference.llm" ], "slug": "openrouter" } ], "tool": { "slug": "stepfun-api", "name": "StepFun API", "vendor": "StepFun", "vendorUrl": "https://platform.stepfun.ai", "kind": "model", "category": "inference", "summary": "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.", "url": "https://www.anchorterminal.com/tools/stepfun-api", "markdownUrl": "https://www.anchorterminal.com/tools/stepfun-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/stepfun-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/stepfun-api.json", "license": "Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law).", "transports": [ "http" ], "remoteUrl": "https://api.stepfun.ai/v1", "packages": [], "auth": "api-key", "authNotes": "A bearer API key created in the StepFun Open Platform console after sign-up. Organisations can create one key per project, billed to the organisation's credit and deletable at once. No key scopes were found. Individual accounts must complete identity verification before tiered rate limits apply.", "pricing": "usage", "pricingNotes": "Step 5 Preview is $1.00 per million input tokens on a cache miss, $0.10 on a cache hit and $2.70 per million output tokens, reasoning included (checked 2026-10-12). Prepaid top-ups. No free API allowance was found. A Step Plan subscription covers coding tools separately.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the international docs index, the pricing page or the Chat Completions reference, checked 12 October 2026. Calls draw on a prepaid balance.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://platform.stepfun.ai/docs/en/guides/models/step-5-preview", "llmsTxt": "https://platform.stepfun.ai/docs/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "usage-priced", "closed-source", "llms-txt", "multimodal", "streaming" ], "graded": true, "anchor": { "graded": true, "score": 44.4, "grade": "E", "agentReady": false, "rank": 889, "ranked": true, "rankOf": 965, "categoryRank": 18, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 50, "payments": 20, "reliability": 28, "schema": 53, "security": 41, "transparency": 58 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 28, "points": 5.6, "reason": "No status page read. status.stepfun.ai refused our reader by robots.txt and the shell couldn't connect, so we couldn't establish whether it is a status page or read any history. Scored absent for both lines, with 5 for unreadable history, and named in the open questions (0 + 5). Rate limits published with numbers per tier, from 5 concurrent, 100 RPM and 500,000 TPM to 130, 2,600 and 13,000,000 (15). The error and exception guides say to retry 429, 500, 503 and 504 after a short delay, with no Retry-After header, backoff schedule or idempotency guidance (8 of 15). No SLA found in the terms or pricing (0). Step 5 Preview is labelled a preview (0)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 53, "points": 8.61, "reason": "No OpenAPI or similar machine-readable contract found. The API reference is Markdown pages (0). llms.txt at platform.stepfun.ai/docs/llms.txt, and every page has a Markdown copy (10). The Chat Completions reference describes each parameter with its default, and the model page lists what Step 5 Preview supports, but little on when not to use an option (12 of 20). Tool definitions take JSON Schema parameters, structured output takes a JSON Schema with `strict: true`, and `reasoning_effort` is an enum of low, medium and high. No `tool_choice` parameter is documented (11 of 15). Worked requests and responses on each page, and an error table of eight codes with causes and fixes, but no error bodies (12 of 15). No API changelog. A model lifecycle page with dated retirements and announcement pages (8 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 68, "points": 11.05, "reason": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through Chat Completions, Responses and Messages, with no documented way to force or forbid a call (15 of 20). Strict JSON Schema output on Step 5 Preview (13 of 15). Prompt caching with a published cache-hit price at a tenth of the miss price (15). 1M-token context and 64k output (15). No batch endpoint found (0). No official SDK. The docs use the OpenAI and Anthropic clients against compatible endpoints (0). Eight error codes with a fix each, plus `finish_reason` handling for length, content filter and tool calls (10 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 41, "points": 7.18, "reason": "Model reading. Bearer API keys, revocable by deletion. Organisations can create one key per project, billed to a project's credit with a per-member cap. No scopes or read-only keys found (20 of 30). Training on API data is not off by default in plain words. The privacy policy (effective 7 August 2026) says StepFun may use and retain data to improve its models, including training and fine-tuning where law and program terms permit, and the terms name early-access programmes as one such case. No opt-out found (5 of 20). No retention period for prompts and outputs and no zero-retention option. IP addresses are kept three years (3 of 15). The console's usage details list each billed call by key, model and date, with export (8 of 15). No security.txt, bug bounty or certification found. A DPA with breach notification exists (5 of 20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 20, "points": 2.5, "reason": "No machine payment protocol (0). Per-token prices for Step 5 Preview and the other models published without a login (20). No free API allowance found. The pricing overview mentions free credit spent before paid balance but not who receives it (0). Browser sign-up and a prepaid top-up, with identity verification for individual rate-limit tiers (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 50, "points": 4.38, "reason": "Model reading. The image models `step-2x-large` and `step-image-edit-2` were retired on 10 October 2026, and a Step 5 Preview price change is announced for 14 October (30). No stated notice period. The 10 October image retirement had a dated notice page and the July retirements a migration table, but we couldn't date when either notice went up (4 of 12). One retirement date in the last 90 days, 10 October, with nine models retired on 8 July just outside that window (6 of 8). Dated announcements, a Discord server and platform@stepfun.com for support. We didn't test whether either answers (10 of 15). No official SDK (0 of 15, 0 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 58, "points": 5.08, "note": "editorial 51, provenance 65", "reason": "Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees. Some earlier Step models have open weights, which doesn't change the hosted service (15). The privacy policy, terms and DPA agree that data may be used for training under program terms, but the terms' licence to Content is broad and perpetual, no retention period is given for prompts and outputs, and no subprocessor list was found (12 of 30). A model lifecycle page with dated retirements and replacements (14 of 20). Servers are disclosed as in the United States. The DPA gives general authorisation for subprocessors without a published list (10 of 20)." } ], "assessment": { "date": "2026-10-12", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through Chat Completions, Responses and Messages, with no documented way to force or forbid a call (15 of 20). Strict JSON Schema output on Step 5 Preview (13 of 15). Prompt caching with a published cache-hit price at a tenth of the miss price (15). 1M-token context and 64k output (15). No batch endpoint found (0). No official SDK. The docs use the OpenAI and Anthropic clients against compatible endpoints (0). Eight error codes with a fix each, plus `finish_reason` handling for length, content filter and tool calls (10 of 15).", "maintenance": "Model reading. The image models `step-2x-large` and `step-image-edit-2` were retired on 10 October 2026, and a Step 5 Preview price change is announced for 14 October (30). No stated notice period. The 10 October image retirement had a dated notice page and the July retirements a migration table, but we couldn't date when either notice went up (4 of 12). One retirement date in the last 90 days, 10 October, with nine models retired on 8 July just outside that window (6 of 8). Dated announcements, a Discord server and platform@stepfun.com for support. We didn't test whether either answers (10 of 15). No official SDK (0 of 15, 0 of 10).", "payments": "No machine payment protocol (0). Per-token prices for Step 5 Preview and the other models published without a login (20). No free API allowance found. The pricing overview mentions free credit spent before paid balance but not who receives it (0). Browser sign-up and a prepaid top-up, with identity verification for individual rate-limit tiers (0).", "reliability": "No status page read. status.stepfun.ai refused our reader by robots.txt and the shell couldn't connect, so we couldn't establish whether it is a status page or read any history. Scored absent for both lines, with 5 for unreadable history, and named in the open questions (0 + 5). Rate limits published with numbers per tier, from 5 concurrent, 100 RPM and 500,000 TPM to 130, 2,600 and 13,000,000 (15). The error and exception guides say to retry 429, 500, 503 and 504 after a short delay, with no Retry-After header, backoff schedule or idempotency guidance (8 of 15). No SLA found in the terms or pricing (0). Step 5 Preview is labelled a preview (0).", "schema": "No OpenAPI or similar machine-readable contract found. The API reference is Markdown pages (0). llms.txt at platform.stepfun.ai/docs/llms.txt, and every page has a Markdown copy (10). The Chat Completions reference describes each parameter with its default, and the model page lists what Step 5 Preview supports, but little on when not to use an option (12 of 20). Tool definitions take JSON Schema parameters, structured output takes a JSON Schema with `strict: true`, and `reasoning_effort` is an enum of low, medium and high. No `tool_choice` parameter is documented (11 of 15). Worked requests and responses on each page, and an error table of eight codes with causes and fixes, but no error bodies (12 of 15). No API changelog. A model lifecycle page with dated retirements and announcement pages (8 of 15).", "security": "Model reading. Bearer API keys, revocable by deletion. Organisations can create one key per project, billed to a project's credit with a per-member cap. No scopes or read-only keys found (20 of 30). Training on API data is not off by default in plain words. The privacy policy (effective 7 August 2026) says StepFun may use and retain data to improve its models, including training and fine-tuning where law and program terms permit, and the terms name early-access programmes as one such case. No opt-out found (5 of 20). No retention period for prompts and outputs and no zero-retention option. IP addresses are kept three years (3 of 15). The console's usage details list each billed call by key, model and date, with export (8 of 15). No security.txt, bug bounty or certification found. A DPA with breach notification exists (5 of 20).", "transparency": "Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees. Some earlier Step models have open weights, which doesn't change the hosted service (15). The privacy policy, terms and DPA agree that data may be used for training under program terms, but the terms' licence to Content is broad and perpetual, no retention period is given for prompts and outputs, and no subprocessor list was found (12 of 30). A model lifecycle page with dated retirements and replacements (14 of 20). Servers are disclosed as in the United States. The DPA gives general authorisation for subprocessors without a published list (10 of 20)." }, "sources": [ { "what": "Step 5 Preview model page", "url": "https://platform.stepfun.ai/docs/en/guides/models/step-5-preview.md", "seen": "2026-10-12" }, { "what": "pricing and rate limits", "url": "https://platform.stepfun.ai/docs/en/guides/pricing/details.md", "seen": "2026-10-12" }, { "what": "pricing overview", "url": "https://platform.stepfun.ai/docs/en/guides/pricing/intro.md", "seen": "2026-10-12" }, { "what": "Chat Completions reference", "url": "https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md", "seen": "2026-10-12" }, { "what": "Messages and Responses references", "url": "https://platform.stepfun.ai/docs/en/api-reference/chat/messages-create.md", "seen": "2026-10-12" }, { "what": "JSON Mode and JSON Schema guide", "url": "https://platform.stepfun.ai/docs/en/guides/developer/json-mode.md", "seen": "2026-10-12" }, { "what": "error codes", "url": "https://platform.stepfun.ai/docs/en/api-reference/error-codes.md", "seen": "2026-10-12" }, { "what": "exception handling guide", "url": "https://platform.stepfun.ai/docs/en/guides/developer/exception.md", "seen": "2026-10-12" }, { "what": "model lifecycle and deprecations", "url": "https://platform.stepfun.ai/docs/en/guides/model-migration.md", "seen": "2026-10-12" }, { "what": "terms of service", "url": "https://platform.stepfun.ai/docs/en/agreement/userservice.md", "seen": "2026-10-12" }, { "what": "privacy policy, effective 7 August 2026", "url": "https://platform.stepfun.ai/docs/en/agreement/userprivacy.md", "seen": "2026-10-12" }, { "what": "data processing agreement", "url": "https://platform.stepfun.ai/docs/en/agreement/dataprocess.md", "seen": "2026-10-12" }, { "what": "project API keys (China docs)", "url": "https://platform.stepfun.com/docs/zh/guides/organization/api-keys.md", "seen": "2026-10-12" }, { "what": "Step 5 Preview cache price announcement (China docs)", "url": "https://platform.stepfun.com/docs/zh/announcements/step-5-preview-price-adjustment.md", "seen": "2026-10-12" }, { "what": "docs index", "url": "https://platform.stepfun.ai/docs/llms.txt", "seen": "2026-10-12" } ], "openQuestions": [ "unchecked: status.stepfun.ai, refused by robots.txt for our reader and unreachable from the shell. Whether StepFun publishes a status page and its incident history", "unchecked: the release date of Step 5 Preview. No first-hand page gave one, and press reports were not used", "unchecked: whether the international platform also changes Step 5 Preview's cache-hit price on 14 October 2026. Only the China docs announce it", "unchecked: who receives the free credit the pricing overview mentions, and how much", "No authenticated call was made. That `step-5-preview` answers on api.stepfun.ai rests on the model page, pricing page and API references, which list it", "No StepFun listing existed before. This listing covers the whole API with Step 5 Preview as its flagship model, in line with the other model-vendor APIs in this category" ] }, "negative": 0, "verdict": "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.", "bestFor": "Long-context agent and coding work over text, screenshots and video at a low per-token price, where a preview model is acceptable.", "strengths": [ "Step 5 Preview takes text, images and video with a 1M-token context and up to 64k output tokens", "Strict JSON Schema output and tool calls on Step 5 Preview, per the structured-output guide", "Per-token prices with cache-hit rates published without a login, and rate-limit tiers published with numbers", "OpenAI-style Chat Completions and Responses endpoints and an Anthropic-style Messages endpoint", "llms.txt and a Markdown copy of every docs page" ], "weaknesses": [ "Step 5 Preview is labelled a preview, and no release date or support commitment was found", "No free API allowance found, and individual accounts need identity verification for tiered limits", "No OpenAPI file, no official SDK and no batch endpoint found", "The privacy policy allows training on user data where law and program terms permit, with no zero-retention option found", "No SLA, security.txt or certification found" ], "agentNotes": [ "Set `max_tokens` yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output", "Use `response_format` with `type: json_schema` and `strict: true` when the shape matters. JSON Mode alone isn't schema-checked", "Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule", "Expect HTTP 451 or `finish_reason: content_filter` when content fails StepFun's review, and don't retry the same input", "Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.4 } ], "editorialScores": { "ergonomics": 68, "maintenance": 50, "payments": 20, "reliability": 28, "schema": 53, "security": 41, "transparency": 51 }, "provenanceScore": 65 }, "connect": { "http": "curl https://api.stepfun.ai/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $STEPFUN_API_KEY\" \\\n -d '{\"model\":\"step-5-preview\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/stepfun-api" }, "notable": [ "Step 5 Preview (`step-5-preview`) takes text, images and video, with a 1M-token context window and up to 64k output tokens, and supports tool calls, JSON Schema output, reasoning effort and prompt caching (https://platform.stepfun.ai/docs/en/guides/models/step-5-preview.md)", "No release date for Step 5 Preview was found on StepFun's own pages. Its weights are not among the stepfun-ai models on Hugging Face (https://huggingface.co/stepfun-ai)", "The China platform raises Step 5 Preview's cache-hit input price from 0.35 to 0.70 yuan per million tokens from 00:30 Beijing time on 14 October 2026, except for users who called it before then (https://platform.stepfun.com/docs/zh/announcements/step-5-preview-price-adjustment.md)", "Individual rate-limit tiers run from 5 concurrent requests, 100 RPM and 500,000 TPM under $15 of cumulative top-up to 130, 2,600 and 13,000,000 from $1,500 (https://platform.stepfun.ai/docs/en/guides/pricing/details.md)", "Nine text and vision models were retired on 8 July 2026, among them `step-3`, and the image models `step-2x-large` and `step-image-edit-2` on 10 October 2026 (https://platform.stepfun.ai/docs/en/guides/model-migration.md)", "The privacy policy (effective 7 August 2026) says the servers are in the United States and that StepFun may use and retain data to improve its models, including training and fine-tuning where permitted by law and program terms (https://platform.stepfun.ai/docs/en/agreement/userprivacy.md)", "The terms let StepFun use prompts and outputs for training in early-access programmes such as the StepFun Startup Program, and give it a broad licence to Content for providing and developing the Services (https://platform.stepfun.ai/docs/en/agreement/userservice.md)" ], "area": "models", "details": [ { "label": "Surface graded", "value": "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." }, { "label": "Step 5 Preview", "value": "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." }, { "label": "Endpoints", "value": "Chat Completions, Responses and Messages for chat, plus speech synthesis and recognition, realtime voice, files, models, token count and account details." }, { "label": "Rate limits", "value": "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." }, { "label": "Errors", "value": "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." }, { "label": "Data handling", "value": "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." }, { "label": "Two platforms", "value": "platform.stepfun.ai (international, dollars, api.stepfun.ai) and platform.stepfun.com (China, yuan, api.stepfun.com), with separate docs." } ], "unitPrices": [ { "item": "Step 5 Preview input, cache miss", "unit": "1m-tokens", "usd": 1, "note": "Includes writing new content to the cache." }, { "item": "Step 5 Preview input, cache hit", "unit": "1m-tokens", "usd": 0.1 }, { "item": "Step 5 Preview output", "unit": "1m-tokens", "usd": 2.7, "note": "Reasoning and final answer tokens." } ], "provenance": { "legalEntity": "STEPFUN TECHNOLOGY (HK) LIMITED", "domain": "stepfun.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://platform.stepfun.ai/docs/en/agreement/userservice", "privacy": "https://platform.stepfun.ai/docs/en/agreement/userprivacy", "statusPage": "", "changelog": "https://platform.stepfun.ai/docs/en/guides/model-migration", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The terms and the privacy policy name STEPFUN TECHNOLOGY (HK) LIMITED. Disputes go to HKIAC arbitration under Hong Kong law.", "platform.stepfun.ai/.well-known/security.txt returned 404, and stepfun.ai/.well-known/security.txt redirects to the platform home page.", "status.stepfun.ai refused our reader by robots.txt, and the shell couldn't connect, so whether it is a status page wasn't established.", "The X handle comes from the QR code labelled X account on the platform home page, which decodes to https://x.com/StepFun_ai.", "Domain registration date was not checked." ], "score": 65, "checks": [ { "check": "Legal entity named", "value": "STEPFUN TECHNOLOGY (HK) LIMITED", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "stepfun.ai, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "api.stepfun.ai", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/stepfun-api.json", "live": { "slug": "stepfun-api", "probe": { "target": "https://api.stepfun.ai/v1", "method": "get", "lastAt": "2026-10-12T04:37:36.182148739Z", "lastOk": true, "lastStatus": 404, "lastMs": 267, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 275, "p95ms24h": 492, "samples24h": 21, "samples30d": 21, "days": [ { "date": "2026-10-12", "probes": 21, "ok": 21 } ] }, "updatedAt": "2026-10-12T04:37:36.182148739Z" } }, "verify": { "accepts": "a page on stepfun.ai or one of its subdomains", "badgeUrl": "https://www.anchorterminal.com/badges/stepfun-api.svg", "body": { "slug": "stepfun-api", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/stepfun-api", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/stepfun-api\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/stepfun-api.svg\" alt=\"StepFun API on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![StepFun API on Anchor Terminal](https://www.anchorterminal.com/badges/stepfun-api.svg)](https://www.anchorterminal.com/tools/stepfun-api)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/stepfun-api\"\u003eStepFun API on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/stepfun-api", "json": "https://www.anchorterminal.com/tools/stepfun-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/stepfun-api.md", "slim": "https://www.anchorterminal.com/tools/stepfun-api.min.md" }, "markdown": "## Overview\n\n**Grade E · 44.4/100 · rank #889 of 965 · #18 in Model APIs \u0026 inference · not agent-ready · confidence medium**\n\n\n## Assessment\n\nStepFun'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.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | StepFun (https://platform.stepfun.ai) |\n| Kind | Model API |\n| Category | Model APIs \u0026 inference (https://www.anchorterminal.com/categories/inference) |\n| Transport | HTTP |\n| Endpoint | `https://api.stepfun.ai/v1` |\n| Auth | API key · A bearer API key created in the StepFun Open Platform console after sign-up. Organisations can create one key per project, billed to the organisation's credit and deletable at once. No key scopes were found. Individual accounts must complete identity verification before tiered rate limits apply. |\n| Pricing | Pay per use (Pay per use) · Step 5 Preview is $1.00 per million input tokens on a cache miss, $0.10 on a cache hit and $2.70 per million output tokens, reasoning included (checked 2026-10-12). Prepaid top-ups. No free API allowance was found. A Step Plan subscription covers coding tools separately. |\n| x402 | No · No x402, MPP or L402 in the international docs index, the pricing page or the Chat Completions reference, checked 12 October 2026. Calls draw on a prepaid balance. |\n| Licence | Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law). |\n| Docs | https://platform.stepfun.ai/docs/en/guides/models/step-5-preview |\n| llms.txt | https://platform.stepfun.ai/docs/llms.txt |\n| 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. |\n| 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. |\n| Endpoints | Chat Completions, Responses and Messages for chat, plus speech synthesis and recognition, realtime voice, files, models, token count and account details. |\n| 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. |\n| 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. |\n| 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. |\n| Two platforms | platform.stepfun.ai (international, dollars, api.stepfun.ai) and platform.stepfun.com (China, yuan, api.stepfun.com), with separate docs. |\n| Capabilities | inference.llm |\n| Tags | official, hosted, model, usage-priced, closed-source, llms-txt, multimodal, streaming |\n| JSON | https://www.anchorterminal.com/api/v1/tools/stepfun-api.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 28 | 5.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 53 | 8.6 |\n| Agent ergonomics | 13% | 16.2 | 68 | 11.1 |\n| Security \u0026 auth | 14% | 17.5 | 41 | 7.2 |\n| Payments \u0026 pricing | 10% | 12.5 | 20 | 2.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 50 | 4.4 |\n| Transparency \u0026 trust (editorial 51, provenance 65) | 7% | 8.8 | 58 | 5.1 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **44.4 → E** |\n\n### Why each score\n\n- Reliability 28: No status page read. status.stepfun.ai refused our reader by robots.txt and the shell couldn't connect, so we couldn't establish whether it is a status page or read any history. Scored absent for both lines, with 5 for unreadable history, and named in the open questions (0 + 5). Rate limits published with numbers per tier, from 5 concurrent, 100 RPM and 500,000 TPM to 130, 2,600 and 13,000,000 (15). The error and exception guides say to retry 429, 500, 503 and 504 after a short delay, with no Retry-After header, backoff schedule or idempotency guidance (8 of 15). No SLA found in the terms or pricing (0). Step 5 Preview is labelled a preview (0).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 53: No OpenAPI or similar machine-readable contract found. The API reference is Markdown pages (0). llms.txt at platform.stepfun.ai/docs/llms.txt, and every page has a Markdown copy (10). The Chat Completions reference describes each parameter with its default, and the model page lists what Step 5 Preview supports, but little on when not to use an option (12 of 20). Tool definitions take JSON Schema parameters, structured output takes a JSON Schema with `strict: true`, and `reasoning_effort` is an enum of low, medium and high. No `tool_choice` parameter is documented (11 of 15). Worked requests and responses on each page, and an error table of eight codes with causes and fixes, but no error bodies (12 of 15). No API changelog. A model lifecycle page with dated retirements and announcement pages (8 of 15).\n- Agent ergonomics 68: Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through Chat Completions, Responses and Messages, with no documented way to force or forbid a call (15 of 20). Strict JSON Schema output on Step 5 Preview (13 of 15). Prompt caching with a published cache-hit price at a tenth of the miss price (15). 1M-token context and 64k output (15). No batch endpoint found (0). No official SDK. The docs use the OpenAI and Anthropic clients against compatible endpoints (0). Eight error codes with a fix each, plus `finish_reason` handling for length, content filter and tool calls (10 of 15).\n- Security \u0026 auth 41: Model reading. Bearer API keys, revocable by deletion. Organisations can create one key per project, billed to a project's credit with a per-member cap. No scopes or read-only keys found (20 of 30). Training on API data is not off by default in plain words. The privacy policy (effective 7 August 2026) says StepFun may use and retain data to improve its models, including training and fine-tuning where law and program terms permit, and the terms name early-access programmes as one such case. No opt-out found (5 of 20). No retention period for prompts and outputs and no zero-retention option. IP addresses are kept three years (3 of 15). The console's usage details list each billed call by key, model and date, with export (8 of 15). No security.txt, bug bounty or certification found. A DPA with breach notification exists (5 of 20).\n- Payments \u0026 pricing 20: No machine payment protocol (0). Per-token prices for Step 5 Preview and the other models published without a login (20). No free API allowance found. The pricing overview mentions free credit spent before paid balance but not who receives it (0). Browser sign-up and a prepaid top-up, with identity verification for individual rate-limit tiers (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 50: Model reading. The image models `step-2x-large` and `step-image-edit-2` were retired on 10 October 2026, and a Step 5 Preview price change is announced for 14 October (30). No stated notice period. The 10 October image retirement had a dated notice page and the July retirements a migration table, but we couldn't date when either notice went up (4 of 12). One retirement date in the last 90 days, 10 October, with nine models retired on 8 July just outside that window (6 of 8). Dated announcements, a Discord server and platform@stepfun.com for support. We didn't test whether either answers (10 of 15). No official SDK (0 of 15, 0 of 10).\n- Transparency \u0026 trust 58: Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees. Some earlier Step models have open weights, which doesn't change the hosted service (15). The privacy policy, terms and DPA agree that data may be used for training under program terms, but the terms' licence to Content is broad and perpetual, no retention period is given for prompts and outputs, and no subprocessor list was found (12 of 30). A model lifecycle page with dated retirements and replacements (14 of 20). Servers are disclosed as in the United States. The DPA gives general authorisation for subprocessors without a published list (10 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (16 items): https://www.anchorterminal.com/fixes/stepfun-api.md (JSON https://www.anchorterminal.com/fixes/stepfun-api.json)\n\n### What we couldn't check\n\n- unchecked: status.stepfun.ai, refused by robots.txt for our reader and unreachable from the shell. Whether StepFun publishes a status page and its incident history\n- unchecked: the release date of Step 5 Preview. No first-hand page gave one, and press reports were not used\n- unchecked: whether the international platform also changes Step 5 Preview's cache-hit price on 14 October 2026. Only the China docs announce it\n- unchecked: who receives the free credit the pricing overview mentions, and how much\n- No authenticated call was made. That `step-5-preview` answers on api.stepfun.ai rests on the model page, pricing page and API references, which list it\n- No StepFun listing existed before. This listing covers the whole API with Step 5 Preview as its flagship model, in line with the other model-vendor APIs in this category\n\n### Sources\n\n- Step 5 Preview model page: \u003chttps://platform.stepfun.ai/docs/en/guides/models/step-5-preview.md\u003e (seen 2026-10-12)\n- pricing and rate limits: \u003chttps://platform.stepfun.ai/docs/en/guides/pricing/details.md\u003e (seen 2026-10-12)\n- pricing overview: \u003chttps://platform.stepfun.ai/docs/en/guides/pricing/intro.md\u003e (seen 2026-10-12)\n- Chat Completions reference: \u003chttps://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md\u003e (seen 2026-10-12)\n- Messages and Responses references: \u003chttps://platform.stepfun.ai/docs/en/api-reference/chat/messages-create.md\u003e (seen 2026-10-12)\n- JSON Mode and JSON Schema guide: \u003chttps://platform.stepfun.ai/docs/en/guides/developer/json-mode.md\u003e (seen 2026-10-12)\n- error codes: \u003chttps://platform.stepfun.ai/docs/en/api-reference/error-codes.md\u003e (seen 2026-10-12)\n- exception handling guide: \u003chttps://platform.stepfun.ai/docs/en/guides/developer/exception.md\u003e (seen 2026-10-12)\n- model lifecycle and deprecations: \u003chttps://platform.stepfun.ai/docs/en/guides/model-migration.md\u003e (seen 2026-10-12)\n- terms of service: \u003chttps://platform.stepfun.ai/docs/en/agreement/userservice.md\u003e (seen 2026-10-12)\n- privacy policy, effective 7 August 2026: \u003chttps://platform.stepfun.ai/docs/en/agreement/userprivacy.md\u003e (seen 2026-10-12)\n- data processing agreement: \u003chttps://platform.stepfun.ai/docs/en/agreement/dataprocess.md\u003e (seen 2026-10-12)\n- project API keys (China docs): \u003chttps://platform.stepfun.com/docs/zh/guides/organization/api-keys.md\u003e (seen 2026-10-12)\n- Step 5 Preview cache price announcement (China docs): \u003chttps://platform.stepfun.com/docs/zh/announcements/step-5-preview-price-adjustment.md\u003e (seen 2026-10-12)\n- docs index: \u003chttps://platform.stepfun.ai/docs/llms.txt\u003e (seen 2026-10-12)\n\n## Who's behind it (provenance 65/100, checked 2026-10-12)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | STEPFUN TECHNOLOGY (HK) LIMITED | 20/20 |\n| Domain age | stepfun.ai, no registry record we could read | 0/15 |\n| Endpoint on the vendor's domain | api.stepfun.ai | 15/15 |\n| Terms of service | published | 10/10 |\n| Privacy policy | published | 10/10 |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe terms and the privacy policy name STEPFUN TECHNOLOGY (HK) LIMITED. Disputes go to HKIAC arbitration under Hong Kong law.\n\nplatform.stepfun.ai/.well-known/security.txt returned 404, and stepfun.ai/.well-known/security.txt redirects to the platform home page.\n\nstatus.stepfun.ai refused our reader by robots.txt, and the shell couldn't connect, so whether it is a status page wasn't established.\n\nThe X handle comes from the QR code labelled X account on the platform home page, which decodes to https://x.com/StepFun_ai.\n\nDomain registration date was not checked.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://platform.stepfun.ai/docs/en/agreement/userservice), not read yet.\n\n\n**Privacy policy** (https://platform.stepfun.ai/docs/en/agreement/userprivacy), not read yet.\n\n\n## Live (updated 2026-10-12 04:37 UTC)\n\n- Right now: up, HTTP 404, 267 ms, checked 2026-10-12 04:37 UTC (get on `https://api.stepfun.ai/v1`)\n- Uptime 24h 100.0% (21 probes) · 30 days 100.0% (21 probes) · p50 275 ms · p95 492 ms\n- Always current: https://www.anchorterminal.com/api/v1/live/stepfun-api.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Step 5 Preview input, cache miss | $1 | per 1M tokens | Includes writing new content to the cache. |\n| Step 5 Preview input, cache hit | $0.10 | per 1M tokens | |\n| Step 5 Preview output | $2.70 | per 1M tokens | Reasoning and final answer tokens. |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Step 5 Preview takes text, images and video with a 1M-token context and up to 64k output tokens\n- Strict JSON Schema output and tool calls on Step 5 Preview, per the structured-output guide\n- Per-token prices with cache-hit rates published without a login, and rate-limit tiers published with numbers\n- OpenAI-style Chat Completions and Responses endpoints and an Anthropic-style Messages endpoint\n- llms.txt and a Markdown copy of every docs page\n\n## Weaknesses\n\n- Step 5 Preview is labelled a preview, and no release date or support commitment was found\n- No free API allowance found, and individual accounts need identity verification for tiered limits\n- No OpenAPI file, no official SDK and no batch endpoint found\n- The privacy policy allows training on user data where law and program terms permit, with no zero-retention option found\n- No SLA, security.txt or certification found\n\n## Before you call it (notes for agents)\n\n1. Set `max_tokens` yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output\n2. Use `response_format` with `type: json_schema` and `strict: true` when the shape matters. JSON Mode alone isn't schema-checked\n3. Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule\n4. Expect HTTP 451 or `finish_reason: content_filter` when content fails StepFun's review, and don't retry the same input\n5. Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing\n\n## Connect\n\nFirst request:\n\n```bash\ncurl https://api.stepfun.ai/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $STEPFUN_API_KEY\" \\\n -d '{\"model\":\"step-5-preview\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| OpenAI API | A | 83.3 | 4 | inference.llm | no | https://www.anchorterminal.com/tools/openai-api.md |\n| Claude API | BB | 77.3 | 21 | inference.llm | no | https://www.anchorterminal.com/tools/anthropic-api.md |\n| GroqCloud | BB | 75.6 | 44 | inference.llm | no | https://www.anchorterminal.com/tools/groq.md |\n| BlockRun.AI | BB | 72.4 | 104 | inference.llm | yes | https://www.anchorterminal.com/tools/blockrun-ai.md |\n| Mistral AI API | BB | 71.2 | 135 | inference.llm | no | https://www.anchorterminal.com/tools/mistral-api.md |\n| OpenRouter | B | 68.5 | 213 | inference.llm | no | https://www.anchorterminal.com/tools/openrouter.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Step 5 Preview (`step-5-preview`) takes text, images and video, with a 1M-token context window and up to 64k output tokens, and supports tool calls, JSON Schema output, reasoning effort and prompt caching (source: \u003chttps://platform.stepfun.ai/docs/en/guides/models/step-5-preview.md\u003e)\n- No release date for Step 5 Preview was found on StepFun's own pages. Its weights are not among the stepfun-ai models on Hugging Face (source: \u003chttps://huggingface.co/stepfun-ai\u003e)\n- The China platform raises Step 5 Preview's cache-hit input price from 0.35 to 0.70 yuan per million tokens from 00:30 Beijing time on 14 October 2026, except for users who called it before then (source: \u003chttps://platform.stepfun.com/docs/zh/announcements/step-5-preview-price-adjustment.md\u003e)\n- Individual rate-limit tiers run from 5 concurrent requests, 100 RPM and 500,000 TPM under $15 of cumulative top-up to 130, 2,600 and 13,000,000 from $1,500 (source: \u003chttps://platform.stepfun.ai/docs/en/guides/pricing/details.md\u003e)\n- Nine text and vision models were retired on 8 July 2026, among them `step-3`, and the image models `step-2x-large` and `step-image-edit-2` on 10 October 2026 (source: \u003chttps://platform.stepfun.ai/docs/en/guides/model-migration.md\u003e)\n- The privacy policy (effective 7 August 2026) says the servers are in the United States and that StepFun may use and retain data to improve its models, including training and fine-tuning where permitted by law and program terms (source: \u003chttps://platform.stepfun.ai/docs/en/agreement/userprivacy.md\u003e)\n- The terms let StepFun use prompts and outputs for training in early-access programmes such as the StepFun Startup Program, and give it a broad licence to Content for providing and developing the Services (source: \u003chttps://platform.stepfun.ai/docs/en/agreement/userservice.md\u003e)\n\n- #18 of 18 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 153 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Compare\n\n- [Claude API vs StepFun API](https://www.anchorterminal.com/compare/anthropic-api-vs-stepfun-api.md): BB 77.3 vs E 44.4\n- [Antseed vs StepFun API](https://www.anchorterminal.com/compare/antseed-vs-stepfun-api.md): C 55.1 vs E 44.4\n- [BlockRun.AI vs StepFun API](https://www.anchorterminal.com/compare/blockrun-ai-vs-stepfun-api.md): BB 72.4 vs E 44.4\n- [Cloudflare AI Gateway vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api.md): B 66.8 vs E 44.4\n- [Cloudflare Workers AI vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api.md): B 68.3 vs E 44.4\n- [Cohere Chat API (Command models) vs StepFun API](https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api.md): B 64.7 vs E 44.4\n- [DeepInfra vs StepFun API](https://www.anchorterminal.com/compare/deepinfra-vs-stepfun-api.md): B 63 vs E 44.4\n- [DeepSeek API vs StepFun API](https://www.anchorterminal.com/compare/deepseek-api-vs-stepfun-api.md): D 46.8 vs E 44.4\n- [Gemini Developer API vs StepFun API](https://www.anchorterminal.com/compare/gemini-api-vs-stepfun-api.md): B 65.5 vs E 44.4\n- [GroqCloud vs StepFun API](https://www.anchorterminal.com/compare/groq-vs-stepfun-api.md): BB 75.6 vs E 44.4\n- [Mistral AI API vs StepFun API](https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api.md): BB 71.2 vs E 44.4\n- [Novita AI vs StepFun API](https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api.md): D 53.5 vs E 44.4\n- [OpenAI API vs StepFun API](https://www.anchorterminal.com/compare/openai-api-vs-stepfun-api.md): A 83.3 vs E 44.4\n- [OpenRouter vs StepFun API](https://www.anchorterminal.com/compare/openrouter-vs-stepfun-api.md): B 68.5 vs E 44.4\n- [Prism Inference vs StepFun API](https://www.anchorterminal.com/compare/prism-inference-vs-stepfun-api.md): C 60.1 vs E 44.4\n- [SambaCloud vs StepFun API](https://www.anchorterminal.com/compare/sambanova-vs-stepfun-api.md): B 66.4 vs E 44.4\n- [SiliconFlow vs StepFun API](https://www.anchorterminal.com/compare/siliconflow-vs-stepfun-api.md): D 46.7 vs E 44.4\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on stepfun.ai or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"stepfun-api\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/stepfun-api\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/stepfun-api.svg\" alt=\"StepFun API on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![StepFun API on Anchor Terminal](https://www.anchorterminal.com/badges/stepfun-api.svg)](https://www.anchorterminal.com/tools/stepfun-api)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/stepfun-api\"\u003eStepFun API on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say StepFun API is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/stepfun-api-dark.png\n- Light: https://www.anchorterminal.com/assets/share/stepfun-api-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Model APIs \u0026 inference", "url": "https://www.anchorterminal.com/categories/inference" }, { "name": "StepFun API", "url": "" } ], "description": "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.", "facts": [ "rank #889 of 965", "API key auth", "0 desk reviews" ], "h1": "StepFun API", "image": "https://www.anchorterminal.com/assets/og/tools-stepfun-api.png", "path": "/tools/stepfun-api", "published": "2026-10-01", "section": "tools", "title": "StepFun review (2026): pricing, alternatives and grade E", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/tools/stepfun-api" }, "tokens": { "markdown": 6150, "slim": 1430 }, "version": 1 }