API-Referenz

curl https://api.sluis.ai/v1/models \
  -H "Authorization: Bearer $SLUIS_KEY"

# a model outside the key's allow-list never dispatches:
# → 403 permission_error · the refusal is sealed in the audit chain

{
  "object": "list",
  "data": [
    { "id": "mistral/mistral-large-latest", "object": "model", "owned_by": "mistral" },
    { "id": "vertex/claude-opus-4-8", "object": "model", "owned_by": "vertex" },
    { "id": "sluis/auto", "object": "model", "owned_by": "sluis" }
  ]
}

curl https://api.sluis.ai/v1/chat/completions \
  -H "Authorization: Bearer $SLUIS_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "mistral/mistral-large-latest",
        "messages": [{ "role": "user", "content": "Say hi" }] }'

{
  "id": "chatcmpl-9f2e…",
  "object": "chat.completion",
  "model": "mistral-large-latest",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hi! How can I help?" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 8, "total_tokens": 17 }
}

# Document OCR, billed per page. Returns pages[] markdown + usage_info.pages_processed.
# model "sluis/ocr" runs the gateway's own OCR engine: fully local, no provider egress (inline data: URLs only).
curl https://api.sluis.ai/v1/ocr \
  -H "Authorization: Bearer $SLUIS_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "mistral/mistral-ocr-latest", "document": { "type": "document_url", "document_url": "https://example.com/invoice.pdf" } }'

{
  "pages": [{
    "index": 0,
    "markdown": "# Invoice 2026-118\nAcme BV · Keizersgracht 1…",
    "images": [],
    "dimensions": { "dpi": 150, "height": 1754, "width": 1240 }
  }],
  "model": "mistral-ocr-latest",
  "usage_info": { "pages_processed": 1, "doc_size_bytes": 48213 }
}

# Document anonymization, billed per page/image. PII becomes «MERGE_TAG»s; images are blurred.
curl https://api.sluis.ai/v1/documents/anonymize \
  -H "Authorization: Bearer $SLUIS_KEY" \
  -F file=@contract.docx \
  -F 'options={ "entities": ["person_name", "email", "iban"], "remove": ["Project Nightingale"], "include_mapping": true }'

{
  "filename": "contract.docx",
  "content_type": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
  "content_base64": "UEsDBBQABgAIA…",
  "summary": { "pages": 4, "images": 1, "categories": ["EMAIL", "IBAN", "PERSON_NAME"], "downgraded": false },
  "mapping": [
    { "token": "«PERSON_NAME_1»", "original": "Jan de Vries" },
    { "token": "«IBAN_1»", "original": "NL91ABNA0417164300" }
  ]
}

# The router behind sluis/auto: send state only, not questions.
curl https://api.sluis.ai/v1/systemone \
  -H "Authorization: Bearer $SLUIS_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sluis/typed/router",
       "state":{"request":"Compare these two supplier contracts clause by clause and list the risks.",
                "previous":"Here are both contracts.",
                "attachments":["contract_a.pdf (application/pdf)","contract_b.pdf (application/pdf)"]}}'

{
  "model": "sluis/typed/router",
  "answers": {
    "reasoning":  { "type": "noul", "noul": 0.9412,
                    "probabilities": { "false": 0.0588, "true": 0.9412 },
                    "confidence": 0.9412, "answer_confidence": 0.9412 },
    "complexity": { "type": "score", "score": 2.31,
                    "legend": { "0": "trivial", "1": "simple", "2": "moderate", "3": "hard" },
                    "probabilities": { "0": 0.01, "1": 0.12, "2": 0.42, "3": 0.45 },
                    "confidence": 0.2612, "answer_confidence": 0.45 },
    "task":       { "type": "choice", "choice": "document",
                    "probabilities": { "code": 0.01, "writing": 0.03, "translation": 0.01, "extraction": 0.05,
                                       "document": 0.86, "support": 0.02, "smalltalk": 0.01, "action": 0.01 },
                    "confidence": 0.6888, "answer_confidence": 0.86 }
  },
  "decision": { "route": "sluis/reasoning", "demand": "strong" },
  "revision": ""
}

# Attach a document as an OpenAI-style `file` content part. The gateway
# normalizes it for the routed provider, so this works on any model.
curl https://api.sluis.ai/v1/chat/completions \
  -H "Authorization: Bearer $SLUIS_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "scaleway/gemma-4-26b-a4b-it",
        "messages": [{ "role": "user", "content": [
          { "type": "file",
            "file": { "filename": "drawing.pdf",
                      "file_data": "data:application/pdf;base64,'"$(base64 -w0 drawing.pdf)"'" } },
          { "type": "text", "text": "Which discipline does this drawing document?" }
        ] }] }'

import OpenAI from "openai";
import { readFileSync } from "node:fs";

const client = new OpenAI({
  baseURL: "https://api.sluis.ai/v1",
  apiKey: process.env.SLUIS_KEY,
});
const pdf = readFileSync("drawing.pdf").toString("base64");

const reply = await client.chat.completions.create({
  model: "vertex/gemini-3.1-pro",
  messages: [{
    role: "user",
    content: [
      { type: "file",
        file: { filename: "drawing.pdf",
                file_data: `data:application/pdf;base64,${pdf}` } },
      { type: "text", text: "Which discipline does this drawing document?" },
    ],
  }],
});

stream = client.chat.completions.create(
    model="mistral/mistral-large-latest",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

const stream = await client.chat.completions.create({
  model: "mistral/mistral-large-latest",
  messages: [{ role: "user", content: "Write a haiku" }],
  stream: true,
  stream_options: { include_usage: true },
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

# the raw event stream on the wire
data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Water"}}]}

data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" finds a way."}}]}

data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"completion_tokens":9,"total_tokens":21}}

data: [DONE]

resp = client.chat.completions.create(
    model="vertex/claude-opus-4-8",
    messages=[{"role": "user", "content": "Prove it step by step…"}],
    reasoning_effort="high",  # minimal | low | medium | high
)

{
  "error": {
    "message": "model must be provider-prefixed, e.g. mistral/mistral-large-latest",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_request"
  }
}

{
  "error": {
    "message": "model is not on this key's allow-list",
    "type": "permission_error",
    "param": null,
    "code": "permission_denied"
  }
}

{
  "error": {
    "message": "provider `openai` (jurisdiction `US`) is not permitted by the tenant's residency policy",
    "type": "permission_error",
    "param": null,
    "code": "permission_denied"
  }
}

# native Anthropic Messages — the model id owns the route, not the wire format
curl https://api.sluis.ai/v1/messages \
  -H "x-api-key: $SLUIS_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{ "model": "vertex/claude-opus-4-8",
        "max_tokens": 256,
        "system": "Be concise.",
        "messages": [{ "role": "user", "content": "Say hi" }] }'

# /anthropic/v1/messages is the unambiguous prefixed path for the same handler

{
  "id": "msg_01f7…",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-8",
  "content": [{ "type": "text", "text": "Hi! How can I help?" }],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 9,
    "output_tokens": 8,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0
  }
}

# "stream": true — the full event grammar, ping keep-alives included
event: message_start
data: {"type":"message_start","message":{"id":"msg_01f7…","role":"assistant","model":"claude-opus-4-8","usage":{"input_tokens":9,"output_tokens":0}}}

event: ping
data: {"type":"ping"}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hi!"}}

event: ping
data: {"type":"ping"}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"output_tokens":8,"cache_read_input_tokens":0}}

event: message_stop
data: {"type":"message_stop"}

# every failure on /v1/messages* is Anthropic-shaped — auth and
# data-protection refusals included, never an OpenAI envelope
{
  "type": "error",
  "error": {
    "type": "rate_limit_error",
    "message": "rate limit exceeded"
  },
  "request_id": "req_9f2e…"
}

# mcp_servers is refused, not quietly passed through: an external MCP
# server called by the model would sit outside the Sluis gate
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "mcp_servers is not supported: register the server in Sluis and call the MCP gateway at /v1/mcp"
  },
  "request_id": "req_4c81…"
}