Complete API Reference

Every endpoint, parameter, and response format documented. Build with confidence using our OpenAI-compatible REST API.

Authentication

All API requests require authentication via Bearer token.

Bearer Token (Recommended)

Include your API key in the Authorization header:

Header

1 Authorization: Bearer cycose.....

API Key Header (Alternative)

Or pass your key via a custom header:

Header

1 X-API-Key: hld_sk_...

Get your API key from the API Keys dashboard

Endpoints

POST/v1/chat/completionsGenerate chat completions with streaming support

POST/v1/embeddingsGenerate vector embeddings for text input

POST/v1/vector/searchSemantic search across vector collections

GET/v1/vector/collectionsList and manage vector collections

GET/v1/modelsList available models and their capabilities

GET/v1/usageTrack API usage, tokens, and costs

GET/v1/healthService health check and status

Rate Limits

Tier	Requests/min	Tokens/min	Concurrent
Free	60	40,000	5
Pro	600	400,000	50
Enterprise	Custom	Custom	Custom

Need higher limits? Upgrade your plan or contact us

Example: Chat Completion

Request

cURL

1 curl -X POST https://api.highlimitdesigns.com/v1/chat/completions \
2   -H "Authorization: Bearer $HLD...KEY" \
3   -H "Content-Type: application/json" \
4   -d '{
    "model": "glm-5.1",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is vector search?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024,
    "stream": true
  }'

Response

response.json

 1 {
 2   "id": "chatcmpl-abc123",
 3   "object": "chat.completion",
 4   "created": 1715000000,
 5   "model": "glm-5.1",
 6   "choices": [
 7     {
 8       "index": 0,
 9       "message": {
10         "role": "assistant",
11         "content": "Vector search is a technique that uses..."
12       },
13       "finish_reason": "stop"
14     }
15   ],
16   "usage": {
17     "prompt_tokens": 24,
18     "completion_tokens": 156,
19     "total_tokens": 180
20   }
21 }

Ready to integrate?

View OpenAI migration guide

Tier

Requests/min

Tokens/min

Concurrent

Free

40,000

Pro

600

400,000

Enterprise

Custom

1 curl -X POST https://api.highlimitdesigns.com/v1/chat/completions \ 2 -H "Authorization: Bearer $HLD...KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ "model": "glm-5.1", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is vector search?"} ], "temperature": 0.7, "max_tokens": 1024, "stream": true }'

1 { 2 "id": "chatcmpl-abc123", 3 "object": "chat.completion", 4 "created": 1715000000, 5 "model": "glm-5.1", 6 "choices": [ 7 { 8 "index": 0, 9 "message": { 10 "role": "assistant", 11 "content": "Vector search is a technique that uses..." 12 }, 13 "finish_reason": "stop" 14 } 15 ], 16 "usage": { 17 "prompt_tokens": 24, 18 "completion_tokens": 156, 19 "total_tokens": 180 20 } 21 }

1	curl -X POST https://api.highlimitdesigns.com/v1/chat/completions \
2	-H "Authorization: Bearer $HLD...KEY" \
3	-H "Content-Type: application/json" \
4	-d '{ "model": "glm-5.1", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is vector search?"} ], "temperature": 0.7, "max_tokens": 1024, "stream": true }'

1	{
2	"id": "chatcmpl-abc123",
3	"object": "chat.completion",
4	"created": 1715000000,
5	"model": "glm-5.1",
6	"choices": [
7	{
8	"index": 0,
9	"message": {
10	"role": "assistant",
11	"content": "Vector search is a technique that uses..."
12	},
13	"finish_reason": "stop"
14	}
15	],
16	"usage": {
17	"prompt_tokens": 24,
18	"completion_tokens": 156,
19	"total_tokens": 180
20	}
21	}