API Documentation

Base URL

All API requests should be made to: https://api.lobsterstoken.co.uk

Authentication

All requests must include your API key in the Authorization header as a Bearer token.

          
          bash
        
curl -H "Authorization: Bearer YOUR_API_KEY" \
     https://api.lobsterstoken.co.uk/v1/models

Keep your API key secure. Do not share it in client-side code, public repositories, or chat logs. If compromised, rotate it immediately from your dashboard.

Chat Completions POST /chat

Send a chat message and receive an AI response. This endpoint is compatible with OpenAI's Chat Completions API.

Request

          
          
          
          bash
        

curl -X POST https://api.lobsterstoken.co.uk/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'
        

Request Parameters

Parameter	Type	Default	Description
`model` required	string	—	Model ID (see Available Models)
`messages` required	array	—	Array of message objects with role and content
`temperature`	number	1.0	Sampling temperature. Range: 0.0 – 2.0
`max_tokens`	integer	∞	Maximum tokens to generate
`top_p`	number	1.0	Nucleus sampling threshold
`stream`	boolean	false	Enable Server-Sent Events streaming
`stop`	string/array	null	Stop sequences

Response

          
          
          
          json
        

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20
  }
}
        

Available Models

Use any of these model IDs in the model parameter.

GPT Models

gpt-4o gpt-4o-mini gpt-4-turbo gpt-4 gpt-3.5-turbo

Anthropic Models

claude-3-5-sonnet-20240620 claude-3-5-haiku-20240620 claude-3-opus-20240229 claude-3-sonnet-20240229

Google Models

gemini-1.5-pro gemini-1.5-flash gemini-1.5-pro-exp-0807

Meta & Open Source

llama-3.1-70b-instruct llama-3.1-8b-instruct llama-3-70b-instruct mistral-large mistral-7b-instruct mixtral-8x22b-instruct qwen-2.5-72b-instruct

40+ additional models are available via OpenRouter routing. Visit openrouter.ai/models for the full list. Any OpenRouter model ID works with our API.

Streaming Responses

Set "stream": true to receive Server-Sent Events (SSE) with incremental response tokens.

          
          
          
          bash
        

curl -X POST https://api.lobsterstoken.co.uk/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Count to 5"}],
    "stream": true
  }'
        

Each streamed chunk looks like:

data: {"choices":[{"delta":{"content":"One"}}]}

data: {"choices":[{"delta":{"content":" two"}}]}

data: [DONE]

List Available Models GET /v1/models

Returns a list of all available models you can use with your API key.

          
          bash
        
curl https://api.lobsterstoken.co.uk/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Error Codes

HTTP Code	Error	Meaning
400	`invalid_request`	Bad request — check your parameters
401	`invalid_api_key`	Unauthorized — invalid or missing API key
429	`rate_limit_exceeded`	Rate limit exceeded — slow down or upgrade your plan
500	`server_error`	Internal server error — something went wrong on our end
503	`model_unavailable`	Model temporarily unavailable — try again shortly

Rate Limits

Default rate limits per API key:

Tier	Requests/min	Tokens/min
Free	20	10,000
Pay-as-you-go	60	100,000
Enterprise	Custom	Custom

Need higher limits? Contact us to discuss an enterprise plan.

SDK Examples

Python (OpenAI SDK)

          
          python
        
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LOBSTERS_TOKEN_KEY",
    base_url="https://api.lobsterstoken.co.uk"
)

chat = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What is 2+2?"}]
)
print(chat.choices[0].message.content)

Node.js

          
          javascript
        
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LOBSTERS_TOKEN_KEY',
  baseURL: 'https://api.lobsterstoken.co.uk'
});

const chat = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{role: 'user', content: 'What is 2+2?'}]
});
console.log(chat.choices[0].message.content);