Features — Lobsters Token

50+ Models

50+ AI Models, One API

Stop managing multiple API keys. Lobsters Token connects you to OpenAI, Anthropic Claude, Google Gemini, Meta Llama, Mistral, and dozens more — through a single, unified endpoint.

GPT-4o & GPT-4o-mini
Claude 3.5 Sonnet & Claude 3.5 Haiku
Gemini 1.5 Pro & Flash
Llama 3.1 70B & 8B
Mistral Large & Mistral 7B
And 40+ more via OpenRouter

gpt-4o gpt-4o-mini claude-3-5-sonnet claude-3-5-haiku gemini-1.5-pro gemini-1.5-flash llama-3.1-70b llama-3.1-8b mistral-large mistral-7b mixtral-8x22b qwen-2.5-72b

Developer First

Built for Developers, By Developers

We obsess over the details so you don't have to. Clean REST API, WebSocket support, streaming responses, and comprehensive documentation.

OpenAI-compatible endpoints
Streaming (SSE) support
Multiple response formats (text, JSON, markdown)
Rate limiting & usage analytics
Webhook support for async tasks

            
            python
          
from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

99.9% Uptime

Enterprise-Grade Reliability

Infrastructure built on battle-tested cloud providers with automatic failover. Your apps keep running even when the internet has a bad day.

99.9% uptime SLA
<100ms median latency
24/7 infrastructure monitoring
Automatic failover & redundancy
Real-time status page

99.9%

Uptime SLA

<100ms

Median Latency

3

Global Regions

Cost Efficient

Pay Only for What You Use

No monthly commitments. No minimum spend. Transparent per-token pricing. Most workloads cost a fraction of going direct.

Our pricing is sourced from OpenRouter's routing fees plus a small margin — consistently cheaper than going direct for most models.

Model	Direct	Lobsters
gpt-4o	$0.005/1K in	$0.004/1K in
gpt-4o-mini	$0.00015/1K in	$0.00012/1K in
claude-3.5-sonnet	$0.003/1K in	$0.0024/1K in
gemini-1.5-flash	$0.000075/1K in	$0.00006/1K in

Secure

Enterprise-Grade Security

Your API keys are encrypted at rest and in transit. We never log your prompts or responses. SOC 2 Type II compliant infrastructure.

AES-256 encryption at rest
TLS 1.3 for all connections
API key scoping & permissions
Usage alerts & configurable rate limits
GDPR compliant data handling

🔒 Privacy First

We do not train on your data. Your prompts and responses are never stored beyond the session needed to deliver the response. Ever.

⚡ Key Scoping

Create multiple API keys with granular permissions. Limit by model, by spend, or by endpoint. Full control.

Global Edge

Low Latency, Worldwide

Edge nodes across North America, Europe, and Asia-Pacific. Your users get fast responses regardless of location.

🇺🇸 US East — Virginia
🇺🇸 US West — San Francisco
🇬🇧 London, UK
🇩🇪 Frankfurt, Germany
🇸🇬 Singapore

Response Time by Region

🇺🇸 US East~45ms

🇬🇧 London~65ms

🇩🇪 Frankfurt~72ms

🇸🇬 Singapore~95ms

Everything you need to build with AI.