LLMRequest

Acustomizable llm router, with metrics and traces

Command and control LLMs from a single interface

dashboard
Client list

How it works

Route your requests based on your requested model

How to use

Configure an API Client and use it in your project.
OpenAI compatible : don't install additional library

1from openai import OpenAI
2
3client = OpenAI(
4    base_url="https://api.llmrequest.com/openai/v1/",
5    api_key="<llmr-private-api-key>"
6)
7
8response = client.chat.completions.create(
9    # translate to claude-3-5-sonnet by llmrequest
10    model="spell-checker-expert",
11    messages=[
12        {"role":"system","content":"Correct the spelling errors"},
13        {"role": "user", "content": "I like apples !"}
14    ]
15)

Features

What Makes Us Different

No additional libraries, effortlessly empower your AI features.

Metrics

Beautiful charts to understand your data consumption

One API for all LLMs

Use any LLM provider or your private infrastructure

Traces

Dig into your API requests and responses

Custom Model Names

Route your requests, based on custom model's name.

Privacy

We do not exploit or sell your data to third parties, ensuring you remain in control of your data.

No Hidden Costs

Use your own API key subscription to providers

Pricing

Choose your plan or start for free !

Free
$0/mo
Try it
Includes:
  • 600 requests per month
  • All providers
  • Traces for 3 days
  • Metrics for 1 month
Starter
$14/mo
Production ready
Includes:
  • 20k requests per month
  • Traces for 1 month
  • Metrics for 1 years
  • Support
Most Popular
Enterprise
$49/mo
Business requirements
Includes:
  • 100k requests per month
  • Traces for 1 month
  • Metrics for 1 years
  • Support
Premium
$239/mo
Heavy requirements
Includes:
  • 500k requests per month
  • Traces for 3 months
  • Metrics for 1 years
  • High priority support