Request Access For A Free Trial
Processing...
Processing...
Thanks for requesting access to Abacus.AI, we will get back to you shortly
RouteLLM API
One API.
Every frontier LLM.
Access 170+ models — GPT, Claude, Gemini, Grok, DeepSeek, Qwen and more — through a single OpenAI-compatible API. Smart routing picks the best model for every prompt while preserving prompt caching.
$10 $7 for the first month, then $10 billed monthly
- Included with ChatLLM Teams
- OpenAI-compatible API
- Cancel anytime
- Summarise this 40-page contract
- Write the SQL migration
- Draft a reply to this email
RouteLLM
- GPT-6 Astra OpenAI
- Opus 5.5 Anthropic
- Gemini 3.1 Pro Google
- Grok 4.7 xAI
- Kimi K3 Open model
- Nano Banana Pro Image
Key Features
Why RouteLLM
One API for every LLM
GPT, Claude, Gemini, Grok and 170+ more behind one endpoint.
Smart routing to the best model
Every prompt is matched to the model that answers it best.
100+ AI Models
Text, image, audio and video models — new releases added as they launch.
Failover & prompt caching
Automatic failover between providers with built-in prompt caching robustness.
Get Started
Drop-in for the OpenAI SDK
- Sign up / Sign inCreate your Abacus.AI account in under a minute.
- Subscribe to ChatLLM Teams$7 for your first month (then $10/mo) unlocks the entire model catalog.
- Grab your API keyPoint your OpenAI SDK at our base URL and ship.
from openai import OpenAI
client = OpenAI(
base_url="https://routellm.abacus.ai/v1",
api_key="YOUR_API_KEY")
r = client.chat.completions.create(
model="route-llm",
messages=[{"role": "user", "content": "Hello!"}])Works with Claude Code, Codex CLI and Cursor
The Catalog
Every provider, one bill
OpenAI
Anthropic
Google
xAI
Open models
Automatic
RouteLLM picks the best one for each task.
Image
Video
Questions, answered
- What is the RouteLLM API?
-
RouteLLM API is a multi-LLM API and router and is offered as part of the ChatLLM subscription that costs $10 a month.
RouteLLM will route to the best LLM by default, based on your prompt. You can also provide an LLM name as one of the parameters and invoke that specific LLM in the API.
You can access ANY LLM model using this unified API. Benefits include great prices, automatic failover, and very high uptime.
- How does it work?
-
Sign up as a ChatLLM subscriber and click on the RouteLLM API icon in the lower left corner to access API documentation and details.
You can then invoke the API for an LLM and use the LLM in any of your applications. The ChatLLM subscription includes 20K credits, with each API call consuming credits proportional to the cost of the LLM call.
LLMs are typically priced at the best available price on the planet. We will publish the prices for each LLM in our RouteLLM API documentation.
- What is the price of each LLM?
-
Closed-source LLMs are priced based on the prices advertised by the provider (e.g., OpenAI, Anthropic, Gemini, etc). We DO NOT charge you more than what the provider does.
The prices are updated whenever the provider updates prices. For open-source LLMs, our prices typically match the best available price anywhere in the world. Please note: all of our LLLMs are located in the United States.
- How is my data protected?
-
We don't use your data for training; it's always encrypted, and we have enterprise compliance, including SOC-2 Type-2 and HIPAA.
- How can I cancel my subscription?
-
You can cancel the subscription anytime using the ChatLLM interface. Billing subscription details are available on the desktop interface by clicking on the top right corner and going to the Billing and Invoices page from your profile.
Trusted by teams at
