Use the OpenAI SDK you already know. Just change the base URL and access 300+ AI models through a single, intelligent router layer.
// Just change the baseURLbaseURL: 'https://api.eachlabs.ai/v1'Get started in under 2 minutes with your favorite language.
These are the canonical model identifiers currently shown for eachlabs-llm-router.
openai/gpt-5.2
OpenAI frontier model for advanced reasoning, coding, tool use, and production text generation through the Eachlabs LLM Router.
Use GPT-5.2 for high-quality reasoning, code generation, long-form writing, and complex tool workflows.
The catalog maps this model to OpenRouter through an explicit llm-router route.
openai/gpt-5.5
OpenAI frontier model for advanced reasoning, coding, and high-quality assistant workloads through the Eachlabs LLM Router.
Use GPT-5.5 for demanding reasoning, coding, and production assistant workloads that need the strongest OpenAI model available in the router.
The catalog maps this model to OpenRouter through an explicit llm-router route.
openai/gpt-5.4-mini
Efficient OpenAI model for lower-latency chat, extraction, classification, and lightweight reasoning through the Eachlabs LLM Router.
Use GPT-5.4 Mini when you want an OpenAI model optimized for speed and cost while retaining broad general-purpose capability.
The catalog maps this model to OpenRouter through an explicit llm-router route.
openai/gpt-5.1
OpenAI frontier model for balanced reasoning, speed, and general-purpose assistant workloads through the Eachlabs LLM Router.
Use GPT-5.1 when you need a strong general-purpose model with dependable reasoning and broad task coverage.
Yes. The catalog uses the OpenRouter-compatible model id and keeps legacy openai-responses aliases hidden.
openai/gpt-4.1
OpenAI model for reliable text generation, extraction, coding, and structured assistant workflows.
Use GPT-4.1 for dependable general-purpose generation and structured output workloads.
No. This entry documents the existing explicit route and does not alter runtime routing.
openai/gpt-4.1-mini
Efficient OpenAI model for lower-latency text generation, classification, extraction, and chat workloads.
Use GPT-4.1 Mini when latency and cost matter more than maximum reasoning depth.
Yes. The visible catalog prefers canonical OpenRouter-style ids while preserving legacy aliases as hidden compatibility entries.
openai/gpt-4.1-nano
Small OpenAI model for fast classification, simple extraction, rewriting, and lightweight chat workloads.
Use GPT-4.1 Nano for simple tasks where speed and low cost are the main requirements.
It is a compact OpenAI model with an explicit OpenRouter route and observed production need.
openai/gpt-4o-mini
Fast OpenAI model for everyday chat, short-form generation, classification, and extraction tasks.
Use GPT-4o Mini for fast general-purpose requests that do not require a frontier reasoning model.
It is routed to OpenRouter explicitly to avoid observed Requesty quota errors.
vertex/gemini-3-flash-preview
Google Gemini preview model for fast multimodal and text workloads through the Eachlabs LLM Router.
Use it for fast Gemini-family experiments and preview workloads where model availability is acceptable.
The customer-facing Vertex id maps to the OpenRouter Google Gemini target model.
vertex/gemini-3.1-flash-lite-preview
Lightweight Gemini preview model for low-latency text and multimodal workflows through OpenRouter.
Use it for low-latency Gemini workloads where a preview model is acceptable.
No. The current route sends the request through OpenRouter with a Google Vertex provider preference.
google/gemini-3.5-flash
Google Gemini Flash model for fast multimodal and text workloads through the Eachlabs LLM Router.
Use Gemini 3.5 Flash for fast Gemini-family text and multimodal workloads.
The catalog maps the Google model id to OpenRouter through an explicit llm-router route.
vertex/gemini-2.5-flash
Gemini 2.5 Flash remains on the explicit Requesty legacy route while OpenRouter migration continues.
It is intentionally pinned as a legacy route until OpenRouter compatibility is validated.
Yes. This catalog keeps the model visible and marks the Requesty route explicitly.
anthropic/claude-sonnet-4-6
Anthropic Claude Sonnet model routed through OpenRouter using its supported target slug.
Eachlabs keeps the existing customer-facing model ID, while the router maps it to OpenRouter's supported `anthropic/claude-sonnet-4.6` target slug.
Yes. The routing config explicitly sends this model to OpenRouter.
anthropic/claude-opus-4-6
Anthropic Claude Opus model kept on Requesty legacy routing until OpenRouter compatibility is proven.
Use Claude Opus 4.6 for high-quality Anthropic reasoning and writing workloads.
No. This catalog marks it as a visible Requesty legacy model for now.
groq/llama-4-scout
Meta Llama model routed through OpenRouter with Groq provider preference for fast open-weight inference.
Use it for fast open-weight model workflows where Llama compatibility is desired.
The public id keeps the provider hint while the route maps to OpenRouter's Meta Llama target model.
byteplus/seed-2-0-mini
BytePlus Seed model routed through the explicit BytePlus Ark provider for lightweight text workloads.
Use it for lightweight text tasks that should remain on the BytePlus Ark provider.
No. It remains an explicit BytePlus route and is included to keep non-OpenRouter routes testable.
deepseek/deepseek-v4-pro
DeepSeek frontier Mixture-of-Experts model with a 1M-token context for advanced reasoning, coding, math, and long-horizon agent workflows through the Eachlabs LLM Router.
Use DeepSeek V4 Pro for demanding reasoning, coding, and long-context agent workloads where you want a strong open-weight frontier model.
The catalog maps this model to OpenRouter through an explicit llm-router route using the canonical deepseek/deepseek-v4-pro target model.
deepseek/deepseek-v4-flash
Efficiency-optimized DeepSeek Mixture-of-Experts model with a 1M-token context for fast, low-cost text generation, classification, and lightweight reasoning through the Eachlabs LLM Router.
Use DeepSeek V4 Flash when you want low latency and low cost while keeping broad general-purpose and long-context capability.
The catalog maps this model to OpenRouter through an explicit llm-router route using the canonical deepseek/deepseek-v4-flash target model.
anthropic/claude-fable-5
Anthropic Claude Fable 5 frontier model with a 1M-token context for advanced reasoning, coding, knowledge work, and long-horizon agent workflows, routed through OpenRouter via the Eachlabs LLM Router.
Use Claude Fable 5 for the most demanding Anthropic reasoning, coding, and long-context agent workloads where maximum capability matters more than cost.
The catalog maps this model to OpenRouter through an explicit llm-router route using the canonical anthropic/claude-fable-5 target model.
anthropic/claude-mythos-5
Anthropic Claude Mythos 5 served through Requesty's legacy Anthropic route while an OpenRouter slug is unavailable; routing flips to OpenRouter once published, with no change to the customer-facing model id.
Use Claude Mythos 5 for demanding Anthropic reasoning and writing workloads where you want the latest Mythos-series model.
It is intentionally pinned to the explicit Requesty Anthropic route until an OpenRouter target slug is available. When OpenRouter publishes the model, the catalog and route flip to OpenRouter (explicit_route + target_model) with no change to the anthropic/claude-mythos-5 model id.
Your existing OpenAI SDK code works instantly. Just swap the base URL and API key.
Our LLM router automatically selects the best model provider for your request.
No monthly fees. Only pay for what you use with transparent per-request pricing. (5% platform fee is applied for all the LLM models)