Cheapest LLM gateway options

Passthrough + fee

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

Passthrough

Microsoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.

Subscription

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

Subscription

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

~100 models · Free OSS

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Passthrough + fee

AI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.

Passthrough + fee

Commercial LLM router that dynamically routes each query to the best-suited model with load balancing and fallback handling, charging 3% of underlying AI spend.

Enterprise quote

Predictive model router that determines the best LLM for each query; claims up to 25% accuracy gains and 10x cost reduction; powers OpenRouter's auto mode and is positioned specifically for coding agents.

Passthrough

OpenAI's native auto-routing mode (GPT-5 Auto) that dynamically routes each API request between GPT-5 and GPT-5 Instant based on prompt complexity, with no extra charge beyond model token costs.

~400 models · Passthrough

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

~1.6K models · Subscription

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

~400 models · Passthrough + fee

AI gateway to 400+ LLM providers with intelligent routing, caching, guardrails, and governance; flat 5% markup on model costs with no subscription fee.

~250 models · Subscription

Unified LLM engineering platform (gateway + observability + evals + prompt management) routing across 250+ models; previously Keywords AI, rebranded February 2026.

Free OSS

Open-source LLM routing framework from LMSYS that routes simpler queries to a cheaper weak model and harder ones to a stronger frontier model, achieving 35–85% cost reduction on benchmarks.

Subscription

Benchmark-driven LLM router using a neural scorer and live runtime benchmarks refreshed every 10 minutes to route each request to the optimal endpoint across 100+ providers.

Free OSS

Open-source Mixture-of-Models router that semantically classifies each request and routes it to the best backend (local, private, or frontier) by cost, latency, privacy, or safety, deployed as an Envoy External Processor.