On-Demand
Free
- Router access with LLM usage at provider cost, up to 70 minutes of TTS, built for evaluation and prototyping
Respan Gateway: up to 55% off tokens on Gemini, GPT, Claude and 1,000+ more models. One API key, 0% fee.
Inworld Router, which Inworld also calls the Realtime Router, is an LLM router from Inworld AI, the realtime voice and model company founded in 2021. One endpoint compatible with both the OpenAI and Anthropic SDKs reaches 220+ models, and routed third-party models bill at the provider's rate with no markup, including on your own keys.
Routing is rule-based and built around experiments, which sets it apart from LLM routers that pick a model from the prompt alone. Conditions written in CEL route on any request metadata, such as language, plan tier, or detected emotion, and traffic can be split between models with sticky user assignment for A/B tests. Because Inworld also builds voice models, a single chat completions request can return both text and synthesized speech.
Observability is request-level. Each call logs the model chosen, the attempt chain, time to first token, cost, and the routing reason, and that data can stream to Mixpanel or BigQuery. Inworld's own guidance for A/B tests is to measure quality in your own analytics, and the product has no built-in evals or scoring.
Core capabilities this platform advertises.
What this tool does well, and the limitations to keep in mind.
Pros
Cons
What's included in each plan, and how the tiers compare.
Free
$25
Per month
$100
Per month
$300
Per month
$1,500
Per month
Custom
Contact sales for a quote
Consumer AI apps, voice agents, and AI companions that need to route by user, test models on live traffic, and add speech output
Respan is the AI router with observability and automated evals built in. When you compare one model against another, Respan scores each model's output on live traffic and links every score to the trace behind it, so you measure quality directly instead of inferring it from downstream analytics.
Respan routes every call across 1,000+ models and scores the output on live production traffic, so you can see which model actually answers better before ramping it to 100%. Every score links back to the trace behind it. Start free.
Top companies in LLM Gateways you can use instead of InWorld AI.
Respan
One API for 1,000+ models
OpenRouter
One OpenAI-compatible API for 500+ models from 80+ providers
Cloudflare AI Gateway
Edge-deployed AI gateway
Vercel AI Gateway
One API key for hundreds of models
Bifrost
OpenAI-compatible API for 1,000+ models from 20+ providers
Portkey
Unified API across major providers
LiteLLM
OpenAI-compatible proxy for 140+ providers
Stainless
SDK generation
Helicone
LLM observability and monitoring
Unify
Kong AI Gateway
AI traffic management
Martian
Intelligent model routing based on prompt type
Apigee AI Gateway
Google Cloud AI traffic management
Requesty
400+ model access
The Token Company
Token compression
Condense
Drop-in proxy: change one base URL, keep your own provider key
TrueFoundry
AI Gateway with routing, fallbacks, rate limits, and budgets
OrcaRouter
orcarouter/auto adaptive routing per request
Orq.ai
AI gateway for 500+ models with fallbacks, retries, and load balancing
Side-by-side comparisons with other tools in this category.
Companies from adjacent layers in the AI stack that work well with InWorld AI.