CallMissed
Back to all models
LLM Chatfree-tierauto-router

OpenRouter Auto

by OpenRouter · Released 2024

A smart auto-router that selects the best free model for each request based on prompt complexity, required capabilities (vision, tools, structured output), and model availability.

LLM Chat

OpenRouter Auto

Powered by OpenRouter · Router (meta-model)

Context Window

Varies

Parameters

Varies (routes to different models)

Max Output

Varies

Category

LLM Chat

Overview

OpenRouter Auto (model ID: openrouter/auto) is a meta-model that doesn't run inference itself — instead, it analyzes each incoming request and routes it to the optimal free model available on OpenRouter at that moment. The router intelligently filters for models that support the features your request needs, such as image understanding, tool calling, and structured outputs.

This makes it the simplest way to get started with CallMissed on the free tier: just set your model to "auto" and the router picks the best available free model for your specific prompt. If your request includes an image, it routes to a vision-capable model. If you need function calling, it picks a model that supports tools. If you just need text generation, it picks the fastest available option.

The router considers factors like prompt complexity, task type, and model capabilities when making its selection. Rate limits apply per the OpenRouter free tier: approximately 20 requests per minute per IP for accounts with less than $10 balance, and 1,000 requests per day for accounts with more than $10 balance.

On CallMissed, the "auto" model ID is an alias for openrouter/auto. It's available on the free tier and charges a small flat rate per call (2.00/10.00 per 1M tokens) to cover infrastructure costs, even though the upstream model inference is free.

Pricing

MetricPrice
Input /1M tokens₹200.0000
Output /1M tokens₹1000.0000

1 credit = ₹1 = $0.01 USD. Prices shown from provider; CallMissed passes through with ~35% markup.

Key Highlights

  • Free tier eligible — zero upstream model cost
  • Automatically selects the best model for each request
  • Supports vision, tool calling, and structured outputs via routing
  • Simplest way to get started — just set model to "auto"

Benchmarks

BenchmarkScore
RoutingDynamic
VisionSupported
ToolsSupported

Technical Details

  • Meta-model: routes to the best available free model per request
  • Filters by required capabilities: vision, tool calling, structured outputs
  • Rate limits: ~20 req/min (free tier), ~1,000 req/day (funded accounts)
  • Model ID alias: "auto" maps to "openrouter/auto" internally
  • Upstream cost: $0 (free models only)
  • CallMissed charges a small flat rate to cover infrastructure

Strengths

  • Zero upstream model cost — only CallMissed infrastructure fee
  • Automatic capability matching — no need to pick a model
  • Always routes to an available model — built-in fallback
  • Simplest onboarding: just use model "auto"

Limitations

  • No control over which specific model handles your request
  • Quality varies depending on which free model is selected
  • Rate limited by OpenRouter free tier (~20 req/min)
  • Not suitable for production workloads requiring consistent model behavior

Use Cases

Getting started quicklyFree tier usagePrototyping and testingLow-cost batch processing

API Example

curl https://api.callmissed.com/v1/chat/completions \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Endpoint: POST /v1/chat/completions · Model ID: openrouter/auto

Try OpenRouter Auto now

Get 1000 free API credits on signup. No credit card required.

Start free Read docs