Auto Router

General purposeVisionTools

OpenRouter · Released November 2023

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...

Facts and pricing

Provider
OpenRouter
Context window
2M tokens
Input price
-1.1e+7 credits / 1M tokens ($-1.0e+6 raw)
Output price
-1.1e+7 credits / 1M tokens ($-1.0e+6 raw)
Vision (image input)
Yes
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Auto Router now

Ask Auto Router anything. Your prompt opens in the Zeplik app with this model selected.

Auto Router

What Auto Router is best for

OpenRouter family

ModelContextInput cr/MOutput cr/MReleased
Fusion1M-1.1e+7-1.1e+7June 2026
Pareto Code Router2M-1.1e+7-1.1e+7April 2026
Free Models Router200K00February 2026
Body Builder (beta)128K-1.1e+7-1.1e+7December 2025
Auto Router2M-1.1e+7-1.1e+7November 2023

Frequently asked questions

What is Auto Router?
Auto Router is an AI model by OpenRouter. Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...
How much does Auto Router cost on Zeplik?
Input tokens cost -1.1e+7 credits per million and output tokens -1.1e+7 credits per million (1 credit = $0.10; the raw provider rates are $-1.0e+6 and $-1.0e+6 per million). New accounts start with free credits.
How long can a conversation with Auto Router be?
Auto Router has a 2M-token context window (2,000,000 tokens), which covers the conversation plus any documents you attach.
Does Auto Router support images and tools?
Auto Router accepts image input and supports tool calling.

Related models

FusionGeneral purpose

Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...

1M ctx-1.1e+7 cr/M outJune 2026
Pareto Code RouterCoding

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...

2M ctx-1.1e+7 cr/M outApril 2026
Free Models RouterGeneral purpose

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...

200K ctx0 cr/M outFebruary 2026
Body Builder (beta)Coding

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

128K ctx-1.1e+7 cr/M outDecember 2025
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
Auto Router - OpenRouter AI Model | Zeplik Chat