Auto Router

openrouter · Released Nov 8, 2023
DFO score #641 / 694
8.4 leaderboard score
Speed
– Not reported
Input Price #1 / 694
$-1,000,000.000 per 1M tokens
Output Price #1 / 694
$-1,000,000.000 per 1M tokens
Context #1 / 694
2M tokens

Analysis Summary

Auto Router is presented as a routing option rather than a single underlying language model. The record lists tool use, function calling, vision, and text, image, file, audio, and video modalities, alongside a 2M context window. It supplies no model-specific benchmark results, and the listed pricing values do not provide a usable cost estimate.

The breadth of listed inputs and integrations could be useful in a workflow that needs routing across varied task types. However, this data does not identify which models handle requests, how routing decisions affect output quality, or what reliability to expect. That makes it difficult to assess for consistent client-facing content or agentic work.

Evaluate it only after confirming routing behavior, underlying model choices, and actual pricing. Without those details, teams should not treat its listed breadth as evidence of dependable production performance.

Assessed September 23, 2026

Editorial notes

Auto Router lists broad multimodal and tool capabilities with a 2M context, but it is a routing product rather than a benchmarked model, and its pricing fields are unusable as costs.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

Auto Router lists broad multimodal and tool capabilities with a 2M context, but it is a routing product rather than a benchmarked model, and its pricing fields are unusable as costs.

#641 of 694 overall Down 1 this week

How Auto Router compares

Its 2M-token context window is larger than 100% of the models we list. At $-1,000,000.00 per million input tokens it is cheaper than 100% of comparable models.

Position in the field
DFO score: ahead of 9% of models #630
Context: larger than 100% of models #1
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Auto Router $-1,000,000.00 in $-1,000,000.00 out
Anthropic: Claude Opus 5.5 $4.00 in $20.00 out
Anthropic: Claude Sonnet 5.5 $2.00 in $10.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens

About Auto Router

The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on..

Frequently asked questions about Auto Router

How much does Auto Router cost?

Auto Router costs $-1,000,000.00 per million input tokens and $-1,000,000.00 per million output tokens.

What is the context window of Auto Router?

Auto Router has a context window of 2,000,000 tokens (2M).

What can Auto Router do?

Auto Router supports image/vision input, tool use, and function calling.

Who created Auto Router?

Auto Router is developed by Openrouter and was released on November 8, 2023.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.