Auto Router (Beta)
by OpenRouter · openrouter/auto-beta · #1 cheapest of 422 paid models
Prices updated Sep 19, 2026, 5:49 PM UTC · refreshed hourly
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$-1.0e+6
per 1M tokens
Output
$-1.0e+6
per 1M tokens
Blended (3:1)
$-1.0e+6
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Auto Router (Beta) (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $-1.0e+6 | $-1.03e+5 | — |
| 50% | $-1.0e+6 | $-1.03e+5 | −0% |
| 90% | $-1.0e+6 | $-1.03e+5 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $-8.00e+2 | $-8.00e+5 |
| Document summary | 8,000 | 1,000 | $-9.00e+3 | $-9.00e+6 |
| Codebase question (RAG) | 30,000 | 2,000 | $-3.20e+4 | $-3.20e+7 |
| Long-context analysis | 150,000 | 5,000 | $-1.55e+5 | $-1.55e+8 |
Specs
Context window
2M
tokens
Max output
—
tokens
Input modalities
text, image, audio, file, video
Tokenizer
Router