openrouter
Auto Router (Beta)
openrouter/auto-beta
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, openrouter/auto-beta is the experimental beta track of the platform's general-purpose Auto Router, which automatically routes requests across models. The catalog lists text, image, audio, file, and video inputs with text and image outputs, a two-million-token context window, and support for tools, structured outputs, and reasoning parameters. No benchmarks or independent model card appear in this source pack, so capabilities are catalog-reported rather than measured; the beta label suggests behavior may change without notice.[1]
Strengths
- Catalog lists unusually broad input support — text, images, audio, files, and video — with text and image output.[1]
- Automatic general-purpose routing removes the need to pick a specific model, and the catalog advertises a two-million-token context window.[1]
- Exposes a wide parameter surface per the catalog, including tools, structured outputs, seed, logprobs, and reasoning controls.[1]
Limitations
- It is an experimental beta, and the catalog itself warns users to expect beta behavior; stability and routed-model choice may change.[1]
- Evidence is catalog-only: no independent model card, benchmark results, knowledge cutoff, or fixed token pricing were available in this source pack.[1]
- Because routing is automatic, the catalog does not identify which underlying model serves a given request; validate quality on your own workload.[1]
Where to use it
- Prototyping assistants or agents where automatic model selection is acceptable and beta-level stability is tolerable.[1]
- A single endpoint for multimodal prompts mixing text with images, audio, files, or video, provided the catalog's modality claims hold for your inputs.[1]
- Early evaluation of OpenRouter's newest routing improvements before they reach the stable router.[1]
Sources
- [1] OpenRouter catalog · Auto Router (Beta)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- openrouter/auto-beta
- Creator
- openrouter
- Added to OpenRouter
- 17.07.2026
- Context length
- 2,000,000
- Modality
- text+image+file+audio+video->text+image
- Input modalities
- text, image, audio, file, video
- Output modalities
- text, image
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | output: image |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
Provider details are unavailable right now; the catalog data above is unaffected.
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.