openrouter
Auto Code
openrouter/auto-code
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Auto Code is a routing model offered through OpenRouter that, according to its catalog listing, is built specifically for coding agents and harnesses and shares the routing engine of OpenRouter's general Auto Router. The listing reports multimodal inputs (text, image, audio, file, and video) with text and image outputs, a two-million-token context window, and broad parameter support including tools and structured outputs. Because Auto Code routes requests to underlying models, behavior may vary by request. No independent model card or benchmark results were available in this source pack, so real-world performance requires workload validation.[1]
Strengths
- Catalog-reported: purpose-built routing for coding agents and harnesses, reusing OpenRouter's Auto Router engine.[1]
- Catalog-reported: accepts text, image, audio, file, and video inputs and returns text or image, suiting multimodal coding contexts.[1]
- Catalog-reported: two-million-token context window plus support for tools, structured outputs, and reasoning-related parameters.[1]
Limitations
- Evidence is catalog-only: no independent model card was available in this source pack, and no benchmark or measured performance data was reported.[1]
- As a router rather than a fixed model, output quality, latency, and cost can vary with the underlying model serving each request; catalog pricing fields are unspecified.[1]
- Catalog claims are unverified here; validate quality and cost on representative coding workloads before adoption.[1]
Where to use it
- Worth evaluating for agentic coding assistants and CLI or IDE harnesses that benefit from automatic model selection; editorial suggestion, not a measured result.[1]
- Potentially useful for development workflows mixing code with screenshots, documents, or other files, per the catalog's reported input modalities.[1]
- Teams needing long-context coding sessions could evaluate it, since the catalog reports a two-million-token window.[1]
Sources
- [1] OpenRouter catalog · Auto CodeSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://openrouter.ai/openrouter/auto), with every request treated as part of an...
Specifications
- Model ID
- openrouter/auto-code
- Creator
- openrouter
- Added to OpenRouter
- 05.11.2026
- 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.