# Zurelay Auto

> zurelay-auto picks the model that fits each request and bills that model's price: how it picks, what you pay, which model answered and how it falls back.

Source: https://zurelay.com/docs/auto

One model name, `zurelay-auto`, that answers each request with the model that fits it. You pay the price of the model that answered, and the answer names it. It works wherever a model ID does, with the same streaming, tools and reasoning levels.

**Python** (`main.py`):

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key=os.environ["ZURELAY_API_KEY"],
)

response = client.chat.completions.create(
    model="zurelay-auto",
    messages=[
      {
        "role": "user",
        "content": "Summarize this in one sentence: Zurelay is one API for many models."
      }
    ],
)

print(response.choices[0].message.content)
```

**Node.js** (`index.mjs`):

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.zurelay.com/v1",
  apiKey: process.env.ZURELAY_API_KEY,
});

const response = await client.chat.completions.create({
  "model": "zurelay-auto",
  "messages": [
    {
      "role": "user",
      "content": "Summarize this in one sentence: Zurelay is one API for many models."
    }
  ]
});

console.log(response.choices[0].message.content);
```

**cURL**:

```bash
curl https://api.zurelay.com/v1/chat/completions \
  -H "Authorization: Bearer $ZURELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "zurelay-auto",
  "messages": [
    {
      "role": "user",
      "content": "Summarize this in one sentence: Zurelay is one API for many models."
    }
  ]
}'
```

## How it picks

Auto reads what the request carries and picks without calling a model of its own, so it adds no delay and costs nothing on top. Each request lands in one of three tiers:

| The request | Goes to |
| --- | --- |
| Short chat, questions, extraction, summaries | Fast, low-cost models |
| Tools, a JSON schema to follow (`response_format` of type `json_schema`), code, a prompt over 32K tokens, or `reasoning_effort` low or medium | Stronger models |
| `reasoning_effort` high, xhigh or max, or Anthropic `thinking` with a large budget | The strongest models |

In its tier, it takes the first model that reads every image, PDF, audio clip or video the request sends, whose context window holds the prompt and its `max_tokens`, and that takes a reasoning level when you set one. Your `reasoning_effort` runs at the closest level that model takes.

## The models it picks from

Each tier in the order Auto tries them, with their prices per 1M input and output tokens. The list changes as better or cheaper models arrive; your code doesn't have to.

| Tier | Model | Input / output per 1M |
| --- | --- | --- |
| Everyday | [DeepSeek V4.1 Flash](https://zurelay.com/models/deepseek-v4.1-flash) | $0.037 / $0.15 |
|  | [Gemini 3.1 Flash-Lite](https://zurelay.com/models/gemini-3.1-flash-lite) | $0.10 / $0.59 |
|  | [Gemini 3.5 Flash-Lite](https://zurelay.com/models/gemini-3.5-flash-lite) | $0.12 / $1.04 |
|  | [GPT-6 Luna](https://zurelay.com/models/gpt-6-luna) | $0.025 / $0.125 |
|  | [Qwen 3.8 Flash](https://zurelay.com/models/qwen3.8-flash) | $0.07 / $0.22 |
|  | [Claude Haiku 4.5](https://zurelay.com/models/claude-haiku-4-5) | $0.38 / $1.90 |
| Tools, code, structure | [Claude Sonnet 5.5](https://zurelay.com/models/claude-sonnet-5-5) | $0.80 / $4.00 |
|  | [GPT-6 Sol](https://zurelay.com/models/gpt-6-sol) | $0.50 / $2.50 |
|  | [Gemini 3.7 Flash](https://zurelay.com/models/gemini-3.7-flash) | $0.32 / $1.59 |
|  | [GPT-6.1 Sol](https://zurelay.com/models/gpt-6.1-sol) | $0.50 / $2.50 |
|  | [DeepSeek V4 Pro 0813](https://zurelay.com/models/deepseek-v4-pro-0813) | $0.23 / $0.62 |
| Deep reasoning | [Claude Opus 5.5](https://zurelay.com/models/claude-opus-5-5) | $1.40 / $7.00 |
|  | [GPT-6.1 Sol](https://zurelay.com/models/gpt-6.1-sol) | $0.50 / $2.50 |
|  | [GPT-6 Astra](https://zurelay.com/models/gpt-6-astra) | $2.50 / $12.50 |
|  | [Claude Fable 5.1](https://zurelay.com/models/claude-fable-5-1) | $3.50 / $17.50 |

## What you pay

Each request is billed at the price of the model that answered it, at that model's rates on Zurelay, with nothing added for the pick: today from $0.025 to $3.50 per 1M input tokens and from $0.125 to $17.50 per 1M output tokens. Requests that fail are never billed.

## Which model answered

The answer's `model` field and the `x-zurelay-model` header name the model that answered, and `x-zurelay-routed-from: zurelay-auto` says Auto picked it. Requests in the dashboard shows the same.

Response:

```
HTTP/1.1 200 OK
x-zurelay-model: deepseek-v4.1-flash
x-zurelay-routed-from: zurelay-auto

{
  "model": "deepseek-v4.1-flash",
  "choices": [{ "message": { "role": "assistant", "content": "…" } }],
  …
}
```

## When a model can't answer

Auto is built to answer:

1. The model it picks heals like any model on Zurelay: it retries, then uses that model's backup routes.
2. If it still can't answer, Auto moves on to the rest of the request's tier, then the tier above, then the one below, up to five models in all.
3. Only if every one of them fails do you get a `503` with `model_unavailable` and a `retry-after` header.

This doesn't depend on your [smart routing](https://zurelay.com/docs/smart-routing) setting: Auto always does it, and the `x-zurelay-fallback` header and a request's `models` list don't change it.

## Anthropic format

`POST /v1/messages` takes `zurelay-auto` too. There Auto picks among Claude models, the ones that take Anthropic's format, so the Anthropic SDKs and tools built on them work as they do with any Claude model.

## API keys

A key limited to `zurelay-auto` (see [key rules](https://zurelay.com/docs/key-rules)) can use whichever model Auto picks. Spend limits and rate limits apply as usual. The short ID `auto` works too.

## Errors

- **400** `unsupported_content`: none of its models reads the media the request sends together, such as audio and a PDF in one request. Send them separately, or pick a model that reads both.
- **400** `context_length_exceeded`: the request is longer than any of its models can read. Send a shorter one or ask for less output.
- **503** `model_unavailable`: every model it tried failed. Retry after the `retry-after` header.

> **Want the same model every time?:** Use its own ID. Auto's choices can change as models improve, so pin a model where you need its exact behavior.

- [Chat completions](https://zurelay.com/docs/chat): Messages, streaming, tools and reasoning.
- [Models](https://zurelay.com/docs/models): Every model, what it reads and what it costs.
- [Smart routing](https://zurelay.com/docs/smart-routing): Fallbacks for the models you pick yourself.