> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# GetModelsRequest
## Example Usage
```typescript theme={null}
import { GetModelsRequest } from "@openrouter/sdk/models/operations";
let value: GetModelsRequest = {};
```
## Fields
| Field | Type | Required | Description | Example |
| ---------------------- | ----------------------------------------------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------- |
| `httpReferer` | *string* | :heavy\_minus\_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.
This is used to track API usage per application.
| |
| `appTitle` | *string* | :heavy\_minus\_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.
| |
| `appCategories` | *string* | :heavy\_minus\_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.
| |
| `offset` | *number* | :heavy\_minus\_sign: | Number of records to skip for pagination. When both offset and limit are omitted, the full list is returned | 0 |
| `limit` | *number* | :heavy\_minus\_sign: | Maximum number of records to return (max 1000). When both offset and limit are omitted, the full list is returned | 500 |
| `category` | [operations.GetModelsCategory](../../models/operations/getmodelscategory.mdx) | :heavy\_minus\_sign: | Filter models by use case category | programming |
| `supportedParameters` | *string* | :heavy\_minus\_sign: | Filter models by supported parameter (comma-separated) | temperature |
| `outputModalities` | *string* | :heavy\_minus\_sign: | Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text". | text |
| `sort` | [operations.GetModelsSort](../../models/operations/getmodelssort.mdx) | :heavy\_minus\_sign: | Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date), intelligence-high-to-low, coding-high-to-low, agentic-high-to-low (Artificial Analysis indices), design-arena-elo-high-to-low (best Design Arena ELO across arenas). Models without a score for the chosen benchmark are placed last. When omitted, the existing default ordering is preserved. | newest |
| `q` | *string* | :heavy\_minus\_sign: | Free-text search by model name or slug. | gpt-4 |
| `inputModalities` | *string* | :heavy\_minus\_sign: | Filter models by input modality. Comma-separated list of: text, image, audio, file. | text,image |
| `context` | *number* | :heavy\_minus\_sign: | Minimum context length (tokens). Models with smaller context are excluded. | 128000 |
| `minPrice` | *number* | :heavy\_minus\_sign: | Minimum prompt price in \$/M tokens. | 0 |
| `maxPrice` | *number* | :heavy\_minus\_sign: | Maximum prompt price in \$/M tokens. | 10 |
| `arch` | *string* | :heavy\_minus\_sign: | Filter models by architecture/model family (e.g. GPT, Claude, Gemini, Llama). | GPT |
| `modelAuthors` | *string* | :heavy\_minus\_sign: | Filter models by the organization that created the model. Comma-separated list of author slugs. | openai,anthropic |
| `providers` | *string* | :heavy\_minus\_sign: | Filter models by hosting provider. Comma-separated list of provider names. | OpenAI,Anthropic |
| `distillable` | [operations.Distillable](../../models/operations/distillable.mdx) | :heavy\_minus\_sign: | Filter by distillation capability. "true" returns only distillable models, "false" excludes them. | true |
| `zdr` | [operations.Zdr](../../models/operations/zdr.mdx) | :heavy\_minus\_sign: | When set to "true", return only models with zero data retention endpoints. | true |
| `region` | [operations.Region](../../models/operations/region.mdx) | :heavy\_minus\_sign: | Filter to models with endpoints in the given data region. Currently only "eu" is supported. | eu |
| `minOutputPrice` | *number* | :heavy\_minus\_sign: | Minimum completion (output) price in \$/M tokens. | 0 |
| `maxOutputPrice` | *number* | :heavy\_minus\_sign: | Maximum completion (output) price in \$/M tokens. | 10 |
| `minAgeDays` | *number* | :heavy\_minus\_sign: | Minimum model age in days since its creation date. | 0 |
| `maxAgeDays` | *number* | :heavy\_minus\_sign: | Maximum model age in days since its creation date. | 90 |
| `minIntelligenceIndex` | *number* | :heavy\_minus\_sign: | Minimum Artificial Analysis intelligence index. | 50 |
| `maxIntelligenceIndex` | *number* | :heavy\_minus\_sign: | Maximum Artificial Analysis intelligence index. | 100 |
| `minCodingIndex` | *number* | :heavy\_minus\_sign: | Minimum Artificial Analysis coding index. | 50 |
| `maxCodingIndex` | *number* | :heavy\_minus\_sign: | Maximum Artificial Analysis coding index. | 100 |
| `minAgenticIndex` | *number* | :heavy\_minus\_sign: | Minimum Artificial Analysis agentic index. | 50 |
| `maxAgenticIndex` | *number* | :heavy\_minus\_sign: | Maximum Artificial Analysis agentic index. | 100 |
| `minToolSuccessRate` | *number* | :heavy\_minus\_sign: | Minimum tool-calling success rate, as a fraction in \[0, 1] (e.g. 0.9 = 90% of requests finishing with a tool\_calls finish reason). | 0.9 |
| `maxToolSuccessRate` | *number* | :heavy\_minus\_sign: | Maximum tool-calling success rate, as a fraction in \[0, 1]. | 1 |