> ## 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.
# Model
Information about an AI model available on OpenRouter
## Example Usage
```typescript theme={null}
import { Model } from "@openrouter/sdk/models";
let value: Model = {
architecture: {
inputModalities: [
"text",
],
modality: "text->text",
outputModalities: [
"text",
],
},
canonicalSlug: "openai/gpt-4",
contextLength: 8192,
created: 1692901234,
defaultParameters: null,
id: "openai/gpt-4",
links: {
details: "/api/v1/models/openai/gpt-5.4/endpoints",
},
name: "GPT-4",
perRequestLimits: null,
pricing: {
completion: "0.00006",
prompt: "0.00003",
},
supportedParameters: [
"temperature",
"top_p",
"max_tokens",
],
supportedVoices: null,
topProvider: {
isModerated: true,
},
};
```
## Fields
| Field | Type | Required | Description | Example |
| --------------------- | ----------------------------------------------------------- | -------------------- | ---------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `aliasTarget` | [models.ModelAliasTarget](../models/modelaliastarget.mdx) | :heavy\_minus\_sign: | Concrete model targeted by this tilde-latest alias, when applicable | \{
"name": "Claude Sonnet 4.5",
"slug": "anthropic/claude-sonnet-4.5"
} |
| `architecture` | [models.ModelArchitecture](../models/modelarchitecture.mdx) | :heavy\_check\_mark: | Model architecture information | \{
"input\_modalities": \[
"text"
],
"instruct\_type": "chatml",
"modality": "text-\u003etext",
"output\_modalities": \[
"text"
],
"tokenizer": "GPT"
} |
| `benchmarks` | [models.ModelBenchmarks](../models/modelbenchmarks.mdx) | :heavy\_minus\_sign: | Third-party benchmark rankings for this model. Omitted when no benchmark data is available. | \{
"artificial\_analysis": \{
"agentic\_index": 55.8,
"coding\_index": 63.2,
"intelligence\_index": 71.4
},
"design\_arena": \[
\{
"arena": "models",
"category": "website",
"elo": 1385.2,
"rank": 5,
"win\_rate": 62.5
}
]
} |
| `canonicalSlug` | *string* | :heavy\_check\_mark: | Canonical slug for the model | openai/gpt-4 |
| `contextLength` | *number* | :heavy\_check\_mark: | Maximum context length in tokens | 8192 |
| `created` | *number* | :heavy\_check\_mark: | Unix timestamp of when the model was created | 1692901234 |
| `defaultParameters` | [models.DefaultParameters](../models/defaultparameters.mdx) | :heavy\_check\_mark: | Default parameters for this model | \{
"frequency\_penalty": 0,
"presence\_penalty": 0,
"repetition\_penalty": 1,
"temperature": 0.7,
"top\_k": 0,
"top\_p": 0.9
} |
| `description` | *string* | :heavy\_minus\_sign: | Description of the model | GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy. |
| `expirationDate` | *string* | :heavy\_minus\_sign: | The date after which the model may be removed. ISO 8601 date string (YYYY-MM-DD) or null if no expiration. | 2025-06-01 |
| `huggingFaceId` | *string* | :heavy\_minus\_sign: | Hugging Face model identifier, if applicable | microsoft/DialoGPT-medium |
| `id` | *string* | :heavy\_check\_mark: | Unique identifier for the model | openai/gpt-4 |
| `knowledgeCutoff` | *string* | :heavy\_minus\_sign: | The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown. | 2024-10-01 |
| `links` | [models.ModelLinks](../models/modellinks.mdx) | :heavy\_check\_mark: | Related API endpoints and resources for this model. | \{
"details": "/api/v1/models/openai/gpt-5.4/endpoints"
} |
| `name` | *string* | :heavy\_check\_mark: | Display name of the model | GPT-4 |
| `perRequestLimits` | [models.PerRequestLimits](../models/perrequestlimits.mdx) | :heavy\_check\_mark: | Per-request token limits | \{
"completion\_tokens": 1000,
"prompt\_tokens": 1000
} |
| `pricing` | [models.PublicPricing](../models/publicpricing.mdx) | :heavy\_check\_mark: | Pricing information for the model | \{
"completion": "0.00006",
"image": "0",
"prompt": "0.00003",
"request": "0"
} |
| `reasoning` | [models.ModelReasoning](../models/modelreasoning.mdx) | :heavy\_minus\_sign: | Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models. | \{
"default\_effort": "medium",
"default\_enabled": true,
"mandatory": false,
"supported\_efforts": \[
"high",
"medium",
"low",
"minimal"
]
} |
| `supportedParameters` | [models.Parameter](../models/parameter.mdx)\[] | :heavy\_check\_mark: | List of supported parameters for this model | |
| `supportedVoices` | *string*\[] | :heavy\_check\_mark: | List of supported voice identifiers for TTS models. Null for non-TTS models. | null |
| `topProvider` | [models.TopProviderInfo](../models/topproviderinfo.mdx) | :heavy\_check\_mark: | Information about the top provider for this model | \{
"context\_length": 8192,
"is\_moderated": true,
"max\_completion\_tokens": 4096
} |