Model - Go SDK

Model type definition

The Go SDK and docs are currently in beta. Report issues on GitHub.

Information about an AI model available on OpenRouter

Fields

FieldTypeRequiredDescriptionExample
Architecturecomponents.ModelArchitecture✔️Model architecture information{"input_modalities": ["text"],"instruct_type": "chatml","modality": "text-\u003etext","output_modalities": ["text"],"tokenizer": "GPT"}
CanonicalSlugstring✔️Canonical slug for the modelopenai/gpt-4
ContextLengthint64✔️Maximum context length in tokens8192
Createdint64✔️Unix timestamp of when the model was created1692901234
DefaultParameters*components.DefaultParameters✔️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*stringDescription of the modelGPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.
ExpirationDateoptionalnullable.OptionalNullable[string]The date after which the model may be removed. ISO 8601 date string (YYYY-MM-DD) or null if no expiration.2025-06-01
HuggingFaceIDoptionalnullable.OptionalNullable[string]Hugging Face model identifier, if applicablemicrosoft/DialoGPT-medium
IDstring✔️Unique identifier for the modelopenai/gpt-4
KnowledgeCutoffoptionalnullable.OptionalNullable[string]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
Linkscomponents.ModelLinks✔️Related API endpoints and resources for this model.{"details": "/api/v1/models/openai/gpt-5.4/endpoints"}
Namestring✔️Display name of the modelGPT-4
PerRequestLimits*components.PerRequestLimits✔️Per-request token limits{"completion_tokens": 1000,"prompt_tokens": 1000}
Pricingcomponents.PublicPricing✔️Pricing information for the model{"completion": "0.00006","image": "0","prompt": "0.00003","request": "0"}
SupportedParameters[]components.Parameter✔️List of supported parameters for this model
TopProvidercomponents.TopProviderInfo✔️Information about the top provider for this model{"context_length": 8192,"is_moderated": true,"max_completion_tokens": 4096}