LLM ReferenceLLM Reference
OpenRouter

GPT-4 on OpenRouter

GPT-4 · OpenAI

Serverless

Last refreshed 2026-05-11. Next refresh: weekly.

Why use GPT-4 on OpenRouter?

OpenRouter offers GPT-4 with pay-as-you-go pricing at $30.00/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Compare GPT-4 across 4 providers to find the best fit for your use case
Input / 1M
$30.00
Output / 1M
$60.00
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: openai/gpt-4-0314
Model ID
openai/gpt-4-0314

Request example

Curated snippets for this provider are not sourced yet. Use OpenRouter documentation with model ID openai/gpt-4-0314.

Gotchas

  • Use provider model ID "openai/gpt-4-0314", not the LLMReference slug "gpt-4".

Compare GPT-4 Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenAI API$30.00$60.00
Azure OpenAI$30.00$60.00
Salesforce Einstein Generative AI
OpenRouter$30.00$60.00

Pricing

TypePrice (per 1M)
Input tokens$30.00
Output tokens$60.00

Capabilities

VisionMultimodalFunction CallingStructured OutputsCode Execution

About GPT-4

OpenAI's original GPT-4 model with strong reasoning and general knowledge. Foundation model for many applications.

FAQ

What does GPT-4 cost on OpenRouter?

On OpenRouter, GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens.

What is the context window for GPT-4 on OpenRouter?

GPT-4 supports a 8,191 token context window on OpenRouter.

How does OpenRouter compare to other GPT-4 providers?

GPT-4 is available from 4 providers. The cheapest input pricing is $30/1M tokens from OpenAI API.

What API model ID do I use for GPT-4 on OpenRouter?

Use the model ID openai/gpt-4-0314 when calling OpenRouter's API.

Who created GPT-4?

GPT-4 was created by OpenAI as part of the GPT-4 model family.

Is GPT-4 open source?

GPT-4 is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2023-03-14
Parameters1.76T (8x222B MoE)*
Context8K
ArchitectureMixture of Experts
Knowledge cutoff2021-09

Related Models on OpenRouter