Skip to content

Model detail

gpt-4

Provided by OpenAI
Pay-as-you-go

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.

Model specs

Context length
8.192K
Max output
8.192K
I/O modalities
Text
Released
2023-05

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$30.0000 /1M Tokens

Completion

$60.0000 /1M Tokens

Cache read

$15.0000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Difficult problems requiring high accuracy and broad knowledge

Use GPT-4 for complex problem-solving, multimodal tasks with text and image inputs, and applications requiring greater accuracy than previous models. It is a large-scale model capable of handling difficult reasoning across domains.

What should you check before using it?

Consider newer models for better cost and performance

GPT-4 is an older flagship model. Newer models like GPT-4o and GPT-4.1 offer improved speed and cost efficiency. Test your workload to confirm GPT-4 is the right fit.

Why use it through MixRoute?

Use the OpenAI-compatible endpoint with stable model ID

Use the confirmed compatible endpoint with model ID gpt-4 through MixRoute.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Share of the same prefix read repeatedly, up to 100%

09

FAQ

GPT-4 is OpenAI’s flagship large-scale multimodal language model, capable of solving difficult problems with greater accuracy than previous models. It supports both text and image inputs.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.