GPT-4
Where it stands
Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.
About this model
GPT-4 is an AI model from OpenAI, made available through the API on May 28, 2023. It can read up to 8,191 tokens in one request, roughly 15 pages of text, and write up to 4,096 tokens in a single answer.
Through the API it costs $30 per million input tokens and $60 per million output tokens. It is among the more expensive models we track, a price usually reserved for the most capable, flagship-class models.
It can call tools and functions, so developers can connect it to search, databases or other software.
Quality scores
Rankings →- GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.35.7%#108 of 116
- AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.1.1%#111 of 112
Where to use it
Companies that serve this model through an API: 2. Prices per million tokens, cheapest first.
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call GPT-4 through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-4", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="openai/gpt-4",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "openai/gpt-4",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$33.00
- Summarise a 100-page document$1.56
- An app with 10,000 requests a day for a month$16,200
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
Claude Opus 4.1Anthropic | $15 | $75 | 200K | Compare with ⇄ |
Fugu Ultra v2Sakana AI | $5 | $30 | 1M | Compare with ⇄ |
MiMo-V2.6-Pro-UltraSpeedXiaomi | $4.35 | $8.70 | 1M | Compare with ⇄ |
Qwen3.8 Max PrimeAlibaba Qwen | $4 | $12 | 1M | Compare with ⇄ |
Ember-1Fireworks AI | $3 | $15 | 1M | Compare with ⇄ |
Aion 3.5Aion Labs | $3 | $6 | 256K | Compare with ⇄ |
News about OpenAI
See all →Frequently asked questions
- How much does GPT-4 cost?
- GPT-4 costs $30 per million input tokens and $60 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $33.00.
- What is the context window of GPT-4?
- GPT-4 can read up to 8,191 tokens in one request, about 15 pages of text. It can write up to 4,096 tokens in a single answer.
- Is GPT-4 open source?
- No. GPT-4 is a closed model: its weights are not published, so you use it through OpenAI’s own apps and API, or through cloud providers.
- Who makes GPT-4?
- GPT-4 is made by OpenAI. It became available through the API on May 28, 2023.
- How good is GPT-4?
- GPT-4 has an overall index of 125.9 in Epoch AI’s independent tests, ranking #123 of 136 models we track.
- Can GPT-4 read images?
- No. GPT-4 only accepts text as input.
- What are the alternatives to GPT-4?
- Models with a similar price from other companies include Claude Opus 4.1, Fugu Ultra v2 and MiMo-V2.6-Pro-UltraSpeed. You can compare them side by side on this page.